From 102ae2ca672f1ff69504f2c1578c7a9080216d35 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=8E=98=E6=9D=83=20=E9=A9=AC?= Date: Mon, 8 Jan 2024 22:15:43 +0800 Subject: [PATCH 01/61] feat: Implementation of ProjectRepo --- metagpt/const.py | 14 ++-- metagpt/utils/file_repository.py | 66 ------------------ metagpt/utils/project_repo.py | 87 ++++++++++++++++++++++++ tests/metagpt/utils/test_project_repo.py | 58 ++++++++++++++++ 4 files changed, 152 insertions(+), 73 deletions(-) create mode 100644 metagpt/utils/project_repo.py create mode 100644 tests/metagpt/utils/test_project_repo.py diff --git a/metagpt/const.py b/metagpt/const.py index 811ff9516..581aff5d3 100644 --- a/metagpt/const.py +++ b/metagpt/const.py @@ -89,23 +89,23 @@ BUGFIX_FILENAME = "bugfix.txt" PACKAGE_REQUIREMENTS_FILENAME = "requirements.txt" DOCS_FILE_REPO = "docs" -PRDS_FILE_REPO = "docs/prds" +PRDS_FILE_REPO = "docs/prd" SYSTEM_DESIGN_FILE_REPO = "docs/system_design" -TASK_FILE_REPO = "docs/tasks" +TASK_FILE_REPO = "docs/task" COMPETITIVE_ANALYSIS_FILE_REPO = "resources/competitive_analysis" DATA_API_DESIGN_FILE_REPO = "resources/data_api_design" SEQ_FLOW_FILE_REPO = "resources/seq_flow" SYSTEM_DESIGN_PDF_FILE_REPO = "resources/system_design" PRD_PDF_FILE_REPO = "resources/prd" -TASK_PDF_FILE_REPO = "resources/api_spec_and_tasks" +TASK_PDF_FILE_REPO = "resources/api_spec_and_task" TEST_CODES_FILE_REPO = "tests" TEST_OUTPUTS_FILE_REPO = "test_outputs" -CODE_SUMMARIES_FILE_REPO = "docs/code_summaries" -CODE_SUMMARIES_PDF_FILE_REPO = "resources/code_summaries" +CODE_SUMMARIES_FILE_REPO = "docs/code_summary" +CODE_SUMMARIES_PDF_FILE_REPO = "resources/code_summary" RESOURCES_FILE_REPO = "resources" -SD_OUTPUT_FILE_REPO = "resources/SD_Output" +SD_OUTPUT_FILE_REPO = "resources/sd_output" GRAPH_REPO_FILE_REPO = "docs/graph_repo" -CLASS_VIEW_FILE_REPO = "docs/class_views" +CLASS_VIEW_FILE_REPO = "docs/class_view" YAPI_URL = "http://yapi.deepwisdomai.com/" diff --git a/metagpt/utils/file_repository.py b/metagpt/utils/file_repository.py index 3b5f5c5ac..01b78cd77 100644 --- a/metagpt/utils/file_repository.py +++ b/metagpt/utils/file_repository.py @@ -202,68 +202,6 @@ class FileRepository: await self.save(filename=str(filename), content=json_to_markdown(m), dependencies=dependencies) logger.debug(f"File Saved: {str(filename)}") - async def get_file(self, filename: Path | str, relative_path: Path | str = ".") -> Document | None: - """Retrieve a specific file from the file repository. - - :param filename: The name or path of the file to retrieve. - :type filename: Path or str - :param relative_path: The relative path within the file repository. - :type relative_path: Path or str, optional - :return: The document representing the file, or None if not found. - :rtype: Document or None - """ - file_repo = self._git_repo.new_file_repository(relative_path=relative_path) - return await file_repo.get(filename=filename) - - async def get_all_files(self, relative_path: Path | str = ".") -> List[Document]: - """Retrieve all files from the file repository. - - :param relative_path: The relative path within the file repository. - :type relative_path: Path or str, optional - :return: A list of documents representing all files in the repository. - :rtype: List[Document] - """ - file_repo = self._git_repo.new_file_repository(relative_path=relative_path) - return await file_repo.get_all() - - async def save_file( - self, filename: Path | str, content, dependencies: List[str] = None, relative_path: Path | str = "." - ): - """Save a file to the file repository. - - :param filename: The name or path of the file to save. - :type filename: Path or str - :param content: The content of the file. - :param dependencies: A list of dependencies for the file. - :type dependencies: List[str], optional - :param relative_path: The relative path within the file repository. - :type relative_path: Path or str, optional - """ - file_repo = self._git_repo.new_file_repository(relative_path=relative_path) - return await file_repo.save(filename=filename, content=content, dependencies=dependencies) - - async def save_as( - self, doc: Document, with_suffix: str = None, dependencies: List[str] = None, relative_path: Path | str = "." - ): - """Save a Document instance with optional modifications. - - This static method creates a new FileRepository, saves the Document instance - with optional modifications (such as a suffix), and logs the saved file. - - :param doc: The Document instance to be saved. - :type doc: Document - :param with_suffix: An optional suffix to append to the saved file's name. - :type with_suffix: str, optional - :param dependencies: A list of dependencies for the saved file. - :type dependencies: List[str], optional - :param relative_path: The relative path within the file repository. - :type relative_path: Path or str, optional - :return: A boolean indicating whether the save operation was successful. - :rtype: bool - """ - file_repo = self._git_repo.new_file_repository(relative_path=relative_path) - return await file_repo.save_doc(doc=doc, with_suffix=with_suffix, dependencies=dependencies) - async def delete(self, filename: Path | str): """Delete a file from the file repository. @@ -280,7 +218,3 @@ class FileRepository: dependency_file = await self._git_repo.get_dependency() await dependency_file.update(filename=pathname, dependencies=None) logger.info(f"remove dependency key: {str(pathname)}") - - async def delete_file(self, filename: Path | str, relative_path: Path | str = "."): - file_repo = self._git_repo.new_file_repository(relative_path=relative_path) - await file_repo.delete(filename=filename) diff --git a/metagpt/utils/project_repo.py b/metagpt/utils/project_repo.py new file mode 100644 index 000000000..deedd6c03 --- /dev/null +++ b/metagpt/utils/project_repo.py @@ -0,0 +1,87 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +""" +@Time : 2024/1/8 +@Author : mashenquan +@File : project_repo.py +@Desc : Wrapper for GitRepository and FileRepository of project. + Implementation of Chapter 4.6 of https://deepwisdom.feishu.cn/wiki/CUK4wImd7id9WlkQBNscIe9cnqh +""" +from __future__ import annotations + +from pathlib import Path + +from metagpt.const import ( + CLASS_VIEW_FILE_REPO, + CODE_SUMMARIES_FILE_REPO, + CODE_SUMMARIES_PDF_FILE_REPO, + COMPETITIVE_ANALYSIS_FILE_REPO, + DATA_API_DESIGN_FILE_REPO, + GRAPH_REPO_FILE_REPO, + PRD_PDF_FILE_REPO, + PRDS_FILE_REPO, + SD_OUTPUT_FILE_REPO, + SEQ_FLOW_FILE_REPO, + SYSTEM_DESIGN_FILE_REPO, + SYSTEM_DESIGN_PDF_FILE_REPO, + TASK_FILE_REPO, + TASK_PDF_FILE_REPO, + TEST_CODES_FILE_REPO, + TEST_OUTPUTS_FILE_REPO, +) +from metagpt.utils.file_repository import FileRepository +from metagpt.utils.git_repository import GitRepository + + +class DocFileRepositories: + prd: FileRepository + system_design: FileRepository + task: FileRepository + code_summary: FileRepository + graph_repo: FileRepository + class_view: FileRepository + + def __init__(self, git_repo): + self.prd = git_repo.new_file_repository(relative_path=PRDS_FILE_REPO) + self.system_design = git_repo.new_file_repository(relative_path=SYSTEM_DESIGN_FILE_REPO) + self.task = git_repo.new_file_repository(relative_path=TASK_FILE_REPO) + self.code_summary = git_repo.new_file_repository(relative_path=CODE_SUMMARIES_FILE_REPO) + self.graph_repo = git_repo.new_file_repository(relative_path=GRAPH_REPO_FILE_REPO) + self.class_view = git_repo.new_file_repository(relative_path=CLASS_VIEW_FILE_REPO) + + +class ResourceFileRepositories: + competitive_analysis: FileRepository + data_api_design: FileRepository + seq_flow: FileRepository + system_design: FileRepository + prd: FileRepository + api_spec_and_task: FileRepository + code_summary: FileRepository + sd_output: FileRepository + + def __init__(self, git_repo): + self.competitive_analysis = git_repo.new_file_repository(relative_path=COMPETITIVE_ANALYSIS_FILE_REPO) + self.data_api_design = git_repo.new_file_repository(relative_path=DATA_API_DESIGN_FILE_REPO) + self.seq_flow = git_repo.new_file_repository(relative_path=SEQ_FLOW_FILE_REPO) + self.system_design = git_repo.new_file_repository(relative_path=SYSTEM_DESIGN_PDF_FILE_REPO) + self.prd = git_repo.new_file_repository(relative_path=PRD_PDF_FILE_REPO) + self.api_spec_and_task = git_repo.new_file_repository(relative_path=TASK_PDF_FILE_REPO) + self.code_summary = git_repo.new_file_repository(relative_path=CODE_SUMMARIES_PDF_FILE_REPO) + self.sd_output = git_repo.new_file_repository(relative_path=SD_OUTPUT_FILE_REPO) + + +class ProjectRepo(FileRepository): + def __init__(self, root: str | Path): + git_repo = GitRepository(local_path=Path(root)) + super().__init__(git_repo=git_repo, relative_path=Path(".")) + + self._git_repo = git_repo + self.docs = DocFileRepositories(self._git_repo) + self.resources = ResourceFileRepositories(self._git_repo) + self.tests = self._git_repo.new_file_repository(relative_path=TEST_CODES_FILE_REPO) + self.test_outputs = self._git_repo.new_file_repository(relative_path=TEST_OUTPUTS_FILE_REPO) + + @property + def git_repo(self): + return self._git_repo diff --git a/tests/metagpt/utils/test_project_repo.py b/tests/metagpt/utils/test_project_repo.py new file mode 100644 index 000000000..6f80fbc14 --- /dev/null +++ b/tests/metagpt/utils/test_project_repo.py @@ -0,0 +1,58 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +""" +@Time : 2024/1/8 +@Author : mashenquan +""" +import uuid +from pathlib import Path + +import pytest + +from metagpt.const import ( + BUGFIX_FILENAME, + PACKAGE_REQUIREMENTS_FILENAME, + PRDS_FILE_REPO, + REQUIREMENT_FILENAME, +) +from metagpt.utils.project_repo import ProjectRepo + + +async def test_project_repo(): + root = Path(__file__).parent / f"../../../workspace/unittest/{uuid.uuid4().hex}" + root = root.resolve() + + pr = ProjectRepo(root=str(root)) + assert pr.git_repo.workdir == root + + await pr.save(filename=REQUIREMENT_FILENAME, content=REQUIREMENT_FILENAME) + doc = await pr.get(filename=REQUIREMENT_FILENAME) + assert doc.content == REQUIREMENT_FILENAME + await pr.save(filename=BUGFIX_FILENAME, content=BUGFIX_FILENAME) + doc = await pr.get(filename=BUGFIX_FILENAME) + assert doc.content == BUGFIX_FILENAME + await pr.save(filename=PACKAGE_REQUIREMENTS_FILENAME, content=PACKAGE_REQUIREMENTS_FILENAME) + doc = await pr.get(filename=PACKAGE_REQUIREMENTS_FILENAME) + assert doc.content == PACKAGE_REQUIREMENTS_FILENAME + await pr.docs.prd.save(filename="1.prd", content="1.prd", dependencies=[REQUIREMENT_FILENAME]) + doc = await pr.docs.prd.get(filename="1.prd") + assert doc.content == "1.prd" + await pr.resources.prd.save( + filename="1.prd", + content="1.prd", + dependencies=[REQUIREMENT_FILENAME, f"{PRDS_FILE_REPO}/1.prd"], + ) + doc = await pr.resources.prd.get(filename="1.prd") + assert doc.content == "1.prd" + dependencies = await pr.resources.prd.get_dependency(filename="1.prd") + assert len(dependencies) == 2 + + assert pr.changed_files + assert pr.docs.prd.changed_files + assert not pr.tests.changed_files + + pr.git_repo.delete_repository() + + +if __name__ == "__main__": + pytest.main([__file__, "-s"]) From 662102d188227259a7702fbbe45da63c11168599 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=8E=98=E6=9D=83=20=E9=A9=AC?= Date: Thu, 11 Jan 2024 10:55:54 +0800 Subject: [PATCH 02/61] feat: save + return --- metagpt/utils/file_repository.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/metagpt/utils/file_repository.py b/metagpt/utils/file_repository.py index 01b78cd77..1cb347a19 100644 --- a/metagpt/utils/file_repository.py +++ b/metagpt/utils/file_repository.py @@ -45,7 +45,7 @@ class FileRepository: # Initializing self.workdir.mkdir(parents=True, exist_ok=True) - async def save(self, filename: Path | str, content, dependencies: List[str] = None): + async def save(self, filename: Path | str, content, dependencies: List[str] = None) -> Document: """Save content to a file and update its dependencies. :param filename: The filename or path within the repository. @@ -63,6 +63,8 @@ class FileRepository: await dependency_file.update(pathname, set(dependencies)) logger.info(f"update dependency: {str(pathname)}:{dependencies}") + return Document(root_path=str(self._relative_path), filename=filename, content=content) + async def get_dependency(self, filename: Path | str) -> Set[str]: """Get the dependencies of a file. From 68e53d2862edebc65ee8ff380510f76bf3708985 Mon Sep 17 00:00:00 2001 From: better629 Date: Mon, 8 Jan 2024 16:09:14 +0800 Subject: [PATCH 03/61] add ActionNode review/revise --- metagpt/actions/action_node.py | 259 +++++++++++++++++- metagpt/utils/human_interaction.py | 107 ++++++++ tests/metagpt/actions/test_action_node.py | 87 +++++- tests/metagpt/utils/test_human_interaction.py | 74 +++++ 4 files changed, 520 insertions(+), 7 deletions(-) create mode 100644 metagpt/utils/human_interaction.py create mode 100644 tests/metagpt/utils/test_human_interaction.py diff --git a/metagpt/actions/action_node.py b/metagpt/actions/action_node.py index 633fc9841..8577338b6 100644 --- a/metagpt/actions/action_node.py +++ b/metagpt/actions/action_node.py @@ -9,7 +9,8 @@ NOTE: You should use typing.List instead of list to do type annotation. Because we can use typing to extract the type of the node, but we cannot use built-in list to extract. """ import json -from typing import Any, Dict, List, Optional, Tuple, Type +from enum import Enum +from typing import Any, Dict, List, Optional, Tuple, Type, Union from pydantic import BaseModel, create_model, model_validator from tenacity import retry, stop_after_attempt, wait_random_exponential @@ -18,6 +19,18 @@ from metagpt.llm import BaseLLM from metagpt.logs import logger from metagpt.provider.postprocess.llm_output_postprocess import llm_output_postprocess from metagpt.utils.common import OutputParser, general_after_log +from metagpt.utils.human_interaction import HumanInteraction + + +class ReviewMode(Enum): + HUMAN = "human" + AUTO = "auto" + + +class ReviseMode(Enum): + HUMAN = "human" + AUTO = "auto" + TAG = "CONTENT" @@ -44,6 +57,58 @@ SIMPLE_TEMPLATE = """ Follow instructions of nodes, generate output and make sure it follows the format example. """ +REVIEW_TEMPLATE = """ +## context +Compare the keys of nodes_output and the corresponding requirements one by one. If a key that does not match the requirement is found, provide the comment content on how to modify it. No output is required for matching keys. + +### nodes_output +{nodes_output} + +----- + +## format example +[{tag}] +{{ + "key1": "comment1", + "key2": "comment2", + "keyn": "commentn" +}} +[/{tag}] + +## nodes: ": # " +- key1: # the first key name of mismatch key +- key2: # the second key name of mismatch key +- keyn: # the last key name of mismatch key + +## constraint +{constraint} + +## action +generate output and make sure it follows the format example. +""" + +REVISE_TEMPLATE = """ +## context +change the nodes_output key's value to meet its comment and no need to add extra comment. + +### nodes_output +{nodes_output} + +----- + +## format example +{example} + +## nodes: ": # " +{instruction} + +## constraint +{constraint} + +## action +generate output and make sure it follows the format example. +""" + def dict_to_markdown(d, prefix="- ", kv_sep="\n", postfix="\n"): markdown_str = "" @@ -104,6 +169,9 @@ class ActionNode: """增加子ActionNode""" self.children[node.key] = node + def get_child(self, key: str) -> Union["ActionNode", None]: + return self.children.get(key, None) + def add_children(self, nodes: List["ActionNode"]): """批量增加子ActionNode""" for node in nodes: @@ -151,6 +219,11 @@ class ActionNode: new_class = create_model(class_name, __validators__=validators, **mapping) return new_class + def create_class(self, mode: str = "auto", class_name: str = None, exclude=None): + class_name = class_name if class_name else f"{self.key}_AN" + mapping = self.get_mapping(mode=mode, exclude=exclude) + return self.create_model_class(class_name, mapping) + def create_children_class(self, exclude=None): """使用object内有的字段直接生成model_class""" class_name = f"{self.key}_AN" @@ -185,6 +258,25 @@ class ActionNode: return node_dict + def update_instruct_content(self, incre_data: dict[str, Any]): + assert self.instruct_content + origin_sc_dict = self.instruct_content.model_dump() + origin_sc_dict.update(incre_data) + output_class = self.create_class() + self.instruct_content = output_class(**origin_sc_dict) + + def keys(self, mode: str = "auto") -> list: + if mode == "children" or (mode == "auto" and self.children): + keys = [] + else: + keys = [self.key] + if mode == "root": + return keys + + for _, child_node in self.children.items(): + keys.append(child_node.key) + return keys + def compile_to(self, i: Dict, schema, kv_sep) -> str: if schema == "json": return json.dumps(i, indent=4) @@ -342,7 +434,170 @@ class ActionNode: if exclude and i.key in exclude: continue child = await i.simple_fill(schema=schema, mode=mode, timeout=timeout, exclude=exclude) - tmp.update(child.instruct_content.dict()) + tmp.update(child.instruct_content.model_dump()) cls = self.create_children_class() self.instruct_content = cls(**tmp) return self + + async def human_review(self) -> dict[str, str]: + review_comments = HumanInteraction().interact_with_instruct_content( + instruct_content=self.instruct_content, interact_type="review" + ) + + return review_comments + + def _makeup_nodes_output_with_req(self) -> dict[str, str]: + instruct_content_dict = self.instruct_content.model_dump() + nodes_output = {} + for key, value in instruct_content_dict.items(): + child = self.get_child(key) + nodes_output[key] = {"value": value, "requirement": child.instruction if child else self.instruction} + return nodes_output + + async def auto_review(self, template: str = REVIEW_TEMPLATE) -> dict[str, str]: + """use key's output value and its instruction to review the modification comment""" + nodes_output = self._makeup_nodes_output_with_req() + """nodes_output format: + { + "key": {"value": "output value", "requirement": "key instruction"} + } + """ + if not nodes_output: + return dict() + + prompt = template.format( + nodes_output=json.dumps(nodes_output, ensure_ascii=False, indent=4), tag=TAG, constraint=FORMAT_CONSTRAINT + ) + + content = await self.llm.aask(prompt) + # Extract the dict of mismatch key and its comment. Due to the mismatch keys are unknown, here use the keys + # of ActionNode to judge if exist in `content` and then follow the `data_mapping` method to create model class. + keys = self.keys() + include_keys = [] + for key in keys: + if f'"{key}":' in content: + include_keys.append(key) + if not include_keys: + return dict() + + exclude_keys = list(set(keys).difference(include_keys)) + output_class_name = f"{self.key}_AN_REVIEW" + output_class = self.create_class(class_name=output_class_name, exclude=exclude_keys) + parsed_data = llm_output_postprocess( + output=content, schema=output_class.model_json_schema(), req_key=f"[/{TAG}]" + ) + instruct_content = output_class(**parsed_data) + return instruct_content.model_dump() + + async def simple_review(self, review_mode: ReviewMode = ReviewMode.AUTO): + # generate review comments + if review_mode == ReviewMode.HUMAN: + review_comments = await self.human_review() + else: + review_comments = await self.auto_review() + + if not review_comments: + logger.warning("There are no review comments") + return review_comments + + async def review(self, strgy: str = "simple", review_mode: ReviewMode = ReviewMode.AUTO): + """only give the review comment of each exist and mismatch key + + :param strgy: simple/complex + - simple: run only once + - complex: run each node + """ + if not hasattr(self, "llm"): + raise RuntimeError("use `review` after `fill`") + assert review_mode in ReviewMode + assert self.instruct_content, 'review only support with `schema != "raw"`' + + if strgy == "simple": + review_comments = await self.simple_review(review_mode) + elif strgy == "complex": + # review each child node one-by-one + review_comments = {} + for _, child in self.children.items(): + child_review_comment = await child.simple_review(review_mode) + review_comments.update(child_review_comment) + + return review_comments + + async def human_revise(self) -> dict[str, str]: + review_contents = HumanInteraction().interact_with_instruct_content( + instruct_content=self.instruct_content, mapping=self.get_mapping(mode="auto"), interact_type="revise" + ) + # re-fill the ActionNode + self.update_instruct_content(review_contents) + return review_contents + + def _makeup_nodes_output_with_comment(self, review_comments: dict[str, str]) -> dict[str, str]: + instruct_content_dict = self.instruct_content.model_dump() + nodes_output = {} + for key, value in instruct_content_dict.items(): + if key in review_comments: + nodes_output[key] = {"value": value, "comment": review_comments[key]} + return nodes_output + + async def auto_revise(self, template: str = REVISE_TEMPLATE) -> dict[str, str]: + """revise the value of incorrect keys""" + # generate review comments + review_comments: dict = await self.auto_review() + include_keys = list(review_comments.keys()) + + # generate revise content + nodes_output = self._makeup_nodes_output_with_comment(review_comments) + keys = self.keys() + exclude_keys = list(set(keys).difference(include_keys)) + example = self.compile_example(schema="json", mode="auto", tag=TAG, exclude=exclude_keys) + instruction = self.compile_instruction(schema="markdown", mode="auto", exclude=exclude_keys) + + prompt = template.format( + nodes_output=json.dumps(nodes_output, ensure_ascii=False, indent=4), + example=example, + instruction=instruction, + constraint=FORMAT_CONSTRAINT, + ) + + output_mapping = self.get_mapping(mode="auto", exclude=exclude_keys) + output_class_name = f"{self.key}_AN_REVISE" + content, scontent = await self._aask_v1( + prompt=prompt, output_class_name=output_class_name, output_data_mapping=output_mapping, schema="json" + ) + + # re-fill the ActionNode + sc_dict = scontent.model_dump() + self.update_instruct_content(sc_dict) + return sc_dict + + async def simple_revise(self, revise_mode: ReviseMode = ReviseMode.AUTO) -> dict[str, str]: + if revise_mode == ReviseMode.HUMAN: + revise_contents = await self.human_revise() + else: + revise_contents = await self.auto_revise() + + return revise_contents + + async def revise(self, strgy: str = "simple", revise_mode: ReviseMode = ReviseMode.AUTO) -> dict[str, str]: + """revise the content of ActionNode and update the instruct_content + + :param strgy: simple/complex + - simple: run only once + - complex: run each node + """ + if not hasattr(self, "llm"): + raise RuntimeError("use `revise` after `fill`") + assert revise_mode in ReviseMode + assert self.instruct_content, 'revise only support with `schema != "raw"`' + + if strgy == "simple": + revise_contents = await self.simple_revise(revise_mode) + elif strgy == "complex": + # revise each child node one-by-one + revise_contents = {} + for _, child in self.children.items(): + child_revise_content = await child.simple_revise(revise_mode) + revise_contents.update(child_revise_content) + self.update_instruct_content(revise_contents) + + return revise_contents diff --git a/metagpt/utils/human_interaction.py b/metagpt/utils/human_interaction.py new file mode 100644 index 000000000..3b245cac8 --- /dev/null +++ b/metagpt/utils/human_interaction.py @@ -0,0 +1,107 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +# @Desc : human interaction to get required type text + +import json +from typing import Any, Tuple, Type + +from pydantic import BaseModel + +from metagpt.logs import logger +from metagpt.utils.common import import_class + + +class HumanInteraction(object): + stop_list = ("q", "quit", "exit") + + def multilines_input(self, prompt: str = "Enter: ") -> str: + logger.warning("Enter your content, use Ctrl-D or Ctrl-Z ( windows ) to save it.") + logger.info(f"{prompt}\n") + lines = [] + while True: + try: + line = input() + lines.append(line) + except EOFError: + break + return "".join(lines) + + def check_input_type(self, input_str: str, req_type: Type) -> Tuple[bool, Any]: + check_ret = True + if req_type == str: + # required_type = str, just return True + return check_ret, input_str + try: + input_str = input_str.strip() + data = json.loads(input_str) + except Exception: + return False, None + + actionnode_class = import_class("ActionNode", "metagpt.actions.action_node") # avoid circular import + tmp_key = "tmp" + tmp_cls = actionnode_class.create_model_class(class_name=tmp_key.upper(), mapping={tmp_key: (req_type, ...)}) + try: + _ = tmp_cls(**{tmp_key: data}) + except Exception: + check_ret = False + return check_ret, data + + def input_until_valid(self, prompt: str, req_type: Type) -> Any: + # check the input with req_type until it's ok + while True: + input_content = self.multilines_input(prompt) + check_ret, structure_content = self.check_input_type(input_content, req_type) + if check_ret: + break + else: + logger.error(f"Input content can't meet required_type: {req_type}, please Re-Enter.") + return structure_content + + def input_num_until_valid(self, num_max: int) -> int: + while True: + input_num = input("Enter the num of the interaction key: ") + input_num = input_num.strip() + if input_num in self.stop_list: + return input_num + try: + input_num = int(input_num) + if 0 <= input_num < num_max: + return input_num + except Exception: + pass + + def interact_with_instruct_content( + self, instruct_content: BaseModel, mapping: dict = dict(), interact_type: str = "review" + ) -> dict[str, Any]: + assert interact_type in ["review", "revise"] + assert instruct_content + instruct_content_dict = instruct_content.model_dump() + num_fields_map = dict(zip(range(0, len(instruct_content_dict)), instruct_content_dict.keys())) + logger.info( + f"\n{interact_type.upper()} interaction\n" + f"Interaction data: {num_fields_map}\n" + f"Enter the num to interact with corresponding field or `q`/`quit`/`exit` to stop interaction.\n" + f"Enter the field content until it meet field required type.\n" + ) + + interact_contents = {} + while True: + input_num = self.input_num_until_valid(len(instruct_content_dict)) + if input_num in self.stop_list: + logger.warning("Stop human interaction") + break + + field = num_fields_map.get(input_num) + logger.info(f"You choose to interact with field: {field}, and do a `{interact_type}` operation.") + + if interact_type == "review": + prompt = "Enter your review comment: " + req_type = str + else: + prompt = "Enter your revise content: " + req_type = mapping.get(field)[0] # revise need input content match the required_type + + field_content = self.input_until_valid(prompt=prompt, req_type=req_type) + interact_contents[field] = field_content + + return interact_contents diff --git a/tests/metagpt/actions/test_action_node.py b/tests/metagpt/actions/test_action_node.py index 384c4507b..fd2c83ac9 100644 --- a/tests/metagpt/actions/test_action_node.py +++ b/tests/metagpt/actions/test_action_node.py @@ -11,7 +11,7 @@ import pytest from pydantic import ValidationError from metagpt.actions import Action -from metagpt.actions.action_node import ActionNode +from metagpt.actions.action_node import ActionNode, ReviewMode, ReviseMode from metagpt.environment import Environment from metagpt.llm import LLM from metagpt.roles import Role @@ -98,6 +98,83 @@ async def test_action_node_two_layer(): assert "579" in answer2.content +@pytest.mark.asyncio +async def test_action_node_review(): + key = "Project Name" + node_a = ActionNode( + key=key, + expected_type=str, + instruction='According to the content of "Original Requirements," name the project using snake case style ' + "with underline, like 'game_2048' or 'simple_crm.", + example="game_2048", + ) + + with pytest.raises(RuntimeError): + _ = await node_a.review() + + _ = await node_a.fill(context=None, llm=LLM()) + setattr(node_a.instruct_content, key, "game snake") # wrong content to review + + review_comments = await node_a.review(review_mode=ReviewMode.AUTO) + assert len(review_comments) == 1 + assert list(review_comments.keys())[0] == key + + review_comments = await node_a.review(strgy="complex", review_mode=ReviewMode.AUTO) + assert len(review_comments) == 0 + + node = ActionNode.from_children(key="WritePRD", nodes=[node_a]) + with pytest.raises(RuntimeError): + _ = await node.review() + + _ = await node.fill(context=None, llm=LLM()) + + review_comments = await node.review(review_mode=ReviewMode.AUTO) + assert len(review_comments) == 1 + assert list(review_comments.keys())[0] == key + + review_comments = await node.review(strgy="complex", review_mode=ReviewMode.AUTO) + assert len(review_comments) == 1 + assert list(review_comments.keys())[0] == key + + +@pytest.mark.asyncio +async def test_action_node_revise(): + key = "Project Name" + node_a = ActionNode( + key=key, + expected_type=str, + instruction='According to the content of "Original Requirements," name the project using snake case style ' + "with underline, like 'game_2048' or 'simple_crm.", + example="game_2048", + ) + + with pytest.raises(RuntimeError): + _ = await node_a.review() + + _ = await node_a.fill(context=None, llm=LLM()) + setattr(node_a.instruct_content, key, "game snake") # wrong content to revise + revise_contents = await node_a.revise(revise_mode=ReviseMode.AUTO) + assert len(revise_contents) == 1 + assert "game_snake" in getattr(node_a.instruct_content, key) + + revise_contents = await node_a.revise(strgy="complex", revise_mode=ReviseMode.AUTO) + assert len(revise_contents) == 0 + + node = ActionNode.from_children(key="WritePRD", nodes=[node_a]) + with pytest.raises(RuntimeError): + _ = await node.revise() + + _ = await node.fill(context=None, llm=LLM()) + setattr(node.instruct_content, key, "game snake") + revise_contents = await node.revise(revise_mode=ReviseMode.AUTO) + assert len(revise_contents) == 1 + assert "game_snake" in getattr(node.instruct_content, key) + + revise_contents = await node.revise(strgy="complex", revise_mode=ReviseMode.AUTO) + assert len(revise_contents) == 1 + assert "game_snake" in getattr(node.instruct_content, key) + + t_dict = { "Required Python third-party packages": '"""\nflask==1.1.2\npygame==2.0.1\n"""\n', "Required Other language third-party packages": '"""\nNo third-party packages required for other languages.\n"""\n', @@ -138,10 +215,10 @@ def test_create_model_class(): assert test_class.__name__ == "test_class" output = test_class(**t_dict) - print(output.schema()) - assert output.schema()["title"] == "test_class" - assert output.schema()["type"] == "object" - assert output.schema()["properties"]["Full API spec"] + print(output.model_json_schema()) + assert output.model_json_schema()["title"] == "test_class" + assert output.model_json_schema()["type"] == "object" + assert output.model_json_schema()["properties"]["Full API spec"] def test_create_model_class_with_fields_unrecognized(): diff --git a/tests/metagpt/utils/test_human_interaction.py b/tests/metagpt/utils/test_human_interaction.py new file mode 100644 index 000000000..038fc0d98 --- /dev/null +++ b/tests/metagpt/utils/test_human_interaction.py @@ -0,0 +1,74 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +# @Desc : unittest of human_interaction + +import pytest + +from pydantic import BaseModel + +from metagpt.utils.human_interaction import HumanInteraction + + +class InstructContent(BaseModel): + test_field1: str = "" + test_field2: list[str] = [] + + +data_mapping = { + "test_field1": (str, ...), + "test_field2": (list[str], ...) +} + +human_interaction = HumanInteraction() + + +def test_input_num(mocker): + mocker.patch("builtins.input", lambda _: "quit") + + interact_contents = human_interaction.interact_with_instruct_content(InstructContent(), data_mapping) + assert len(interact_contents) == 0 + + mocker.patch("builtins.input", lambda _: "1") + input_num = human_interaction.input_num_until_valid(2) + assert input_num == 1 + + +def test_check_input_type(): + ret, _ = human_interaction.check_input_type(input_str="test string", + req_type=str) + assert ret + + ret, _ = human_interaction.check_input_type(input_str='["test string"]', + req_type=list[str]) + assert ret + + ret, _ = human_interaction.check_input_type(input_str='{"key", "value"}', + req_type=list[str]) + assert not ret + + +global_index = 0 + + +def mock_input(*args, **kwargs): + """there are multi input call, return it by global_index""" + arr = ["1", '["test"]', "ignore", "quit"] + global global_index + global_index += 1 + if global_index == 3: + raise EOFError() + val = arr[global_index-1] + return val + + +def test_human_interact_valid_content(mocker): + mocker.patch("builtins.input", mock_input) + input_contents = HumanInteraction().interact_with_instruct_content(InstructContent(), data_mapping, "review") + assert len(input_contents) == 1 + assert input_contents["test_field2"] == '["test"]' + + global global_index + global_index = 0 + input_contents = HumanInteraction().interact_with_instruct_content(InstructContent(), data_mapping, "revise") + assert len(input_contents) == 1 + assert input_contents["test_field2"] == ["test"] From 09e82e488d13edf5a10ce0ae93dd7c4148e30eee Mon Sep 17 00:00:00 2001 From: better629 Date: Mon, 8 Jan 2024 16:23:46 +0800 Subject: [PATCH 04/61] fix format --- tests/metagpt/utils/test_human_interaction.py | 18 +++++------------- 1 file changed, 5 insertions(+), 13 deletions(-) diff --git a/tests/metagpt/utils/test_human_interaction.py b/tests/metagpt/utils/test_human_interaction.py index 038fc0d98..24dbac61c 100644 --- a/tests/metagpt/utils/test_human_interaction.py +++ b/tests/metagpt/utils/test_human_interaction.py @@ -2,8 +2,6 @@ # -*- coding: utf-8 -*- # @Desc : unittest of human_interaction -import pytest - from pydantic import BaseModel from metagpt.utils.human_interaction import HumanInteraction @@ -14,10 +12,7 @@ class InstructContent(BaseModel): test_field2: list[str] = [] -data_mapping = { - "test_field1": (str, ...), - "test_field2": (list[str], ...) -} +data_mapping = {"test_field1": (str, ...), "test_field2": (list[str], ...)} human_interaction = HumanInteraction() @@ -34,16 +29,13 @@ def test_input_num(mocker): def test_check_input_type(): - ret, _ = human_interaction.check_input_type(input_str="test string", - req_type=str) + ret, _ = human_interaction.check_input_type(input_str="test string", req_type=str) assert ret - ret, _ = human_interaction.check_input_type(input_str='["test string"]', - req_type=list[str]) + ret, _ = human_interaction.check_input_type(input_str='["test string"]', req_type=list[str]) assert ret - ret, _ = human_interaction.check_input_type(input_str='{"key", "value"}', - req_type=list[str]) + ret, _ = human_interaction.check_input_type(input_str='{"key", "value"}', req_type=list[str]) assert not ret @@ -57,7 +49,7 @@ def mock_input(*args, **kwargs): global_index += 1 if global_index == 3: raise EOFError() - val = arr[global_index-1] + val = arr[global_index - 1] return val From 54373154880474598ebf74649c68d5952f33fc9f Mon Sep 17 00:00:00 2001 From: better629 Date: Mon, 8 Jan 2024 17:35:28 +0800 Subject: [PATCH 05/61] add revise_mode=HUMAN_REVIEW to support human_review and auto_revise --- metagpt/actions/action_node.py | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/metagpt/actions/action_node.py b/metagpt/actions/action_node.py index 8577338b6..7971ef56d 100644 --- a/metagpt/actions/action_node.py +++ b/metagpt/actions/action_node.py @@ -28,8 +28,9 @@ class ReviewMode(Enum): class ReviseMode(Enum): - HUMAN = "human" - AUTO = "auto" + HUMAN = "human" # human revise + HUMAN_REVIEW = "human_review" # human-review and auto-revise + AUTO = "auto" # auto-review and auto-revise TAG = "CONTENT" @@ -539,10 +540,16 @@ class ActionNode: nodes_output[key] = {"value": value, "comment": review_comments[key]} return nodes_output - async def auto_revise(self, template: str = REVISE_TEMPLATE) -> dict[str, str]: + async def auto_revise( + self, revise_mode: ReviseMode = ReviseMode.AUTO, template: str = REVISE_TEMPLATE + ) -> dict[str, str]: """revise the value of incorrect keys""" # generate review comments - review_comments: dict = await self.auto_review() + if revise_mode == ReviseMode.AUTO: + review_comments: dict = await self.auto_review() + elif revise_mode == ReviseMode.HUMAN_REVIEW: + review_comments: dict = await self.human_review() + include_keys = list(review_comments.keys()) # generate revise content @@ -574,7 +581,7 @@ class ActionNode: if revise_mode == ReviseMode.HUMAN: revise_contents = await self.human_revise() else: - revise_contents = await self.auto_revise() + revise_contents = await self.auto_revise(revise_mode) return revise_contents From 58f48b9cc1e06de83da075bc089a8287a987eb34 Mon Sep 17 00:00:00 2001 From: better629 Date: Mon, 8 Jan 2024 22:21:21 +0800 Subject: [PATCH 06/61] add detail revise comments --- metagpt/actions/action_node.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/metagpt/actions/action_node.py b/metagpt/actions/action_node.py index 7971ef56d..286cf534d 100644 --- a/metagpt/actions/action_node.py +++ b/metagpt/actions/action_node.py @@ -552,7 +552,8 @@ class ActionNode: include_keys = list(review_comments.keys()) - # generate revise content + # generate revise content, two-steps + # step1, find the needed revise keys from review comments to makeup prompt template nodes_output = self._makeup_nodes_output_with_comment(review_comments) keys = self.keys() exclude_keys = list(set(keys).difference(include_keys)) @@ -566,6 +567,7 @@ class ActionNode: constraint=FORMAT_CONSTRAINT, ) + # step2, use `_aask_v1` to get revise structure result output_mapping = self.get_mapping(mode="auto", exclude=exclude_keys) output_class_name = f"{self.key}_AN_REVISE" content, scontent = await self._aask_v1( From 62677c37b7e60cad0569c9fb0e85092d361a84fe Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 14:16:32 +0800 Subject: [PATCH 07/61] add context tests --- metagpt/config2.py | 24 ++++++++++++- metagpt/context.py | 40 +++++++++++----------- tests/metagpt/test_context.py | 63 +++++++++++++++++++++++++++++++++++ 3 files changed, 105 insertions(+), 22 deletions(-) create mode 100644 tests/metagpt/test_context.py diff --git a/metagpt/config2.py b/metagpt/config2.py index a6aa62f6b..9c809e559 100644 --- a/metagpt/config2.py +++ b/metagpt/config2.py @@ -3,7 +3,7 @@ """ @Time : 2024/1/4 01:25 @Author : alexanderwu -@File : llm_factory.py +@File : config2.py """ import os from pathlib import Path @@ -23,6 +23,8 @@ from metagpt.utils.yaml_model import YamlModel class CLIParams(BaseModel): + """CLI parameters""" + project_path: str = "" project_name: str = "" inc: bool = False @@ -32,12 +34,15 @@ class CLIParams(BaseModel): @model_validator(mode="after") def check_project_path(self): + """Check project_path and project_name""" if self.project_path: self.inc = True self.project_name = self.project_name or Path(self.project_path).name class Config(CLIParams, YamlModel): + """Configurations for MetaGPT""" + # Key Parameters llm: Dict[str, LLMConfig] = Field(default_factory=Dict) @@ -133,4 +138,21 @@ def merge_dict(dicts: Iterable[Dict]) -> Dict: return result +class ConfigurableMixin: + """Mixin class for configurable objects""" + + def __init__(self, config=None): + self._config = config + + def try_set_parent_config(self, parent_config): + """Try to set parent config if not set""" + if self._config is None: + self._config = parent_config + + @property + def config(self): + """Get config""" + return self._config + + config = Config.default() diff --git a/metagpt/context.py b/metagpt/context.py index 0ea5d6046..e396de7e1 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -9,6 +9,8 @@ import os from pathlib import Path from typing import Optional +from pydantic import BaseModel, ConfigDict + from metagpt.config2 import Config from metagpt.configs.llm_config import LLMType from metagpt.const import OPTIONS @@ -18,28 +20,33 @@ from metagpt.utils.cost_manager import CostManager from metagpt.utils.git_repository import GitRepository -class AttrDict: - """A dict-like object that allows access to keys as attributes.""" +class AttrDict(BaseModel): + """A dict-like object that allows access to keys as attributes, compatible with Pydantic.""" - def __init__(self, d=None): - if d is None: - d = {} - self.__dict__["_dict"] = d + model_config = ConfigDict(extra="allow") + + def __init__(self, **kwargs): + super().__init__(**kwargs) + self.__dict__.update(kwargs) def __getattr__(self, key): - return self._dict.get(key, None) + return self.__dict__.get(key, None) def __setattr__(self, key, value): - self._dict[key] = value + self.__dict__[key] = value def __delattr__(self, key): - if key in self._dict: - del self._dict[key] + if key in self.__dict__: + del self.__dict__[key] else: raise AttributeError(f"No such attribute: {key}") -class Context: +class Context(BaseModel): + """Env context for MetaGPT""" + + model_config = ConfigDict(arbitrary_types_allowed=True) + kwargs: AttrDict = AttrDict() config: Config = Config.default() git_repo: Optional[GitRepository] = None @@ -82,14 +89,5 @@ class Context: return llm -# Global context +# Global context, not in Env context = Context() - - -if __name__ == "__main__": - # print(context.model_dump_json(indent=4)) - # print(context.config.get_openai_llm()) - ad = AttrDict({"name": "John", "age": 30}) - - print(ad.name) # Output: John - print(ad.height) # Output: None (因为height不存在) diff --git a/tests/metagpt/test_context.py b/tests/metagpt/test_context.py new file mode 100644 index 000000000..d4f29e352 --- /dev/null +++ b/tests/metagpt/test_context.py @@ -0,0 +1,63 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +""" +@Time : 2024/1/9 13:52 +@Author : alexanderwu +@File : test_context.py +""" +from metagpt.configs.llm_config import LLMType +from metagpt.context import AttrDict, Context, context + + +def test_attr_dict_1(): + ad = AttrDict(name="John", age=30) + assert ad.name == "John" + assert ad.age == 30 + assert ad.height is None + + +def test_attr_dict_2(): + ad = AttrDict(name="John", age=30) + ad.height = 180 + assert ad.height == 180 + + +def test_attr_dict_3(): + ad = AttrDict(name="John", age=30) + del ad.age + assert ad.age is None + + +def test_attr_dict_4(): + ad = AttrDict(name="John", age=30) + try: + del ad.weight + except AttributeError as e: + assert str(e) == "No such attribute: weight" + + +def test_attr_dict_5(): + ad = AttrDict.model_validate({"name": "John", "age": 30}) + assert ad.name == "John" + assert ad.age == 30 + + +def test_context_1(): + ctx = Context() + assert ctx.config is not None + assert ctx.git_repo is None + assert ctx.src_workspace is None + assert ctx.cost_manager is not None + assert ctx.options is not None + + +def test_context_2(): + llm = context.config.get_openai_llm() + assert llm is not None + assert llm.api_type == LLMType.OPENAI + + kwargs = context.kwargs + assert kwargs is not None + + kwargs.test_key = "test_value" + assert kwargs.test_key == "test_value" From cc893914c4d8465cb368ff6c353b2881050485df Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 15:56:40 +0800 Subject: [PATCH 08/61] llm config mixin update --- metagpt/config2.py | 23 ++++++++-- metagpt/context.py | 51 +++++++++++++---------- metagpt/provider/base_llm.py | 1 + metagpt/provider/llm_provider_registry.py | 2 +- tests/metagpt/test_context.py | 9 ++++ 5 files changed, 61 insertions(+), 25 deletions(-) diff --git a/metagpt/config2.py b/metagpt/config2.py index 9c809e559..230e090af 100644 --- a/metagpt/config2.py +++ b/metagpt/config2.py @@ -101,7 +101,7 @@ class Config(CLIParams, YamlModel): self.reqa_file = reqa_file self.max_auto_summarize_code = max_auto_summarize_code - def get_llm_config(self, name: Optional[str] = None) -> LLMConfig: + def _get_llm_config(self, name: Optional[str] = None) -> LLMConfig: """Get LLM instance by name""" if name is None: # Use the first LLM as default @@ -121,6 +121,21 @@ class Config(CLIParams, YamlModel): return llm[0] return None + def get_llm_config(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> LLMConfig: + """Return a LLMConfig instance""" + if provider: + llm_configs = self.get_llm_configs_by_type(provider) + if name: + llm_configs = [c for c in llm_configs if c.name == name] + + if len(llm_configs) == 0: + raise ValueError(f"Cannot find llm config with name {name} and provider {provider}") + # return the first one if name is None, or return the only one + llm_config = llm_configs[0] + else: + llm_config = self._get_llm_config(name) + return llm_config + def get_openai_llm(self) -> Optional[LLMConfig]: """Get OpenAI LLMConfig by name. If no OpenAI, raise Exception""" return self.get_llm_config_by_type(LLMType.OPENAI) @@ -138,10 +153,12 @@ def merge_dict(dicts: Iterable[Dict]) -> Dict: return result -class ConfigurableMixin: +class ConfigMixin: """Mixin class for configurable objects""" - def __init__(self, config=None): + _config: Optional[Config] = None + + def __init__(self, config: Optional[Config] = None): self._config = config def try_set_parent_config(self, parent_config): diff --git a/metagpt/context.py b/metagpt/context.py index e396de7e1..3505614bb 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -12,10 +12,10 @@ from typing import Optional from pydantic import BaseModel, ConfigDict from metagpt.config2 import Config -from metagpt.configs.llm_config import LLMType +from metagpt.configs.llm_config import LLMConfig, LLMType from metagpt.const import OPTIONS from metagpt.provider.base_llm import BaseLLM -from metagpt.provider.llm_provider_registry import get_llm +from metagpt.provider.llm_provider_registry import create_llm_instance from metagpt.utils.cost_manager import CostManager from metagpt.utils.git_repository import GitRepository @@ -42,7 +42,26 @@ class AttrDict(BaseModel): raise AttributeError(f"No such attribute: {key}") -class Context(BaseModel): +class LLMMixin: + config: Optional[Config] = None + llm_config: Optional[LLMConfig] = None + _llm_instance: Optional[BaseLLM] = None + + def use_llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI): + # 更新LLM配置 + self.llm_config = self.config.get_llm_config(name, provider) + # 重置LLM实例 + self._llm_instance = None + + @property + def llm(self) -> BaseLLM: + # 实例化LLM，如果尚未实例化 + if not self._llm_instance and self.llm_config: + self._llm_instance = create_llm_instance(self.llm_config) + return self._llm_instance + + +class Context(LLMMixin, BaseModel): """Env context for MetaGPT""" model_config = ConfigDict(arbitrary_types_allowed=True) @@ -69,24 +88,14 @@ class Context(BaseModel): env.update({k: v for k, v in i.items() if isinstance(v, str)}) return env - def llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: - """Return a LLM instance""" - if provider: - llm_configs = self.config.get_llm_configs_by_type(provider) - if name: - llm_configs = [c for c in llm_configs if c.name == name] - - if len(llm_configs) == 0: - raise ValueError(f"Cannot find llm config with name {name} and provider {provider}") - # return the first one if name is None, or return the only one - llm_config = llm_configs[0] - else: - llm_config = self.config.get_llm_config(name) - - llm = get_llm(llm_config) - if llm.cost_manager is None: - llm.cost_manager = self.cost_manager - return llm + # def llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: + # """Return a LLM instance""" + # llm_config = self.config.get_llm_config(name, provider) + # + # llm = create_llm_instance(llm_config) + # if llm.cost_manager is None: + # llm.cost_manager = self.cost_manager + # return llm # Global context, not in Env diff --git a/metagpt/provider/base_llm.py b/metagpt/provider/base_llm.py index 3c6c464dc..b9847850e 100644 --- a/metagpt/provider/base_llm.py +++ b/metagpt/provider/base_llm.py @@ -27,6 +27,7 @@ class BaseLLM(ABC): # OpenAI / Azure / Others aclient: Optional[Union[AsyncOpenAI]] = None cost_manager: Optional[CostManager] = None + model: Optional[str] = None @abstractmethod def __init__(self, config: LLMConfig): diff --git a/metagpt/provider/llm_provider_registry.py b/metagpt/provider/llm_provider_registry.py index 2f68f27c8..df89d36aa 100644 --- a/metagpt/provider/llm_provider_registry.py +++ b/metagpt/provider/llm_provider_registry.py @@ -31,7 +31,7 @@ def register_provider(key): return decorator -def get_llm(config: LLMConfig) -> BaseLLM: +def create_llm_instance(config: LLMConfig) -> BaseLLM: """get the default llm provider""" return LLM_REGISTRY.get_provider(config.api_type)(config) diff --git a/tests/metagpt/test_context.py b/tests/metagpt/test_context.py index d4f29e352..2d52325bc 100644 --- a/tests/metagpt/test_context.py +++ b/tests/metagpt/test_context.py @@ -61,3 +61,12 @@ def test_context_2(): kwargs.test_key = "test_value" assert kwargs.test_key == "test_value" + + +def test_context_3(): + ctx = Context() + ctx.use_llm(provider=LLMType.OPENAI) + assert ctx.llm_config is not None + assert ctx.llm_config.api_type == LLMType.OPENAI + assert ctx.llm is not None + assert "gpt" in ctx.llm.model From 39fb4b0e6fddc07cfd49561091d5fa2118eb274e Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 16:01:05 +0800 Subject: [PATCH 09/61] add test config --- tests/metagpt/test_config.py | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 tests/metagpt/test_config.py diff --git a/tests/metagpt/test_config.py b/tests/metagpt/test_config.py new file mode 100644 index 000000000..d793b2615 --- /dev/null +++ b/tests/metagpt/test_config.py @@ -0,0 +1,21 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +""" +@Time : 2024/1/9 15:57 +@Author : alexanderwu +@File : test_config.py +""" + +from metagpt.config2 import Config, config +from metagpt.configs.llm_config import LLMType + + +def test_config_1(): + cfg = Config.default() + llm = cfg.get_openai_llm() + assert llm is not None + assert llm.api_type == LLMType.OPENAI + + +def test_config_2(): + assert config == Config.default() From eeffb50a3e5432b1a28123f5251ee76c5f0a6367 Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 16:12:31 +0800 Subject: [PATCH 10/61] add test config --- metagpt/context.py | 7 ++++++- tests/metagpt/test_config.py | 7 +++++++ 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/metagpt/context.py b/metagpt/context.py index 3505614bb..eb46ab19b 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -43,11 +43,14 @@ class AttrDict(BaseModel): class LLMMixin: + """Mixin class for LLM""" + config: Optional[Config] = None llm_config: Optional[LLMConfig] = None _llm_instance: Optional[BaseLLM] = None def use_llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI): + """Use a LLM provider""" # 更新LLM配置 self.llm_config = self.config.get_llm_config(name, provider) # 重置LLM实例 @@ -55,7 +58,9 @@ class LLMMixin: @property def llm(self) -> BaseLLM: - # 实例化LLM，如果尚未实例化 + """Return the LLM instance""" + if not self.llm_config: + self.use_llm() if not self._llm_instance and self.llm_config: self._llm_instance = create_llm_instance(self.llm_config) return self._llm_instance diff --git a/tests/metagpt/test_config.py b/tests/metagpt/test_config.py index d793b2615..eecabb546 100644 --- a/tests/metagpt/test_config.py +++ b/tests/metagpt/test_config.py @@ -8,6 +8,7 @@ from metagpt.config2 import Config, config from metagpt.configs.llm_config import LLMType +from tests.metagpt.provider.mock_llm_config import mock_llm_config def test_config_1(): @@ -19,3 +20,9 @@ def test_config_1(): def test_config_2(): assert config == Config.default() + + +def test_config_from_dict(): + cfg = Config(llm={"default": mock_llm_config}) + assert cfg + assert cfg.llm["default"].api_key == "mock_api_key" From 95687b9ed4f4f9765c61e748302d1c37e021bea0 Mon Sep 17 00:00:00 2001 From: better629 Date: Mon, 8 Jan 2024 22:15:56 +0800 Subject: [PATCH 11/61] rm expicit serialize&deserialize interface and update unittests --- metagpt/actions/action.py | 2 +- metagpt/environment.py | 41 +--------- metagpt/memory/memory.py | 24 +----- metagpt/roles/role.py | 53 ++----------- metagpt/schema.py | 74 +++++++++---------- metagpt/team.py | 15 +--- metagpt/utils/make_sk_kernel.py | 4 +- .../serialize_deserialize/test_action.py | 15 ++-- ...itect_deserialize.py => test_architect.py} | 9 +-- .../serialize_deserialize/test_environment.py | 21 +++--- .../serialize_deserialize/test_memory.py | 12 +-- .../serialize_deserialize/test_polymorphic.py | 9 ++- .../test_prepare_interview.py | 2 +- .../test_product_manager.py | 2 +- .../test_project_manager.py | 9 +-- .../serialize_deserialize/test_reasearcher.py | 2 +- .../serialize_deserialize/test_role.py | 41 +++++----- .../serialize_deserialize/test_sk_agent.py | 9 +-- .../serialize_deserialize/test_team.py | 42 +++++++---- .../test_tutorial_assistant.py | 2 +- .../serialize_deserialize/test_write_code.py | 4 +- .../test_write_code_review.py | 2 +- .../test_write_design.py | 32 +++----- .../test_write_docstring.py | 2 +- .../serialize_deserialize/test_write_prd.py | 10 +-- .../test_write_review.py | 2 +- .../test_write_tutorial.py | 4 +- 27 files changed, 154 insertions(+), 290 deletions(-) rename tests/metagpt/serialize_deserialize/{test_architect_deserialize.py => test_architect.py} (76%) diff --git a/metagpt/actions/action.py b/metagpt/actions/action.py index 24357a700..9f045bbaa 100644 --- a/metagpt/actions/action.py +++ b/metagpt/actions/action.py @@ -27,7 +27,7 @@ from metagpt.schema import ( from metagpt.utils.file_repository import FileRepository -class Action(SerializationMixin, is_polymorphic_base=True): +class Action(SerializationMixin): model_config = ConfigDict(arbitrary_types_allowed=True, exclude=["llm"]) name: str = "" diff --git a/metagpt/environment.py b/metagpt/environment.py index 6511647ef..5a2dd339b 100644 --- a/metagpt/environment.py +++ b/metagpt/environment.py @@ -12,7 +12,6 @@ functionality is to be consolidated into the `Environment` class. """ import asyncio -from pathlib import Path from typing import Iterable, Set from pydantic import BaseModel, ConfigDict, Field, SerializeAsAny, model_validator @@ -21,7 +20,7 @@ from metagpt.context import Context from metagpt.logs import logger from metagpt.roles.role import Role from metagpt.schema import Message -from metagpt.utils.common import is_send_to, read_json_file, write_json_file +from metagpt.utils.common import is_send_to class Environment(BaseModel): @@ -42,44 +41,6 @@ class Environment(BaseModel): self.add_roles(self.roles.values()) return self - def serialize(self, stg_path: Path): - roles_path = stg_path.joinpath("roles.json") - roles_info = [] - for role_key, role in self.roles.items(): - roles_info.append( - { - "role_class": role.__class__.__name__, - "module_name": role.__module__, - "role_name": role.name, - "role_sub_tags": list(self.member_addrs.get(role)), - } - ) - role.serialize(stg_path=stg_path.joinpath(f"roles/{role.__class__.__name__}_{role.name}")) - write_json_file(roles_path, roles_info) - - history_path = stg_path.joinpath("history.json") - write_json_file(history_path, {"content": self.history}) - - @classmethod - def deserialize(cls, stg_path: Path) -> "Environment": - """stg_path: ./storage/team/environment/""" - roles_path = stg_path.joinpath("roles.json") - roles_info = read_json_file(roles_path) - roles = [] - for role_info in roles_info: - # role stored in ./environment/roles/{role_class}_{role_name} - role_path = stg_path.joinpath(f"roles/{role_info.get('role_class')}_{role_info.get('role_name')}") - role = Role.deserialize(role_path) - roles.append(role) - - history = read_json_file(stg_path.joinpath("history.json")) - history = history.get("content") - - environment = Environment(**{"history": history}) - environment.add_roles(roles) - - return environment - def add_role(self, role: Role): """增加一个在当前环境的角色 Add a role in the current environment diff --git a/metagpt/memory/memory.py b/metagpt/memory/memory.py index 593409648..580361d33 100644 --- a/metagpt/memory/memory.py +++ b/metagpt/memory/memory.py @@ -7,19 +7,13 @@ @Modified By: mashenquan, 2023-11-1. According to RFC 116: Updated the type of index key. """ from collections import defaultdict -from pathlib import Path from typing import DefaultDict, Iterable, Set from pydantic import BaseModel, Field, SerializeAsAny from metagpt.const import IGNORED_MESSAGE_ID from metagpt.schema import Message -from metagpt.utils.common import ( - any_to_str, - any_to_str_set, - read_json_file, - write_json_file, -) +from metagpt.utils.common import any_to_str, any_to_str_set class Memory(BaseModel): @@ -29,22 +23,6 @@ class Memory(BaseModel): index: DefaultDict[str, list[SerializeAsAny[Message]]] = Field(default_factory=lambda: defaultdict(list)) ignore_id: bool = False - def serialize(self, stg_path: Path): - """stg_path = ./storage/team/environment/ or ./storage/team/environment/roles/{role_class}_{role_name}/""" - memory_path = stg_path.joinpath("memory.json") - storage = self.model_dump() - write_json_file(memory_path, storage) - - @classmethod - def deserialize(cls, stg_path: Path) -> "Memory": - """stg_path = ./storage/team/environment/ or ./storage/team/environment/roles/{role_class}_{role_name}/""" - memory_path = stg_path.joinpath("memory.json") - - memory_dict = read_json_file(memory_path) - memory = Memory(**memory_dict) - - return memory - def add(self, message: Message): """Add a new message to storage, while updating the index""" if self.ignore_id: diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py index cdb2da40a..73d82e369 100644 --- a/metagpt/roles/role.py +++ b/metagpt/roles/role.py @@ -23,7 +23,6 @@ from __future__ import annotations from enum import Enum -from pathlib import Path from typing import Any, Iterable, Optional, Set, Type from pydantic import BaseModel, ConfigDict, Field, SerializeAsAny, model_validator @@ -31,7 +30,6 @@ from pydantic import BaseModel, ConfigDict, Field, SerializeAsAny, model_validat from metagpt.actions import Action, ActionOutput from metagpt.actions.action_node import ActionNode from metagpt.actions.add_requirement import UserRequirement -from metagpt.const import SERDESER_PATH from metagpt.context import Context, context from metagpt.llm import LLM from metagpt.logs import logger @@ -39,14 +37,7 @@ from metagpt.memory import Memory from metagpt.provider import HumanProvider from metagpt.provider.base_llm import BaseLLM from metagpt.schema import Message, MessageQueue, SerializationMixin -from metagpt.utils.common import ( - any_to_name, - any_to_str, - import_class, - read_json_file, - role_raise_decorator, - write_json_file, -) +from metagpt.utils.common import any_to_name, any_to_str, role_raise_decorator from metagpt.utils.repair_llm_raw_output import extract_state_value_from_output PREFIX_TEMPLATE = """You are a {profile}, named {name}, your goal is {goal}. """ @@ -128,7 +119,7 @@ class RoleContext(BaseModel): return self.memory.get() -class Role(SerializationMixin, is_polymorphic_base=True): +class Role(SerializationMixin): """Role/Agent""" model_config = ConfigDict(arbitrary_types_allowed=True, exclude=["llm"]) @@ -217,6 +208,9 @@ class Role(SerializationMixin, is_polymorphic_base=True): self.llm.system_prompt = self._get_prefix() self._watch(data.get("watch") or [UserRequirement]) + if self.latest_observed_msg: + self.recovered = True + def _reset(self): self.states = [] self.actions = [] @@ -225,47 +219,12 @@ class Role(SerializationMixin, is_polymorphic_base=True): def _setting(self): return f"{self.name}({self.profile})" - def serialize(self, stg_path: Path = None): - stg_path = ( - SERDESER_PATH.joinpath(f"team/environment/roles/{self.__class__.__name__}_{self.name}") - if stg_path is None - else stg_path - ) - - role_info = self.model_dump(exclude={"rc": {"memory": True, "msg_buffer": True}, "llm": True}) - role_info.update({"role_class": self.__class__.__name__, "module_name": self.__module__}) - role_info_path = stg_path.joinpath("role_info.json") - write_json_file(role_info_path, role_info) - - self.rc.memory.serialize(stg_path) # serialize role's memory alone - - @classmethod - def deserialize(cls, stg_path: Path) -> "Role": - """stg_path = ./storage/team/environment/roles/{role_class}_{role_name}""" - role_info_path = stg_path.joinpath("role_info.json") - role_info = read_json_file(role_info_path) - - role_class_str = role_info.pop("role_class") - module_name = role_info.pop("module_name") - role_class = import_class(class_name=role_class_str, module_name=module_name) - - role = role_class(**role_info) # initiate particular Role - role.set_recovered(True) # set True to make a tag - - role_memory = Memory.deserialize(stg_path) - role.set_memory(role_memory) - - return role - def _init_action_system_message(self, action: Action): action.set_prefix(self._get_prefix()) def refresh_system_message(self): self.llm.system_prompt = self._get_prefix() - def set_recovered(self, recovered: bool = False): - self.recovered = recovered - def set_memory(self, memory: Memory): self.rc.memory = memory @@ -376,7 +335,7 @@ class Role(SerializationMixin, is_polymorphic_base=True): if self.recovered and self.rc.state >= 0: self._set_state(self.rc.state) # action to run from recovered state - self.set_recovered(False) # avoid max_react_loop out of work + self.recovered = False # avoid max_react_loop out of work return True prompt = self._get_prefix() diff --git a/metagpt/schema.py b/metagpt/schema.py index cf24fbc6f..a557951c7 100644 --- a/metagpt/schema.py +++ b/metagpt/schema.py @@ -23,7 +23,7 @@ from abc import ABC from asyncio import Queue, QueueEmpty, wait_for from json import JSONDecodeError from pathlib import Path -from typing import Any, Callable, Dict, List, Optional, Type, TypeVar, Union +from typing import Any, Dict, List, Optional, Type, TypeVar, Union from pydantic import ( BaseModel, @@ -32,8 +32,9 @@ from pydantic import ( PrivateAttr, field_serializer, field_validator, + model_serializer, + model_validator, ) -from pydantic_core import core_schema from metagpt.const import ( MESSAGE_ROUTE_CAUSE_BY, @@ -53,7 +54,7 @@ from metagpt.utils.serialize import ( ) -class SerializationMixin(BaseModel): +class SerializationMixin(BaseModel, extra="forbid"): """ PolyMorphic subclasses Serialization / Deserialization Mixin - First of all, we need to know that pydantic is not designed for polymorphism. @@ -68,49 +69,44 @@ class SerializationMixin(BaseModel): __is_polymorphic_base = False __subclasses_map__ = {} - @classmethod - def __get_pydantic_core_schema__( - cls, source: type["SerializationMixin"], handler: Callable[[Any], core_schema.CoreSchema] - ) -> core_schema.CoreSchema: - schema = handler(source) - og_schema_ref = schema["ref"] - schema["ref"] += ":mixin" - - return core_schema.no_info_before_validator_function( - cls.__deserialize_with_real_type__, - schema=schema, - ref=og_schema_ref, - serialization=core_schema.wrap_serializer_function_ser_schema(cls.__serialize_add_class_type__), - ) - - @classmethod - def __serialize_add_class_type__( - cls, - value, - handler: core_schema.SerializerFunctionWrapHandler, - ) -> Any: - ret = handler(value) - if not len(cls.__subclasses__()): - # only subclass add `__module_class_name` - ret["__module_class_name"] = f"{cls.__module__}.{cls.__qualname__}" + @model_serializer(mode="wrap") + def __serialize_with_class_type__(self, default_serializer) -> Any: + # default serializer, then append the `__module_class_name` field and return + ret = default_serializer(self) + ret["__module_class_name"] = f"{self.__class__.__module__}.{self.__class__.__qualname__}" return ret + @model_validator(mode="wrap") @classmethod - def __deserialize_with_real_type__(cls, value: Any): - if not isinstance(value, dict): - return value + def __convert_to_real_type__(cls, value: Any, handler): + if isinstance(value, dict) is False: + return handler(value) - if not cls.__is_polymorphic_base or (len(cls.__subclasses__()) and "__module_class_name" not in value): - # add right condition to init BaseClass like Action() - return value - module_class_name = value.get("__module_class_name", None) - if module_class_name is None: - raise ValueError("Missing field: __module_class_name") + # it is a dict so make sure to remove the __module_class_name + # because we don't allow extra keywords but want to ensure + # e.g Cat.model_validate(cat.model_dump()) works + class_full_name = value.pop("__module_class_name", None) - class_type = cls.__subclasses_map__.get(module_class_name, None) + # if it's not the polymorphic base we construct via default handler + if not cls.__is_polymorphic_base: + if class_full_name is None: + return handler(value) + elif str(cls) == f"": + return handler(value) + else: + # f"Trying to instantiate {class_full_name} but this is not the polymorphic base class") + pass + + # otherwise we lookup the correct polymorphic type and construct that + # instead + if class_full_name is None: + raise ValueError("Missing __module_class_name field") + + class_type = cls.__subclasses_map__.get(class_full_name, None) if class_type is None: - raise TypeError("Trying to instantiate {module_class_name} which not defined yet.") + # TODO could try dynamic import + raise TypeError("Trying to instantiate {class_full_name}, which has not yet been defined!") return class_type(**value) diff --git a/metagpt/team.py b/metagpt/team.py index 87fee8dc7..96a27d482 100644 --- a/metagpt/team.py +++ b/metagpt/team.py @@ -49,28 +49,21 @@ class Team(BaseModel): def serialize(self, stg_path: Path = None): stg_path = SERDESER_PATH.joinpath("team") if stg_path is None else stg_path + team_info_path = stg_path.joinpath("team.json") - team_info_path = stg_path.joinpath("team_info.json") - write_json_file(team_info_path, self.model_dump(exclude={"env": True})) - - self.env.serialize(stg_path.joinpath("environment")) # save environment alone + write_json_file(team_info_path, self.model_dump()) @classmethod def deserialize(cls, stg_path: Path) -> "Team": """stg_path = ./storage/team""" # recover team_info - team_info_path = stg_path.joinpath("team_info.json") + team_info_path = stg_path.joinpath("team.json") if not team_info_path.exists(): raise FileNotFoundError( - "recover storage meta file `team_info.json` not exist, " - "not to recover and please start a new project." + "recover storage meta file `team.json` not exist, " "not to recover and please start a new project." ) team_info: dict = read_json_file(team_info_path) - - # recover environment - environment = Environment.deserialize(stg_path=stg_path.joinpath("environment")) - team_info.update({"env": environment}) team = Team(**team_info) return team diff --git a/metagpt/utils/make_sk_kernel.py b/metagpt/utils/make_sk_kernel.py index 319ba3e34..283a682d6 100644 --- a/metagpt/utils/make_sk_kernel.py +++ b/metagpt/utils/make_sk_kernel.py @@ -18,12 +18,12 @@ from metagpt.config2 import config def make_sk_kernel(): kernel = sk.Kernel() - if llm := config.get_openai_llm(): + if llm := config.get_azure_llm(): kernel.add_chat_service( "chat_completion", AzureChatCompletion(llm.model, llm.base_url, llm.api_key), ) - else: + elif llm := config.get_openai_llm(): kernel.add_chat_service( "chat_completion", OpenAIChatCompletion(llm.model, llm.api_key), diff --git a/tests/metagpt/serialize_deserialize/test_action.py b/tests/metagpt/serialize_deserialize/test_action.py index 81879e34e..f66900241 100644 --- a/tests/metagpt/serialize_deserialize/test_action.py +++ b/tests/metagpt/serialize_deserialize/test_action.py @@ -8,25 +8,20 @@ from metagpt.actions import Action from metagpt.llm import LLM -def test_action_serialize(): +@pytest.mark.asyncio +async def test_action_serdeser(): action = Action() ser_action_dict = action.model_dump() assert "name" in ser_action_dict assert "llm" not in ser_action_dict # not export - assert "__module_class_name" not in ser_action_dict + assert "__module_class_name" in ser_action_dict action = Action(name="test") ser_action_dict = action.model_dump() assert "test" in ser_action_dict["name"] + new_action = Action(**ser_action_dict) -@pytest.mark.asyncio -async def test_action_deserialize(): - action = Action() - serialized_data = action.model_dump() - - new_action = Action(**serialized_data) - - assert new_action.name == "Action" + assert new_action.name == "test" assert isinstance(new_action.llm, type(LLM())) assert len(await new_action._aask("who are you")) > 0 diff --git a/tests/metagpt/serialize_deserialize/test_architect_deserialize.py b/tests/metagpt/serialize_deserialize/test_architect.py similarity index 76% rename from tests/metagpt/serialize_deserialize/test_architect_deserialize.py rename to tests/metagpt/serialize_deserialize/test_architect.py index b113912a7..343662494 100644 --- a/tests/metagpt/serialize_deserialize/test_architect_deserialize.py +++ b/tests/metagpt/serialize_deserialize/test_architect.py @@ -8,20 +8,15 @@ from metagpt.actions.action import Action from metagpt.roles.architect import Architect -def test_architect_serialize(): +@pytest.mark.asyncio +async def test_architect_serdeser(): role = Architect() ser_role_dict = role.model_dump(by_alias=True) assert "name" in ser_role_dict assert "states" in ser_role_dict assert "actions" in ser_role_dict - -@pytest.mark.asyncio -async def test_architect_deserialize(): - role = Architect() - ser_role_dict = role.model_dump(by_alias=True) new_role = Architect(**ser_role_dict) - # new_role = Architect.deserialize(ser_role_dict) assert new_role.name == "Bob" assert len(new_role.actions) == 1 assert isinstance(new_role.actions[0], Action) diff --git a/tests/metagpt/serialize_deserialize/test_environment.py b/tests/metagpt/serialize_deserialize/test_environment.py index 5a68288a6..3e2a3abba 100644 --- a/tests/metagpt/serialize_deserialize/test_environment.py +++ b/tests/metagpt/serialize_deserialize/test_environment.py @@ -2,7 +2,6 @@ # -*- coding: utf-8 -*- # @Desc : -import shutil from metagpt.actions.action_node import ActionNode from metagpt.actions.add_requirement import UserRequirement @@ -10,7 +9,7 @@ from metagpt.actions.project_management import WriteTasks from metagpt.environment import Environment from metagpt.roles.project_manager import ProjectManager from metagpt.schema import Message -from metagpt.utils.common import any_to_str +from metagpt.utils.common import any_to_str, read_json_file, write_json_file from tests.metagpt.serialize_deserialize.test_serdeser_base import ( ActionOK, ActionRaise, @@ -19,17 +18,14 @@ from tests.metagpt.serialize_deserialize.test_serdeser_base import ( ) -def test_env_serialize(): +def test_env_serdeser(): env = Environment() + env.publish_message(message=Message(content="test env serialize")) + ser_env_dict = env.model_dump() assert "roles" in ser_env_dict assert len(ser_env_dict["roles"]) == 0 - -def test_env_deserialize(): - env = Environment() - env.publish_message(message=Message(content="test env serialize")) - ser_env_dict = env.model_dump() new_env = Environment(**ser_env_dict) assert len(new_env.roles) == 0 assert len(new_env.history) == 25 @@ -79,12 +75,13 @@ def test_environment_serdeser_save(): environment = Environment() role_c = RoleC() - shutil.rmtree(serdeser_path.joinpath("team"), ignore_errors=True) - stg_path = serdeser_path.joinpath("team", "environment") + env_path = stg_path.joinpath("env.json") environment.add_role(role_c) - environment.serialize(stg_path) - new_env: Environment = Environment.deserialize(stg_path) + write_json_file(env_path, environment.model_dump()) + + env_dict = read_json_file(env_path) + new_env: Environment = Environment(**env_dict) assert len(new_env.roles) == 1 assert type(list(new_env.roles.values())[0].actions[0]) == ActionOK diff --git a/tests/metagpt/serialize_deserialize/test_memory.py b/tests/metagpt/serialize_deserialize/test_memory.py index aa3e2a465..fdaea7861 100644 --- a/tests/metagpt/serialize_deserialize/test_memory.py +++ b/tests/metagpt/serialize_deserialize/test_memory.py @@ -9,7 +9,7 @@ from metagpt.actions.add_requirement import UserRequirement from metagpt.actions.design_api import WriteDesign from metagpt.memory.memory import Memory from metagpt.schema import Message -from metagpt.utils.common import any_to_str +from metagpt.utils.common import any_to_str, read_json_file, write_json_file from tests.metagpt.serialize_deserialize.test_serdeser_base import serdeser_path @@ -53,14 +53,14 @@ def test_memory_serdeser_save(): memory.add_batch([msg1, msg2]) stg_path = serdeser_path.joinpath("team", "environment") - memory.serialize(stg_path) - assert stg_path.joinpath("memory.json").exists() + memory_path = stg_path.joinpath("memory.json") + write_json_file(memory_path, memory.model_dump()) + assert memory_path.exists() - new_memory = Memory.deserialize(stg_path) + memory_dict = read_json_file(memory_path) + new_memory = Memory(**memory_dict) assert new_memory.count() == 2 new_msg2 = new_memory.get(1)[0] assert new_msg2.instruct_content.field1 == ["field1 value1", "field1 value2"] assert new_msg2.cause_by == any_to_str(WriteDesign) assert len(new_memory.index) == 2 - - stg_path.joinpath("memory.json").unlink() diff --git a/tests/metagpt/serialize_deserialize/test_polymorphic.py b/tests/metagpt/serialize_deserialize/test_polymorphic.py index ed0482c34..e5f8ec8d6 100644 --- a/tests/metagpt/serialize_deserialize/test_polymorphic.py +++ b/tests/metagpt/serialize_deserialize/test_polymorphic.py @@ -1,6 +1,7 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- # @Desc : unittest of polymorphic conditions +import copy from pydantic import BaseModel, ConfigDict, SerializeAsAny @@ -12,6 +13,8 @@ from tests.metagpt.serialize_deserialize.test_serdeser_base import ( class ActionSubClasses(BaseModel): + model_config = ConfigDict(arbitrary_types_allowed=True) + actions: list[SerializeAsAny[Action]] = [] @@ -40,19 +43,21 @@ def test_no_serialize_as_any(): def test_polymorphic(): - _ = ActionOKV2( + ok_v2 = ActionOKV2( **{"name": "ActionOKV2", "context": "", "prefix": "", "desc": "", "extra_field": "ActionOKV2 Extra Info"} ) action_subcls = ActionSubClasses(actions=[ActionOKV2(), ActionPass()]) action_subcls_dict = action_subcls.model_dump() + action_subcls_dict2 = copy.deepcopy(action_subcls_dict) assert "__module_class_name" in action_subcls_dict["actions"][0] new_action_subcls = ActionSubClasses(**action_subcls_dict) assert isinstance(new_action_subcls.actions[0], ActionOKV2) + assert new_action_subcls.actions[0].extra_field == ok_v2.extra_field assert isinstance(new_action_subcls.actions[1], ActionPass) - new_action_subcls = ActionSubClasses.model_validate(action_subcls_dict) + new_action_subcls = ActionSubClasses.model_validate(action_subcls_dict2) assert isinstance(new_action_subcls.actions[0], ActionOKV2) assert isinstance(new_action_subcls.actions[1], ActionPass) diff --git a/tests/metagpt/serialize_deserialize/test_prepare_interview.py b/tests/metagpt/serialize_deserialize/test_prepare_interview.py index cd9912103..3b57aa27e 100644 --- a/tests/metagpt/serialize_deserialize/test_prepare_interview.py +++ b/tests/metagpt/serialize_deserialize/test_prepare_interview.py @@ -8,7 +8,7 @@ from metagpt.actions.prepare_interview import PrepareInterview @pytest.mark.asyncio -async def test_action_deserialize(): +async def test_action_serdeser(): action = PrepareInterview() serialized_data = action.model_dump() assert serialized_data["name"] == "PrepareInterview" diff --git a/tests/metagpt/serialize_deserialize/test_product_manager.py b/tests/metagpt/serialize_deserialize/test_product_manager.py index 094943900..1a056f9d4 100644 --- a/tests/metagpt/serialize_deserialize/test_product_manager.py +++ b/tests/metagpt/serialize_deserialize/test_product_manager.py @@ -10,7 +10,7 @@ from metagpt.schema import Message @pytest.mark.asyncio -async def test_product_manager_deserialize(new_filename): +async def test_product_manager_serdeser(new_filename): role = ProductManager() ser_role_dict = role.model_dump(by_alias=True) new_role = ProductManager(**ser_role_dict) diff --git a/tests/metagpt/serialize_deserialize/test_project_manager.py b/tests/metagpt/serialize_deserialize/test_project_manager.py index 1088a4461..f2c5af853 100644 --- a/tests/metagpt/serialize_deserialize/test_project_manager.py +++ b/tests/metagpt/serialize_deserialize/test_project_manager.py @@ -9,19 +9,14 @@ from metagpt.actions.project_management import WriteTasks from metagpt.roles.project_manager import ProjectManager -def test_project_manager_serialize(): +@pytest.mark.asyncio +async def test_project_manager_serdeser(): role = ProjectManager() ser_role_dict = role.model_dump(by_alias=True) assert "name" in ser_role_dict assert "states" in ser_role_dict assert "actions" in ser_role_dict - -@pytest.mark.asyncio -async def test_project_manager_deserialize(): - role = ProjectManager() - ser_role_dict = role.model_dump(by_alias=True) - new_role = ProjectManager(**ser_role_dict) assert new_role.name == "Eve" assert len(new_role.actions) == 1 diff --git a/tests/metagpt/serialize_deserialize/test_reasearcher.py b/tests/metagpt/serialize_deserialize/test_reasearcher.py index 1b8dbf2c7..a2d1fa513 100644 --- a/tests/metagpt/serialize_deserialize/test_reasearcher.py +++ b/tests/metagpt/serialize_deserialize/test_reasearcher.py @@ -8,7 +8,7 @@ from metagpt.roles.researcher import Researcher @pytest.mark.asyncio -async def test_tutorial_assistant_deserialize(): +async def test_tutorial_assistant_serdeser(): role = Researcher() ser_role_dict = role.model_dump() assert "name" in ser_role_dict diff --git a/tests/metagpt/serialize_deserialize/test_role.py b/tests/metagpt/serialize_deserialize/test_role.py index d38797baf..bbfe350b7 100644 --- a/tests/metagpt/serialize_deserialize/test_role.py +++ b/tests/metagpt/serialize_deserialize/test_role.py @@ -10,13 +10,12 @@ from pydantic import BaseModel, SerializeAsAny from metagpt.actions import WriteCode from metagpt.actions.add_requirement import UserRequirement -from metagpt.const import SERDESER_PATH from metagpt.logs import logger from metagpt.roles.engineer import Engineer from metagpt.roles.product_manager import ProductManager from metagpt.roles.role import Role from metagpt.schema import Message -from metagpt.utils.common import format_trackback_info +from metagpt.utils.common import format_trackback_info, read_json_file, write_json_file from tests.metagpt.serialize_deserialize.test_serdeser_base import ( ActionOK, RoleA, @@ -60,37 +59,31 @@ def test_role_serialize(): assert "actions" in ser_role_dict -def test_engineer_serialize(): +def test_engineer_serdeser(): role = Engineer() ser_role_dict = role.model_dump() assert "name" in ser_role_dict assert "states" in ser_role_dict assert "actions" in ser_role_dict - -@pytest.mark.asyncio -async def test_engineer_deserialize(): - role = Engineer(use_code_review=True) - ser_role_dict = role.model_dump() - new_role = Engineer(**ser_role_dict) assert new_role.name == "Alex" - assert new_role.use_code_review is True + assert new_role.use_code_review is False assert len(new_role.actions) == 1 assert isinstance(new_role.actions[0], WriteCode) - # await new_role.actions[0].run(context="write a cli snake game", filename="test_code") def test_role_serdeser_save(): - stg_path_prefix = serdeser_path.joinpath("team", "environment", "roles") shutil.rmtree(serdeser_path.joinpath("team"), ignore_errors=True) pm = ProductManager() - role_tag = f"{pm.__class__.__name__}_{pm.name}" - stg_path = stg_path_prefix.joinpath(role_tag) - pm.serialize(stg_path) - new_pm = Role.deserialize(stg_path) + stg_path = serdeser_path.joinpath("team", "environment", "roles", f"{pm.__class__.__name__}_{pm.name}") + role_path = stg_path.joinpath("role.json") + write_json_file(role_path, pm.model_dump()) + + role_dict = read_json_file(role_path) + new_pm = ProductManager(**role_dict) assert new_pm.name == pm.name assert len(new_pm.get_memories(1)) == 0 @@ -98,22 +91,24 @@ def test_role_serdeser_save(): @pytest.mark.asyncio async def test_role_serdeser_interrupt(): role_c = RoleC() - shutil.rmtree(SERDESER_PATH.joinpath("team"), ignore_errors=True) + shutil.rmtree(serdeser_path.joinpath("team"), ignore_errors=True) - stg_path = SERDESER_PATH.joinpath("team", "environment", "roles", f"{role_c.__class__.__name__}_{role_c.name}") + stg_path = serdeser_path.joinpath("team", "environment", "roles", f"{role_c.__class__.__name__}_{role_c.name}") + role_path = stg_path.joinpath("role.json") try: await role_c.run(with_message=Message(content="demo", cause_by=UserRequirement)) except Exception: - logger.error(f"Exception in `role_a.run`, detail: {format_trackback_info()}") - role_c.serialize(stg_path) + logger.error(f"Exception in `role_c.run`, detail: {format_trackback_info()}") + write_json_file(role_path, role_c.model_dump()) assert role_c.rc.memory.count() == 1 - new_role_a: Role = Role.deserialize(stg_path) - assert new_role_a.rc.state == 1 + role_dict = read_json_file(role_path) + new_role_c: Role = RoleC(**role_dict) + assert new_role_c.rc.state == 1 with pytest.raises(Exception): - await new_role_a.run(with_message=Message(content="demo", cause_by=UserRequirement)) + await new_role_c.run(with_message=Message(content="demo", cause_by=UserRequirement)) if __name__ == "__main__": diff --git a/tests/metagpt/serialize_deserialize/test_sk_agent.py b/tests/metagpt/serialize_deserialize/test_sk_agent.py index 7f287b8f9..97c0ade99 100644 --- a/tests/metagpt/serialize_deserialize/test_sk_agent.py +++ b/tests/metagpt/serialize_deserialize/test_sk_agent.py @@ -5,15 +5,8 @@ import pytest from metagpt.roles.sk_agent import SkAgent -def test_sk_agent_serialize(): - role = SkAgent() - ser_role_dict = role.model_dump(exclude={"import_semantic_skill_from_directory", "import_skill"}) - assert "name" in ser_role_dict - assert "planner" in ser_role_dict - - @pytest.mark.asyncio -async def test_sk_agent_deserialize(): +async def test_sk_agent_serdeser(): role = SkAgent() ser_role_dict = role.model_dump(exclude={"import_semantic_skill_from_directory", "import_skill"}) assert "name" in ser_role_dict diff --git a/tests/metagpt/serialize_deserialize/test_team.py b/tests/metagpt/serialize_deserialize/test_team.py index 566f63c3d..57c8a8508 100644 --- a/tests/metagpt/serialize_deserialize/test_team.py +++ b/tests/metagpt/serialize_deserialize/test_team.py @@ -4,13 +4,14 @@ # @Desc : import shutil +from pathlib import Path import pytest -from metagpt.const import SERDESER_PATH from metagpt.logs import logger from metagpt.roles import Architect, ProductManager, ProjectManager from metagpt.team import Team +from metagpt.utils.common import write_json_file from tests.metagpt.serialize_deserialize.test_serdeser_base import ( ActionOK, RoleA, @@ -45,9 +46,16 @@ def test_team_deserialize(): assert new_company.env.get_role(arch.profile) is not None -def test_team_serdeser_save(): - company = Team() +def mock_team_serialize(self, stg_path: Path = serdeser_path.joinpath("team")): + team_info_path = stg_path.joinpath("team.json") + write_json_file(team_info_path, self.model_dump()) + + +def test_team_serdeser_save(mocker): + mocker.patch("metagpt.team.Team.serialize", mock_team_serialize) + + company = Team() company.hire([RoleC()]) stg_path = serdeser_path.joinpath("team") @@ -61,9 +69,11 @@ def test_team_serdeser_save(): @pytest.mark.asyncio -async def test_team_recover(): +async def test_team_recover(mocker): + mocker.patch("metagpt.team.Team.serialize", mock_team_serialize) + idea = "write a snake game" - stg_path = SERDESER_PATH.joinpath("team") + stg_path = serdeser_path.joinpath("team") shutil.rmtree(stg_path, ignore_errors=True) company = Team() @@ -75,9 +85,9 @@ async def test_team_recover(): ser_data = company.model_dump() new_company = Team(**ser_data) - new_company.env.get_role(role_c.profile) - # assert new_role_c.rc.memory == role_c.rc.memory # TODO - # assert new_role_c.rc.env != role_c.rc.env # TODO + new_role_c = new_company.env.get_role(role_c.profile) + assert new_role_c.rc.memory == role_c.rc.memory + assert new_role_c.rc.env != role_c.rc.env assert type(list(new_company.env.roles.values())[0].actions[0]) == ActionOK new_company.run_project(idea) @@ -85,9 +95,11 @@ async def test_team_recover(): @pytest.mark.asyncio -async def test_team_recover_save(): +async def test_team_recover_save(mocker): + mocker.patch("metagpt.team.Team.serialize", mock_team_serialize) + idea = "write a 2048 web game" - stg_path = SERDESER_PATH.joinpath("team") + stg_path = serdeser_path.joinpath("team") shutil.rmtree(stg_path, ignore_errors=True) company = Team() @@ -98,8 +110,8 @@ async def test_team_recover_save(): new_company = Team.deserialize(stg_path) new_role_c = new_company.env.get_role(role_c.profile) - # assert new_role_c.rc.memory == role_c.rc.memory - # assert new_role_c.rc.env != role_c.rc.env + assert new_role_c.rc.memory == role_c.rc.memory + assert new_role_c.rc.env != role_c.rc.env assert new_role_c.recovered != role_c.recovered # here cause previous ut is `!=` assert new_role_c.rc.todo != role_c.rc.todo # serialize exclude `rc.todo` assert new_role_c.rc.news != role_c.rc.news # serialize exclude `rc.news` @@ -109,9 +121,11 @@ async def test_team_recover_save(): @pytest.mark.asyncio -async def test_team_recover_multi_roles_save(): +async def test_team_recover_multi_roles_save(mocker): + mocker.patch("metagpt.team.Team.serialize", mock_team_serialize) + idea = "write a snake game" - stg_path = SERDESER_PATH.joinpath("team") + stg_path = serdeser_path.joinpath("team") shutil.rmtree(stg_path, ignore_errors=True) role_a = RoleA() diff --git a/tests/metagpt/serialize_deserialize/test_tutorial_assistant.py b/tests/metagpt/serialize_deserialize/test_tutorial_assistant.py index e642dae54..cb8feec19 100644 --- a/tests/metagpt/serialize_deserialize/test_tutorial_assistant.py +++ b/tests/metagpt/serialize_deserialize/test_tutorial_assistant.py @@ -7,7 +7,7 @@ from metagpt.roles.tutorial_assistant import TutorialAssistant @pytest.mark.asyncio -async def test_tutorial_assistant_deserialize(): +async def test_tutorial_assistant_serdeser(): role = TutorialAssistant() ser_role_dict = role.model_dump() assert "name" in ser_role_dict diff --git a/tests/metagpt/serialize_deserialize/test_write_code.py b/tests/metagpt/serialize_deserialize/test_write_code.py index cb262bb45..12dc49c3b 100644 --- a/tests/metagpt/serialize_deserialize/test_write_code.py +++ b/tests/metagpt/serialize_deserialize/test_write_code.py @@ -9,7 +9,7 @@ from metagpt.actions import WriteCode from metagpt.schema import CodingContext, Document -def test_write_design_serialize(): +def test_write_design_serdeser(): action = WriteCode() ser_action_dict = action.model_dump() assert ser_action_dict["name"] == "WriteCode" @@ -17,7 +17,7 @@ def test_write_design_serialize(): @pytest.mark.asyncio -async def test_write_code_deserialize(): +async def test_write_code_serdeser(): context = CodingContext( filename="test_code.py", design_doc=Document(content="write add function to calculate two numbers") ) diff --git a/tests/metagpt/serialize_deserialize/test_write_code_review.py b/tests/metagpt/serialize_deserialize/test_write_code_review.py index 991b3c13b..d1a9bff24 100644 --- a/tests/metagpt/serialize_deserialize/test_write_code_review.py +++ b/tests/metagpt/serialize_deserialize/test_write_code_review.py @@ -9,7 +9,7 @@ from metagpt.schema import CodingContext, Document @pytest.mark.asyncio -async def test_write_code_review_deserialize(): +async def test_write_code_review_serdeser(): code_content = """ def div(a: int, b: int = 0): return a / b diff --git a/tests/metagpt/serialize_deserialize/test_write_design.py b/tests/metagpt/serialize_deserialize/test_write_design.py index 7bcba3fc8..37d505914 100644 --- a/tests/metagpt/serialize_deserialize/test_write_design.py +++ b/tests/metagpt/serialize_deserialize/test_write_design.py @@ -7,33 +7,25 @@ import pytest from metagpt.actions import WriteDesign, WriteTasks -def test_write_design_serialize(): - action = WriteDesign() - ser_action_dict = action.model_dump() - assert "name" in ser_action_dict - assert "llm" not in ser_action_dict # not export - - -def test_write_task_serialize(): - action = WriteTasks() - ser_action_dict = action.model_dump() - assert "name" in ser_action_dict - assert "llm" not in ser_action_dict # not export - - @pytest.mark.asyncio -async def test_write_design_deserialize(): +async def test_write_design_serialize(): action = WriteDesign() - serialized_data = action.model_dump() - new_action = WriteDesign(**serialized_data) + ser_action_dict = action.model_dump() + assert "name" in ser_action_dict + assert "llm" not in ser_action_dict # not export + + new_action = WriteDesign(**ser_action_dict) assert new_action.name == "WriteDesign" await new_action.run(with_messages="write a cli snake game") @pytest.mark.asyncio -async def test_write_task_deserialize(): +async def test_write_task_serialize(): action = WriteTasks() - serialized_data = action.model_dump() - new_action = WriteTasks(**serialized_data) + ser_action_dict = action.model_dump() + assert "name" in ser_action_dict + assert "llm" not in ser_action_dict # not export + + new_action = WriteTasks(**ser_action_dict) assert new_action.name == "WriteTasks" await new_action.run(with_messages="write a cli snake game") diff --git a/tests/metagpt/serialize_deserialize/test_write_docstring.py b/tests/metagpt/serialize_deserialize/test_write_docstring.py index e4116ab30..fb927f089 100644 --- a/tests/metagpt/serialize_deserialize/test_write_docstring.py +++ b/tests/metagpt/serialize_deserialize/test_write_docstring.py @@ -29,7 +29,7 @@ class Person: ], ids=["google", "numpy", "sphinx"], ) -async def test_action_deserialize(style: str, part: str): +async def test_action_serdeser(style: str, part: str): action = WriteDocstring() serialized_data = action.model_dump() diff --git a/tests/metagpt/serialize_deserialize/test_write_prd.py b/tests/metagpt/serialize_deserialize/test_write_prd.py index b9eff5a19..820ee237c 100644 --- a/tests/metagpt/serialize_deserialize/test_write_prd.py +++ b/tests/metagpt/serialize_deserialize/test_write_prd.py @@ -9,18 +9,14 @@ from metagpt.actions import WritePRD from metagpt.schema import Message -def test_action_serialize(new_filename): +@pytest.mark.asyncio +async def test_action_serdeser(new_filename): action = WritePRD() ser_action_dict = action.model_dump() assert "name" in ser_action_dict assert "llm" not in ser_action_dict # not export - -@pytest.mark.asyncio -async def test_action_deserialize(new_filename): - action = WritePRD() - serialized_data = action.model_dump() - new_action = WritePRD(**serialized_data) + new_action = WritePRD(**ser_action_dict) assert new_action.name == "WritePRD" action_output = await new_action.run(with_messages=Message(content="write a cli snake game")) assert len(action_output.content) > 0 diff --git a/tests/metagpt/serialize_deserialize/test_write_review.py b/tests/metagpt/serialize_deserialize/test_write_review.py index f02a01910..17e212276 100644 --- a/tests/metagpt/serialize_deserialize/test_write_review.py +++ b/tests/metagpt/serialize_deserialize/test_write_review.py @@ -42,7 +42,7 @@ CONTEXT = """ @pytest.mark.asyncio -async def test_action_deserialize(): +async def test_action_serdeser(): action = WriteReview() serialized_data = action.model_dump() assert serialized_data["name"] == "WriteReview" diff --git a/tests/metagpt/serialize_deserialize/test_write_tutorial.py b/tests/metagpt/serialize_deserialize/test_write_tutorial.py index 606a90f8c..4eeef7e0d 100644 --- a/tests/metagpt/serialize_deserialize/test_write_tutorial.py +++ b/tests/metagpt/serialize_deserialize/test_write_tutorial.py @@ -9,7 +9,7 @@ from metagpt.actions.write_tutorial import WriteContent, WriteDirectory @pytest.mark.asyncio @pytest.mark.parametrize(("language", "topic"), [("English", "Write a tutorial about Python")]) -async def test_write_directory_deserialize(language: str, topic: str): +async def test_write_directory_serdeser(language: str, topic: str): action = WriteDirectory() serialized_data = action.model_dump() assert serialized_data["name"] == "WriteDirectory" @@ -30,7 +30,7 @@ async def test_write_directory_deserialize(language: str, topic: str): ("language", "topic", "directory"), [("English", "Write a tutorial about Python", {"Introduction": ["What is Python?", "Why learn Python?"]})], ) -async def test_write_content_deserialize(language: str, topic: str, directory: Dict): +async def test_write_content_serdeser(language: str, topic: str, directory: Dict): action = WriteContent(language=language, directory=directory) serialized_data = action.model_dump() assert serialized_data["name"] == "WriteContent" From e2e00beb755bb10c73460cad2f19944567cbd4ea Mon Sep 17 00:00:00 2001 From: better629 Date: Tue, 9 Jan 2024 15:40:42 +0800 Subject: [PATCH 12/61] make instruct_content support any inherited basemodel ser&deser --- metagpt/schema.py | 25 ++++--- .../serialize_deserialize/test_schema.py | 68 +++++++++++++++---- .../test_serdeser_base.py | 10 +-- 3 files changed, 77 insertions(+), 26 deletions(-) diff --git a/metagpt/schema.py b/metagpt/schema.py index a557951c7..7d1c2b539 100644 --- a/metagpt/schema.py +++ b/metagpt/schema.py @@ -182,12 +182,16 @@ class Message(BaseModel): @field_validator("instruct_content", mode="before") @classmethod def check_instruct_content(cls, ic: Any) -> BaseModel: - if ic and not isinstance(ic, BaseModel) and "class" in ic: - # compatible with custom-defined ActionOutput - mapping = actionoutput_str_to_mapping(ic["mapping"]) - - actionnode_class = import_class("ActionNode", "metagpt.actions.action_node") # avoid circular import - ic_obj = actionnode_class.create_model_class(class_name=ic["class"], mapping=mapping) + if ic and isinstance(ic, dict) and "class" in ic: + if "mapping" in ic: + # compatible with custom-defined ActionOutput + mapping = actionoutput_str_to_mapping(ic["mapping"]) + actionnode_class = import_class("ActionNode", "metagpt.actions.action_node") # avoid circular import + ic_obj = actionnode_class.create_model_class(class_name=ic["class"], mapping=mapping) + elif "module" in ic: + ic_obj = import_class(ic["class"], ic["module"]) + else: + raise KeyError("missing required key to init Message.instruct_content from dict") ic = ic_obj(**ic["value"]) return ic @@ -212,13 +216,16 @@ class Message(BaseModel): if ic: # compatible with custom-defined ActionOutput schema = ic.model_json_schema() - # `Documents` contain definitions - if "definitions" not in schema: - # TODO refine with nested BaseModel + ic_type = str(type(ic)) + if " Date: Tue, 9 Jan 2024 16:07:33 +0800 Subject: [PATCH 13/61] update --- metagpt/schema.py | 1 + 1 file changed, 1 insertion(+) diff --git a/metagpt/schema.py b/metagpt/schema.py index 7d1c2b539..853a9c6bb 100644 --- a/metagpt/schema.py +++ b/metagpt/schema.py @@ -189,6 +189,7 @@ class Message(BaseModel): actionnode_class = import_class("ActionNode", "metagpt.actions.action_node") # avoid circular import ic_obj = actionnode_class.create_model_class(class_name=ic["class"], mapping=mapping) elif "module" in ic: + # subclasses of BaseModel ic_obj = import_class(ic["class"], ic["module"]) else: raise KeyError("missing required key to init Message.instruct_content from dict") From dacdfd799ee64c06da48d05bff188b6eb278d22a Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 16:32:38 +0800 Subject: [PATCH 14/61] add context mixin --- metagpt/context.py | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/metagpt/context.py b/metagpt/context.py index eb46ab19b..293beb9b5 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -103,5 +103,23 @@ class Context(LLMMixin, BaseModel): # return llm +class ContextMixin: + """Mixin class for configurable objects""" + + _context: Optional[Context] = None + + def __init__(self, context: Optional[Context] = None): + self._context = context + + def set_context(self, context: Optional[Context] = None): + """Set parent context""" + self._context = context + + @property + def context(self): + """Get config""" + return self._context + + # Global context, not in Env context = Context() From b259203f743213ad1abc61e28df6426ba045a7aa Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 17:01:21 +0800 Subject: [PATCH 15/61] refine code --- examples/agent_creator.py | 2 +- examples/build_customized_agent.py | 4 +-- examples/build_customized_multi_agents.py | 6 ++--- examples/debate.py | 2 +- metagpt/context.py | 2 +- metagpt/roles/architect.py | 2 +- metagpt/roles/engineer.py | 2 +- metagpt/roles/invoice_ocr_assistant.py | 6 ++--- metagpt/roles/product_manager.py | 2 +- metagpt/roles/project_manager.py | 2 +- metagpt/roles/qa_engineer.py | 2 +- metagpt/roles/researcher.py | 2 +- metagpt/roles/role.py | 26 +++++++++---------- metagpt/roles/sales.py | 2 +- metagpt/roles/searcher.py | 4 +-- metagpt/roles/sk_agent.py | 2 +- metagpt/roles/teacher.py | 2 +- metagpt/roles/tutorial_assistant.py | 4 +-- .../test_serdeser_base.py | 6 ++--- tests/metagpt/test_role.py | 8 +++--- 20 files changed, 43 insertions(+), 45 deletions(-) diff --git a/examples/agent_creator.py b/examples/agent_creator.py index e908fe6ee..fe883bdf4 100644 --- a/examples/agent_creator.py +++ b/examples/agent_creator.py @@ -61,7 +61,7 @@ class AgentCreator(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self._init_actions([CreateAgent]) + self.add_actions([CreateAgent]) async def _act(self) -> Message: logger.info(f"{self._setting}: to do {self.rc.todo}({self.rc.todo.name})") diff --git a/examples/build_customized_agent.py b/examples/build_customized_agent.py index 6c3219efc..a0c8ddfb3 100644 --- a/examples/build_customized_agent.py +++ b/examples/build_customized_agent.py @@ -57,7 +57,7 @@ class SimpleCoder(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self._init_actions([SimpleWriteCode]) + self.add_actions([SimpleWriteCode]) async def _act(self) -> Message: logger.info(f"{self._setting}: to do {self.rc.todo}({self.rc.todo.name})") @@ -76,7 +76,7 @@ class RunnableCoder(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self._init_actions([SimpleWriteCode, SimpleRunCode]) + self.add_actions([SimpleWriteCode, SimpleRunCode]) self._set_react_mode(react_mode=RoleReactMode.BY_ORDER.value) async def _act(self) -> Message: diff --git a/examples/build_customized_multi_agents.py b/examples/build_customized_multi_agents.py index 73278c08c..aceb3f2ab 100644 --- a/examples/build_customized_multi_agents.py +++ b/examples/build_customized_multi_agents.py @@ -46,7 +46,7 @@ class SimpleCoder(Role): def __init__(self, **kwargs): super().__init__(**kwargs) self._watch([UserRequirement]) - self._init_actions([SimpleWriteCode]) + self.add_actions([SimpleWriteCode]) class SimpleWriteTest(Action): @@ -75,7 +75,7 @@ class SimpleTester(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self._init_actions([SimpleWriteTest]) + self.add_actions([SimpleWriteTest]) # self._watch([SimpleWriteCode]) self._watch([SimpleWriteCode, SimpleWriteReview]) # feel free to try this too @@ -114,7 +114,7 @@ class SimpleReviewer(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self._init_actions([SimpleWriteReview]) + self.add_actions([SimpleWriteReview]) self._watch([SimpleWriteTest]) diff --git a/examples/debate.py b/examples/debate.py index eb0a09839..b47eba3cd 100644 --- a/examples/debate.py +++ b/examples/debate.py @@ -49,7 +49,7 @@ class Debator(Role): def __init__(self, **data: Any): super().__init__(**data) - self._init_actions([SpeakAloud]) + self.add_actions([SpeakAloud]) self._watch([UserRequirement, SpeakAloud]) async def _observe(self) -> int: diff --git a/metagpt/context.py b/metagpt/context.py index 293beb9b5..495fe9e2f 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -104,7 +104,7 @@ class Context(LLMMixin, BaseModel): class ContextMixin: - """Mixin class for configurable objects""" + """Mixin class for configurable objects: Priority: more specific < parent""" _context: Optional[Context] = None diff --git a/metagpt/roles/architect.py b/metagpt/roles/architect.py index c6ceaccb7..a22a1c926 100644 --- a/metagpt/roles/architect.py +++ b/metagpt/roles/architect.py @@ -33,7 +33,7 @@ class Architect(Role): def __init__(self, **kwargs) -> None: super().__init__(**kwargs) # Initialize actions specific to the Architect role - self._init_actions([WriteDesign]) + self.add_actions([WriteDesign]) # Set events or actions the Architect should watch or be aware of self._watch({WritePRD}) diff --git a/metagpt/roles/engineer.py b/metagpt/roles/engineer.py index 98744383c..ad0c1ac92 100644 --- a/metagpt/roles/engineer.py +++ b/metagpt/roles/engineer.py @@ -84,7 +84,7 @@ class Engineer(Role): def __init__(self, **kwargs) -> None: super().__init__(**kwargs) - self._init_actions([WriteCode]) + self.add_actions([WriteCode]) self._watch([WriteTasks, SummarizeCode, WriteCode, WriteCodeReview, FixBug]) self.code_todos = [] self.summarize_todos = [] diff --git a/metagpt/roles/invoice_ocr_assistant.py b/metagpt/roles/invoice_ocr_assistant.py index 8635f4307..de7d3f8a3 100644 --- a/metagpt/roles/invoice_ocr_assistant.py +++ b/metagpt/roles/invoice_ocr_assistant.py @@ -60,7 +60,7 @@ class InvoiceOCRAssistant(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self._init_actions([InvoiceOCR]) + self.add_actions([InvoiceOCR]) self._set_react_mode(react_mode=RoleReactMode.BY_ORDER.value) async def _act(self) -> Message: @@ -82,10 +82,10 @@ class InvoiceOCRAssistant(Role): resp = await todo.run(file_path) if len(resp) == 1: # Single file support for questioning based on OCR recognition results - self._init_actions([GenerateTable, ReplyQuestion]) + self.add_actions([GenerateTable, ReplyQuestion]) self.orc_data = resp[0] else: - self._init_actions([GenerateTable]) + self.add_actions([GenerateTable]) self.set_todo(None) content = INVOICE_OCR_SUCCESS diff --git a/metagpt/roles/product_manager.py b/metagpt/roles/product_manager.py index 7f1a49231..a35dcb3a0 100644 --- a/metagpt/roles/product_manager.py +++ b/metagpt/roles/product_manager.py @@ -33,7 +33,7 @@ class ProductManager(Role): def __init__(self, **kwargs) -> None: super().__init__(**kwargs) - self._init_actions([PrepareDocuments, WritePRD]) + self.add_actions([PrepareDocuments, WritePRD]) self._watch([UserRequirement, PrepareDocuments]) self.todo_action = any_to_name(PrepareDocuments) diff --git a/metagpt/roles/project_manager.py b/metagpt/roles/project_manager.py index 1fad4afc2..7fa16b1e5 100644 --- a/metagpt/roles/project_manager.py +++ b/metagpt/roles/project_manager.py @@ -33,5 +33,5 @@ class ProjectManager(Role): def __init__(self, **kwargs) -> None: super().__init__(**kwargs) - self._init_actions([WriteTasks]) + self.add_actions([WriteTasks]) self._watch([WriteDesign]) diff --git a/metagpt/roles/qa_engineer.py b/metagpt/roles/qa_engineer.py index 7da0af072..80b0fd39a 100644 --- a/metagpt/roles/qa_engineer.py +++ b/metagpt/roles/qa_engineer.py @@ -44,7 +44,7 @@ class QaEngineer(Role): # FIXME: a bit hack here, only init one action to circumvent _think() logic, # will overwrite _think() in future updates - self._init_actions([WriteTest]) + self.add_actions([WriteTest]) self._watch([SummarizeCode, WriteTest, RunCode, DebugError]) self.test_round = 0 diff --git a/metagpt/roles/researcher.py b/metagpt/roles/researcher.py index 5110c6485..e877778f6 100644 --- a/metagpt/roles/researcher.py +++ b/metagpt/roles/researcher.py @@ -34,7 +34,7 @@ class Researcher(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self._init_actions( + self.add_actions( [CollectLinks(name=self.name), WebBrowseAndSummarize(name=self.name), ConductResearch(name=self.name)] ) self._set_react_mode(react_mode=RoleReactMode.BY_ORDER.value) diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py index 73d82e369..42996bea8 100644 --- a/metagpt/roles/role.py +++ b/metagpt/roles/role.py @@ -23,7 +23,7 @@ from __future__ import annotations from enum import Enum -from typing import Any, Iterable, Optional, Set, Type +from typing import Any, Iterable, Optional, Set, Type, Union from pydantic import BaseModel, ConfigDict, Field, SerializeAsAny, model_validator @@ -222,20 +222,18 @@ class Role(SerializationMixin): def _init_action_system_message(self, action: Action): action.set_prefix(self._get_prefix()) - def refresh_system_message(self): - self.llm.system_prompt = self._get_prefix() + def add_action(self, action: Action): + """Add action to the role.""" + self.add_actions([action]) - def set_memory(self, memory: Memory): - self.rc.memory = memory + def add_actions(self, actions: list[Union[Action, Type[Action]]]): + """Add actions to the role. - def init_actions(self, actions): - self._init_actions(actions) - - def _init_actions(self, actions): - self._reset() - for idx, action in enumerate(actions): + Args: + actions: list of Action classes or instances + """ + for action in actions: if not isinstance(action, Action): - ## 默认初始化 i = action(name="", llm=self.llm) else: if self.is_human and not isinstance(action.llm, HumanProvider): @@ -247,7 +245,7 @@ class Role(SerializationMixin): i = action self._init_action_system_message(i) self.actions.append(i) - self.states.append(f"{idx}. {action}") + self.states.append(f"{len(self.actions)}. {action}") def _set_react_mode(self, react_mode: str, max_react_loop: int = 1): """Set strategy of the Role reacting to observed Message. Variation lies in how @@ -302,7 +300,7 @@ class Role(SerializationMixin): self.rc.env = env if env: env.set_addresses(self, self.addresses) - self.refresh_system_message() # add env message to system message + self.llm.system_prompt = self._get_prefix() @property def action_count(self): diff --git a/metagpt/roles/sales.py b/metagpt/roles/sales.py index ca1cfee85..8da930888 100644 --- a/metagpt/roles/sales.py +++ b/metagpt/roles/sales.py @@ -38,5 +38,5 @@ class Sales(Role): action = SearchAndSummarize(name="", engine=SearchEngineType.CUSTOM_ENGINE, search_func=store.asearch) else: action = SearchAndSummarize() - self._init_actions([action]) + self.add_actions([action]) self._watch([UserRequirement]) diff --git a/metagpt/roles/searcher.py b/metagpt/roles/searcher.py index e713f7697..f37bd4704 100644 --- a/metagpt/roles/searcher.py +++ b/metagpt/roles/searcher.py @@ -48,12 +48,12 @@ class Searcher(Role): engine (SearchEngineType): The type of search engine to use. """ super().__init__(**kwargs) - self._init_actions([SearchAndSummarize(engine=self.engine)]) + self.add_actions([SearchAndSummarize(engine=self.engine)]) def set_search_func(self, search_func): """Sets a custom search function for the searcher.""" action = SearchAndSummarize(name="", engine=SearchEngineType.CUSTOM_ENGINE, search_func=search_func) - self._init_actions([action]) + self.add_actions([action]) async def _act_sp(self) -> Message: """Performs the search action in a single process.""" diff --git a/metagpt/roles/sk_agent.py b/metagpt/roles/sk_agent.py index 8921774f0..468905fce 100644 --- a/metagpt/roles/sk_agent.py +++ b/metagpt/roles/sk_agent.py @@ -52,7 +52,7 @@ class SkAgent(Role): def __init__(self, **data: Any) -> None: """Initializes the Engineer role with given attributes.""" super().__init__(**data) - self._init_actions([ExecuteTask()]) + self.add_actions([ExecuteTask()]) self._watch([UserRequirement]) self.kernel = make_sk_kernel() diff --git a/metagpt/roles/teacher.py b/metagpt/roles/teacher.py index fb547f56b..b4ffd01d3 100644 --- a/metagpt/roles/teacher.py +++ b/metagpt/roles/teacher.py @@ -47,7 +47,7 @@ class Teacher(Role): for topic in TeachingPlanBlock.TOPICS: act = WriteTeachingPlanPart(context=self.rc.news[0].content, topic=topic, llm=self.llm) actions.append(act) - self._init_actions(actions) + self.add_actions(actions) if self.rc.todo is None: self._set_state(0) diff --git a/metagpt/roles/tutorial_assistant.py b/metagpt/roles/tutorial_assistant.py index 10bd82c60..d296c7b3f 100644 --- a/metagpt/roles/tutorial_assistant.py +++ b/metagpt/roles/tutorial_assistant.py @@ -40,7 +40,7 @@ class TutorialAssistant(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self._init_actions([WriteDirectory(language=self.language)]) + self.add_actions([WriteDirectory(language=self.language)]) self._set_react_mode(react_mode=RoleReactMode.BY_ORDER.value) async def _handle_directory(self, titles: Dict) -> Message: @@ -63,7 +63,7 @@ class TutorialAssistant(Role): directory += f"- {key}\n" for second_dir in first_dir[key]: directory += f" - {second_dir}\n" - self._init_actions(actions) + self.add_actions(actions) async def _act(self) -> Message: """Perform an action as determined by the role. diff --git a/tests/metagpt/serialize_deserialize/test_serdeser_base.py b/tests/metagpt/serialize_deserialize/test_serdeser_base.py index ddb47a3e2..c97cea597 100644 --- a/tests/metagpt/serialize_deserialize/test_serdeser_base.py +++ b/tests/metagpt/serialize_deserialize/test_serdeser_base.py @@ -67,7 +67,7 @@ class RoleA(Role): def __init__(self, **kwargs): super(RoleA, self).__init__(**kwargs) - self._init_actions([ActionPass]) + self.add_actions([ActionPass]) self._watch([UserRequirement]) @@ -79,7 +79,7 @@ class RoleB(Role): def __init__(self, **kwargs): super(RoleB, self).__init__(**kwargs) - self._init_actions([ActionOK, ActionRaise]) + self.add_actions([ActionOK, ActionRaise]) self._watch([ActionPass]) self.rc.react_mode = RoleReactMode.BY_ORDER @@ -92,7 +92,7 @@ class RoleC(Role): def __init__(self, **kwargs): super(RoleC, self).__init__(**kwargs) - self._init_actions([ActionOK, ActionRaise]) + self.add_actions([ActionOK, ActionRaise]) self._watch([UserRequirement]) self.rc.react_mode = RoleReactMode.BY_ORDER self.rc.memory.ignore_id = True diff --git a/tests/metagpt/test_role.py b/tests/metagpt/test_role.py index 52d08e92e..20c8dba6d 100644 --- a/tests/metagpt/test_role.py +++ b/tests/metagpt/test_role.py @@ -33,7 +33,7 @@ class MockAction(Action): class MockRole(Role): def __init__(self, name="", profile="", goal="", constraints="", desc=""): super().__init__(name=name, profile=profile, goal=goal, constraints=constraints, desc=desc) - self._init_actions([MockAction()]) + self.add_actions([MockAction()]) def test_basic(): @@ -111,7 +111,7 @@ async def test_send_to(): def test_init_action(): role = Role() - role.init_actions([MockAction, MockAction]) + role.add_actions([MockAction, MockAction]) assert role.action_count == 2 @@ -127,7 +127,7 @@ async def test_recover(): role.publish_message(None) role.llm = mock_llm - role.init_actions([MockAction, MockAction]) + role.add_actions([MockAction, MockAction]) role.recovered = True role.latest_observed_msg = Message(content="recover_test") role.rc.state = 0 @@ -144,7 +144,7 @@ async def test_think_act(): mock_llm.aask.side_effect = ["ok"] role = Role() - role.init_actions([MockAction]) + role.add_actions([MockAction]) await role.think() role.rc.memory.add(Message("run")) assert len(role.get_memories()) == 1 From 20b53fa8597f6527cb7da950b060d43eafa4a2e7 Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 17:04:45 +0800 Subject: [PATCH 16/61] refine code --- metagpt/context.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/metagpt/context.py b/metagpt/context.py index 495fe9e2f..ba859ed5c 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -45,24 +45,24 @@ class AttrDict(BaseModel): class LLMMixin: """Mixin class for LLM""" - config: Optional[Config] = None - llm_config: Optional[LLMConfig] = None + # _config: Optional[Config] = None + _llm_config: Optional[LLMConfig] = None _llm_instance: Optional[BaseLLM] = None def use_llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI): """Use a LLM provider""" # 更新LLM配置 - self.llm_config = self.config.get_llm_config(name, provider) + self._llm_config = self._config.get_llm_config(name, provider) # 重置LLM实例 self._llm_instance = None @property def llm(self) -> BaseLLM: """Return the LLM instance""" - if not self.llm_config: + if not self._llm_config: self.use_llm() - if not self._llm_instance and self.llm_config: - self._llm_instance = create_llm_instance(self.llm_config) + if not self._llm_instance and self._llm_config: + self._llm_instance = create_llm_instance(self._llm_config) return self._llm_instance From 6259acc4bd0357793e0327c600fc02d534fd1639 Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 17:13:22 +0800 Subject: [PATCH 17/61] refine code --- metagpt/context.py | 40 +++++++++++++++++++++------------------- metagpt/llm.py | 1 + 2 files changed, 22 insertions(+), 19 deletions(-) diff --git a/metagpt/context.py b/metagpt/context.py index ba859ed5c..71570bac6 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -9,7 +9,7 @@ import os from pathlib import Path from typing import Optional -from pydantic import BaseModel, ConfigDict +from pydantic import BaseModel, ConfigDict, Field from metagpt.config2 import Config from metagpt.configs.llm_config import LLMConfig, LLMType @@ -42,31 +42,33 @@ class AttrDict(BaseModel): raise AttributeError(f"No such attribute: {key}") -class LLMMixin: +class LLMMixin(BaseModel): """Mixin class for LLM""" + model_config = ConfigDict(arbitrary_types_allowed=True) + # _config: Optional[Config] = None - _llm_config: Optional[LLMConfig] = None - _llm_instance: Optional[BaseLLM] = None + llm_config: Optional[LLMConfig] = Field(default=None, exclude=True) + llm_instance: Optional[BaseLLM] = Field(default=None, exclude=True) def use_llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI): """Use a LLM provider""" # 更新LLM配置 - self._llm_config = self._config.get_llm_config(name, provider) + self.llm_config = self.config.get_llm_config(name, provider) # 重置LLM实例 - self._llm_instance = None + self.llm_instance = None @property def llm(self) -> BaseLLM: """Return the LLM instance""" - if not self._llm_config: + if not self.llm_config: self.use_llm() - if not self._llm_instance and self._llm_config: - self._llm_instance = create_llm_instance(self._llm_config) - return self._llm_instance + if not self.llm_instance and self.llm_config: + self.llm_instance = create_llm_instance(self.llm_config) + return self.llm_instance -class Context(LLMMixin, BaseModel): +class Context(BaseModel): """Env context for MetaGPT""" model_config = ConfigDict(arbitrary_types_allowed=True) @@ -93,14 +95,14 @@ class Context(LLMMixin, BaseModel): env.update({k: v for k, v in i.items() if isinstance(v, str)}) return env - # def llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: - # """Return a LLM instance""" - # llm_config = self.config.get_llm_config(name, provider) - # - # llm = create_llm_instance(llm_config) - # if llm.cost_manager is None: - # llm.cost_manager = self.cost_manager - # return llm + def llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: + """Return a LLM instance""" + llm_config = self.config.get_llm_config(name, provider) + + llm = create_llm_instance(llm_config) + if llm.cost_manager is None: + llm.cost_manager = self.cost_manager + return llm class ContextMixin: diff --git a/metagpt/llm.py b/metagpt/llm.py index f9a5aaedb..aff72d3c5 100644 --- a/metagpt/llm.py +++ b/metagpt/llm.py @@ -15,4 +15,5 @@ from metagpt.provider.base_llm import BaseLLM def LLM(name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: """get the default llm provider if name is None""" + # context.use_llm(name=name, provider=provider) return context.llm(name=name, provider=provider) From f4ae3bbfd925b6e595806b34a5a016b41d006688 Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 17:39:09 +0800 Subject: [PATCH 18/61] refine code --- metagpt/context.py | 49 ++++++++++++---------------------------------- 1 file changed, 13 insertions(+), 36 deletions(-) diff --git a/metagpt/context.py b/metagpt/context.py index 71570bac6..4016e8d7c 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -9,7 +9,7 @@ import os from pathlib import Path from typing import Optional -from pydantic import BaseModel, ConfigDict, Field +from pydantic import BaseModel, ConfigDict from metagpt.config2 import Config from metagpt.configs.llm_config import LLMConfig, LLMType @@ -42,30 +42,26 @@ class AttrDict(BaseModel): raise AttributeError(f"No such attribute: {key}") -class LLMMixin(BaseModel): +class LLMInstance: """Mixin class for LLM""" - model_config = ConfigDict(arbitrary_types_allowed=True) - # _config: Optional[Config] = None - llm_config: Optional[LLMConfig] = Field(default=None, exclude=True) - llm_instance: Optional[BaseLLM] = Field(default=None, exclude=True) + _llm_config: Optional[LLMConfig] = None + _llm_instance: Optional[BaseLLM] = None - def use_llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI): + def __init__(self, config: Config, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI): """Use a LLM provider""" # 更新LLM配置 - self.llm_config = self.config.get_llm_config(name, provider) + self._llm_config = config.get_llm_config(name, provider) # 重置LLM实例 - self.llm_instance = None + self._llm_instance = None @property - def llm(self) -> BaseLLM: + def instance(self) -> BaseLLM: """Return the LLM instance""" - if not self.llm_config: - self.use_llm() - if not self.llm_instance and self.llm_config: - self.llm_instance = create_llm_instance(self.llm_config) - return self.llm_instance + if not self._llm_instance and self._llm_config: + self._llm_instance = create_llm_instance(self._llm_config) + return self._llm_instance class Context(BaseModel): @@ -78,6 +74,7 @@ class Context(BaseModel): git_repo: Optional[GitRepository] = None src_workspace: Optional[Path] = None cost_manager: CostManager = CostManager() + _llm: Optional[LLMInstance] = None @property def file_repo(self): @@ -97,31 +94,11 @@ class Context(BaseModel): def llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: """Return a LLM instance""" - llm_config = self.config.get_llm_config(name, provider) - - llm = create_llm_instance(llm_config) + llm = LLMInstance(self.config, name, provider).instance if llm.cost_manager is None: llm.cost_manager = self.cost_manager return llm -class ContextMixin: - """Mixin class for configurable objects: Priority: more specific < parent""" - - _context: Optional[Context] = None - - def __init__(self, context: Optional[Context] = None): - self._context = context - - def set_context(self, context: Optional[Context] = None): - """Set parent context""" - self._context = context - - @property - def context(self): - """Get config""" - return self._context - - # Global context, not in Env context = Context() From 2ff28775366dcc0e801bf5f66d0930567ee10854 Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 17:52:34 +0800 Subject: [PATCH 19/61] refine code --- metagpt/config2.py | 3 ++- tests/metagpt/test_config.py | 24 +++++++++++++++++++++++- 2 files changed, 25 insertions(+), 2 deletions(-) diff --git a/metagpt/config2.py b/metagpt/config2.py index 230e090af..6b6f4935b 100644 --- a/metagpt/config2.py +++ b/metagpt/config2.py @@ -153,12 +153,13 @@ def merge_dict(dicts: Iterable[Dict]) -> Dict: return result -class ConfigMixin: +class ConfigMixin(BaseModel): """Mixin class for configurable objects""" _config: Optional[Config] = None def __init__(self, config: Optional[Config] = None): + super().__init__() self._config = config def try_set_parent_config(self, parent_config): diff --git a/tests/metagpt/test_config.py b/tests/metagpt/test_config.py index eecabb546..85e32818d 100644 --- a/tests/metagpt/test_config.py +++ b/tests/metagpt/test_config.py @@ -5,8 +5,9 @@ @Author : alexanderwu @File : test_config.py """ +from pydantic import BaseModel -from metagpt.config2 import Config, config +from metagpt.config2 import Config, ConfigMixin, config from metagpt.configs.llm_config import LLMType from tests.metagpt.provider.mock_llm_config import mock_llm_config @@ -26,3 +27,24 @@ def test_config_from_dict(): cfg = Config(llm={"default": mock_llm_config}) assert cfg assert cfg.llm["default"].api_key == "mock_api_key" + + +class NewModel(ConfigMixin, BaseModel): + a: str = "a" + b: str = "b" + + +def test_config_mixin(): + new_model = NewModel() + assert new_model.a == "a" + assert new_model.b == "b" + assert new_model._config == new_model.config + assert new_model._config is None + + +def test_config_mixin_2(): + i = Config(llm={"default": mock_llm_config}) + new_model = NewModel(config=i) + assert new_model.config == i + assert new_model._config == i + assert new_model.config.llm["default"] == mock_llm_config From 4d3e97b1a85a2926b80b28310338bb771c63b4aa Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 17:56:58 +0800 Subject: [PATCH 20/61] refine code --- tests/metagpt/test_config.py | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/tests/metagpt/test_config.py b/tests/metagpt/test_config.py index 85e32818d..5492d1726 100644 --- a/tests/metagpt/test_config.py +++ b/tests/metagpt/test_config.py @@ -34,7 +34,7 @@ class NewModel(ConfigMixin, BaseModel): b: str = "b" -def test_config_mixin(): +def test_config_mixin_1(): new_model = NewModel() assert new_model.a == "a" assert new_model.b == "b" @@ -44,7 +44,12 @@ def test_config_mixin(): def test_config_mixin_2(): i = Config(llm={"default": mock_llm_config}) - new_model = NewModel(config=i) - assert new_model.config == i - assert new_model._config == i - assert new_model.config.llm["default"] == mock_llm_config + j = Config(llm={"new": mock_llm_config}) + obj = NewModel(config=i) + assert obj.config == i + assert obj._config == i + assert obj.config.llm["default"] == mock_llm_config + + obj.try_set_parent_config(j) + # obj already has a config, so it will not be set + assert obj.config == i From 12223b1d26964f329340d4b67eef860e0f659249 Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 19:43:46 +0800 Subject: [PATCH 21/61] add tests.. --- metagpt/config2.py | 22 +++++++++--------- tests/metagpt/test_config.py | 43 ++++++++++++++++++++++++++++++------ 2 files changed, 47 insertions(+), 18 deletions(-) diff --git a/metagpt/config2.py b/metagpt/config2.py index 6b6f4935b..243a98078 100644 --- a/metagpt/config2.py +++ b/metagpt/config2.py @@ -156,21 +156,21 @@ def merge_dict(dicts: Iterable[Dict]) -> Dict: class ConfigMixin(BaseModel): """Mixin class for configurable objects""" - _config: Optional[Config] = None + config: Optional[Config] = None - def __init__(self, config: Optional[Config] = None): - super().__init__() - self._config = config + def __init__(self, config: Optional[Config] = None, **kwargs): + """Initialize with config""" + super().__init__(**kwargs) + self.set_config(config) - def try_set_parent_config(self, parent_config): + def set(self, k, v, override=False): """Try to set parent config if not set""" - if self._config is None: - self._config = parent_config + if override or not self.__dict__.get(k): + self.__dict__[k] = v - @property - def config(self): - """Get config""" - return self._config + def set_config(self, config: Config, override=False): + """Set config""" + self.set("config", config, override) config = Config.default() diff --git a/tests/metagpt/test_config.py b/tests/metagpt/test_config.py index 5492d1726..81673fc65 100644 --- a/tests/metagpt/test_config.py +++ b/tests/metagpt/test_config.py @@ -29,27 +29,56 @@ def test_config_from_dict(): assert cfg.llm["default"].api_key == "mock_api_key" -class NewModel(ConfigMixin, BaseModel): +class ModelX(ConfigMixin, BaseModel): a: str = "a" b: str = "b" +class WTFMixin(BaseModel): + c: str = "c" + d: str = "d" + + def __init__(self, **data): + super().__init__(**data) + + +class ModelY(WTFMixin, ModelX): + def __init__(self, **data): + super().__init__(**data) + + def test_config_mixin_1(): - new_model = NewModel() + new_model = ModelX() assert new_model.a == "a" assert new_model.b == "b" - assert new_model._config == new_model.config - assert new_model._config is None def test_config_mixin_2(): i = Config(llm={"default": mock_llm_config}) j = Config(llm={"new": mock_llm_config}) - obj = NewModel(config=i) + obj = ModelX(config=i) assert obj.config == i - assert obj._config == i assert obj.config.llm["default"] == mock_llm_config - obj.try_set_parent_config(j) + obj.set_config(j) # obj already has a config, so it will not be set assert obj.config == i + + +def test_config_mixin_3(): + """Test config mixin with multiple inheritance""" + i = Config(llm={"default": mock_llm_config}) + j = Config(llm={"new": mock_llm_config}) + obj = ModelY(config=i) + assert obj.config == i + assert obj.config.llm["default"] == mock_llm_config + + obj.set_config(j) + # obj already has a config, so it will not be set + assert obj.config == i + assert obj.config.llm["default"] == mock_llm_config + + assert obj.a == "a" + assert obj.b == "b" + assert obj.c == "c" + assert obj.d == "d" From 5ad618c49d218826dd33381b17ac61983554b263 Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 19:45:13 +0800 Subject: [PATCH 22/61] add tests.. --- tests/metagpt/test_config.py | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/tests/metagpt/test_config.py b/tests/metagpt/test_config.py index 81673fc65..bd22bf88b 100644 --- a/tests/metagpt/test_config.py +++ b/tests/metagpt/test_config.py @@ -38,13 +38,9 @@ class WTFMixin(BaseModel): c: str = "c" d: str = "d" - def __init__(self, **data): - super().__init__(**data) - class ModelY(WTFMixin, ModelX): - def __init__(self, **data): - super().__init__(**data) + pass def test_config_mixin_1(): From 2ac37300ce40e736aede0f750e9f36aceadfabe1 Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 21:16:11 +0800 Subject: [PATCH 23/61] refine config mixin --- metagpt/config2.py | 7 ++++--- metagpt/roles/role.py | 3 ++- tests/metagpt/test_config.py | 14 +++++++------- 3 files changed, 13 insertions(+), 11 deletions(-) diff --git a/metagpt/config2.py b/metagpt/config2.py index 243a98078..393c46200 100644 --- a/metagpt/config2.py +++ b/metagpt/config2.py @@ -156,7 +156,8 @@ def merge_dict(dicts: Iterable[Dict]) -> Dict: class ConfigMixin(BaseModel): """Mixin class for configurable objects""" - config: Optional[Config] = None + # Env/Role/Action will use this config as private config, or use self.context.config as public config + _config: Optional[Config] = None def __init__(self, config: Optional[Config] = None, **kwargs): """Initialize with config""" @@ -164,13 +165,13 @@ class ConfigMixin(BaseModel): self.set_config(config) def set(self, k, v, override=False): - """Try to set parent config if not set""" + """Set attribute""" if override or not self.__dict__.get(k): self.__dict__[k] = v def set_config(self, config: Config, override=False): """Set config""" - self.set("config", config, override) + self.set("_config", config, override) config = Config.default() diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py index 42996bea8..88bab72cb 100644 --- a/metagpt/roles/role.py +++ b/metagpt/roles/role.py @@ -30,6 +30,7 @@ from pydantic import BaseModel, ConfigDict, Field, SerializeAsAny, model_validat from metagpt.actions import Action, ActionOutput from metagpt.actions.action_node import ActionNode from metagpt.actions.add_requirement import UserRequirement +from metagpt.config2 import ConfigMixin from metagpt.context import Context, context from metagpt.llm import LLM from metagpt.logs import logger @@ -119,7 +120,7 @@ class RoleContext(BaseModel): return self.memory.get() -class Role(SerializationMixin): +class Role(SerializationMixin, ConfigMixin, BaseModel): """Role/Agent""" model_config = ConfigDict(arbitrary_types_allowed=True, exclude=["llm"]) diff --git a/tests/metagpt/test_config.py b/tests/metagpt/test_config.py index bd22bf88b..0a2c0d462 100644 --- a/tests/metagpt/test_config.py +++ b/tests/metagpt/test_config.py @@ -53,12 +53,12 @@ def test_config_mixin_2(): i = Config(llm={"default": mock_llm_config}) j = Config(llm={"new": mock_llm_config}) obj = ModelX(config=i) - assert obj.config == i - assert obj.config.llm["default"] == mock_llm_config + assert obj._config == i + assert obj._config.llm["default"] == mock_llm_config obj.set_config(j) # obj already has a config, so it will not be set - assert obj.config == i + assert obj._config == i def test_config_mixin_3(): @@ -66,13 +66,13 @@ def test_config_mixin_3(): i = Config(llm={"default": mock_llm_config}) j = Config(llm={"new": mock_llm_config}) obj = ModelY(config=i) - assert obj.config == i - assert obj.config.llm["default"] == mock_llm_config + assert obj._config == i + assert obj._config.llm["default"] == mock_llm_config obj.set_config(j) # obj already has a config, so it will not be set - assert obj.config == i - assert obj.config.llm["default"] == mock_llm_config + assert obj._config == i + assert obj._config.llm["default"] == mock_llm_config assert obj.a == "a" assert obj.b == "b" From cf80777f79f97ab3b817c900429b4950b95756ec Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 21:31:38 +0800 Subject: [PATCH 24/61] refine code --- metagpt/actions/action.py | 5 +++-- metagpt/roles/role.py | 43 ++++++++++++++++++++++----------------- 2 files changed, 27 insertions(+), 21 deletions(-) diff --git a/metagpt/actions/action.py b/metagpt/actions/action.py index 9f045bbaa..cdedfcd64 100644 --- a/metagpt/actions/action.py +++ b/metagpt/actions/action.py @@ -10,10 +10,11 @@ from __future__ import annotations from typing import Optional, Union -from pydantic import ConfigDict, Field, model_validator +from pydantic import BaseModel, ConfigDict, Field, model_validator import metagpt from metagpt.actions.action_node import ActionNode +from metagpt.config2 import ConfigMixin from metagpt.context import Context from metagpt.llm import LLM from metagpt.provider.base_llm import BaseLLM @@ -27,7 +28,7 @@ from metagpt.schema import ( from metagpt.utils.file_repository import FileRepository -class Action(SerializationMixin): +class Action(SerializationMixin, ConfigMixin, BaseModel): model_config = ConfigDict(arbitrary_types_allowed=True, exclude=["llm"]) name: str = "" diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py index 88bab72cb..75dff94f2 100644 --- a/metagpt/roles/role.py +++ b/metagpt/roles/role.py @@ -146,6 +146,23 @@ class Role(SerializationMixin, ConfigMixin, BaseModel): __hash__ = object.__hash__ # support Role as hashable type in `Environment.members` + def __init__(self, **data: Any): + self.pydantic_rebuild_model() + super().__init__(**data) + + self.llm.system_prompt = self._get_prefix() + self._watch(data.get("watch") or [UserRequirement]) + + if self.latest_observed_msg: + self.recovered = True + + @staticmethod + def pydantic_rebuild_model(): + from metagpt.environment import Environment + + Environment + Role.model_rebuild() + @property def todo(self) -> Action: return self.rc.todo @@ -157,6 +174,9 @@ class Role(SerializationMixin, ConfigMixin, BaseModel): @property def config(self): + """Role config: role config > context config""" + if self._config: + return self._config return self.context.config @property @@ -177,19 +197,19 @@ class Role(SerializationMixin, ConfigMixin, BaseModel): @property def prompt_schema(self): - return self.context.config.prompt_schema + return self.config.prompt_schema @property def project_name(self): - return self.context.config.project_name + return self.config.project_name @project_name.setter def project_name(self, value): - self.context.config.project_name = value + self.config.project_name = value @property def project_path(self): - return self.context.config.project_path + return self.config.project_path @model_validator(mode="after") def check_addresses(self): @@ -197,21 +217,6 @@ class Role(SerializationMixin, ConfigMixin, BaseModel): self.addresses = {any_to_str(self), self.name} if self.name else {any_to_str(self)} return self - def __init__(self, **data: Any): - # --- avoid PydanticUndefinedAnnotation name 'Environment' is not defined # - from metagpt.environment import Environment - - Environment - # ------ - Role.model_rebuild() - super().__init__(**data) - - self.llm.system_prompt = self._get_prefix() - self._watch(data.get("watch") or [UserRequirement]) - - if self.latest_observed_msg: - self.recovered = True - def _reset(self): self.states = [] self.actions = [] From 4bb4dce4b9f445042bee9e90887d3d144375e746 Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 21:38:09 +0800 Subject: [PATCH 25/61] refine code --- metagpt/roles/role.py | 11 ++++++----- tests/metagpt/test_role.py | 2 +- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py index 75dff94f2..959b5d00d 100644 --- a/metagpt/roles/role.py +++ b/metagpt/roles/role.py @@ -158,6 +158,7 @@ class Role(SerializationMixin, ConfigMixin, BaseModel): @staticmethod def pydantic_rebuild_model(): + """Rebuild model to avoid `RecursionError: maximum recursion depth exceeded in comparison`""" from metagpt.environment import Environment Environment @@ -165,9 +166,11 @@ class Role(SerializationMixin, ConfigMixin, BaseModel): @property def todo(self) -> Action: + """Get action to do""" return self.rc.todo def set_todo(self, value: Optional[Action]): + """Set action to do and update context""" if value: value.g_context = self.context self.rc.todo = value @@ -181,6 +184,7 @@ class Role(SerializationMixin, ConfigMixin, BaseModel): @property def git_repo(self): + """Git repo""" return self.context.git_repo @git_repo.setter @@ -189,6 +193,7 @@ class Role(SerializationMixin, ConfigMixin, BaseModel): @property def src_workspace(self): + """Source workspace under git repo""" return self.context.src_workspace @src_workspace.setter @@ -197,6 +202,7 @@ class Role(SerializationMixin, ConfigMixin, BaseModel): @property def prompt_schema(self): + """Prompt schema: json/markdown""" return self.config.prompt_schema @property @@ -308,11 +314,6 @@ class Role(SerializationMixin, ConfigMixin, BaseModel): env.set_addresses(self, self.addresses) self.llm.system_prompt = self._get_prefix() - @property - def action_count(self): - """Return number of action""" - return len(self.actions) - def _get_prefix(self): """Get the role prefix""" if self.desc: diff --git a/tests/metagpt/test_role.py b/tests/metagpt/test_role.py index 20c8dba6d..c67a8ad8a 100644 --- a/tests/metagpt/test_role.py +++ b/tests/metagpt/test_role.py @@ -112,7 +112,7 @@ async def test_send_to(): def test_init_action(): role = Role() role.add_actions([MockAction, MockAction]) - assert role.action_count == 2 + assert len(role.actions) == 2 @pytest.mark.asyncio From 613515836d45c53e44efe46f0b945f95c7bcb67d Mon Sep 17 00:00:00 2001 From: geekan Date: Tue, 9 Jan 2024 22:04:49 +0800 Subject: [PATCH 26/61] refine code --- metagpt/actions/action.py | 23 +++++------ metagpt/actions/debug_error.py | 4 +- metagpt/actions/design_api.py | 2 +- metagpt/actions/design_api_review.py | 2 +- metagpt/actions/execute_task.py | 2 +- metagpt/actions/invoice_ocr.py | 6 +-- metagpt/actions/prepare_documents.py | 6 +-- metagpt/actions/project_management.py | 2 +- metagpt/actions/rebuild_class_view.py | 6 +-- metagpt/actions/rebuild_sequence_view.py | 2 +- metagpt/actions/research.py | 6 +-- metagpt/actions/run_code.py | 4 +- metagpt/actions/search_and_summarize.py | 23 ++++------- metagpt/actions/summarize_code.py | 4 +- metagpt/actions/talk_action.py | 6 +-- metagpt/actions/write_code.py | 6 +-- metagpt/actions/write_code_review.py | 6 +-- metagpt/actions/write_docstring.py | 2 +- metagpt/actions/write_prd_review.py | 2 +- metagpt/actions/write_teaching_plan.py | 2 +- metagpt/actions/write_test.py | 2 +- metagpt/config.py | 4 +- metagpt/config2.py | 21 ---------- metagpt/context.py | 52 ++++++++++++++++++++++++ metagpt/roles/engineer.py | 16 ++++---- metagpt/roles/role.py | 16 ++------ tests/metagpt/test_config.py | 5 ++- 27 files changed, 123 insertions(+), 109 deletions(-) diff --git a/metagpt/actions/action.py b/metagpt/actions/action.py index cdedfcd64..cabab784f 100644 --- a/metagpt/actions/action.py +++ b/metagpt/actions/action.py @@ -12,10 +12,8 @@ from typing import Optional, Union from pydantic import BaseModel, ConfigDict, Field, model_validator -import metagpt from metagpt.actions.action_node import ActionNode -from metagpt.config2 import ConfigMixin -from metagpt.context import Context +from metagpt.context import ContextMixin from metagpt.llm import LLM from metagpt.provider.base_llm import BaseLLM from metagpt.schema import ( @@ -28,44 +26,43 @@ from metagpt.schema import ( from metagpt.utils.file_repository import FileRepository -class Action(SerializationMixin, ConfigMixin, BaseModel): +class Action(SerializationMixin, ContextMixin, BaseModel): model_config = ConfigDict(arbitrary_types_allowed=True, exclude=["llm"]) name: str = "" llm: BaseLLM = Field(default_factory=LLM, exclude=True) - context: Union[dict, CodingContext, CodeSummarizeContext, TestingContext, RunCodeContext, str, None] = "" + i_context: Union[dict, CodingContext, CodeSummarizeContext, TestingContext, RunCodeContext, str, None] = "" prefix: str = "" # aask*时会加上prefix，作为system_message desc: str = "" # for skill manager node: ActionNode = Field(default=None, exclude=True) - g_context: Optional[Context] = Field(default=metagpt.context.context, exclude=True) @property def git_repo(self): - return self.g_context.git_repo + return self.context.git_repo @property def file_repo(self): - return FileRepository(self.g_context.git_repo) + return FileRepository(self.context.git_repo) @property def src_workspace(self): - return self.g_context.src_workspace + return self.context.src_workspace @property def prompt_schema(self): - return self.g_context.config.prompt_schema + return self.config.prompt_schema @property def project_name(self): - return self.g_context.config.project_name + return self.config.project_name @project_name.setter def project_name(self, value): - self.g_context.config.project_name = value + self.config.project_name = value @property def project_path(self): - return self.g_context.config.project_path + return self.config.project_path @model_validator(mode="before") @classmethod diff --git a/metagpt/actions/debug_error.py b/metagpt/actions/debug_error.py index aa84d1f11..3647640c0 100644 --- a/metagpt/actions/debug_error.py +++ b/metagpt/actions/debug_error.py @@ -47,7 +47,7 @@ Now you should start rewriting the code: class DebugError(Action): - context: RunCodeContext = Field(default_factory=RunCodeContext) + i_context: RunCodeContext = Field(default_factory=RunCodeContext) async def run(self, *args, **kwargs) -> str: output_doc = await self.file_repo.get_file( @@ -63,7 +63,7 @@ class DebugError(Action): logger.info(f"Debug and rewrite {self.context.test_filename}") code_doc = await self.file_repo.get_file( - filename=self.context.code_filename, relative_path=self.g_context.src_workspace + filename=self.context.code_filename, relative_path=self.context.src_workspace ) if not code_doc: return "" diff --git a/metagpt/actions/design_api.py b/metagpt/actions/design_api.py index b89ec7877..3e978f823 100644 --- a/metagpt/actions/design_api.py +++ b/metagpt/actions/design_api.py @@ -37,7 +37,7 @@ NEW_REQ_TEMPLATE = """ class WriteDesign(Action): name: str = "" - context: Optional[str] = None + i_context: Optional[str] = None desc: str = ( "Based on the PRD, think about the system design, and design the corresponding APIs, " "data structures, library tables, processes, and paths. Please provide your design, feedback " diff --git a/metagpt/actions/design_api_review.py b/metagpt/actions/design_api_review.py index fb1b92d85..ccd01a4c3 100644 --- a/metagpt/actions/design_api_review.py +++ b/metagpt/actions/design_api_review.py @@ -13,7 +13,7 @@ from metagpt.actions.action import Action class DesignReview(Action): name: str = "DesignReview" - context: Optional[str] = None + i_context: Optional[str] = None async def run(self, prd, api_design): prompt = ( diff --git a/metagpt/actions/execute_task.py b/metagpt/actions/execute_task.py index 4ae4ee17b..1cc3bd699 100644 --- a/metagpt/actions/execute_task.py +++ b/metagpt/actions/execute_task.py @@ -13,7 +13,7 @@ from metagpt.schema import Message class ExecuteTask(Action): name: str = "ExecuteTask" - context: list[Message] = [] + i_context: list[Message] = [] async def run(self, *args, **kwargs): pass diff --git a/metagpt/actions/invoice_ocr.py b/metagpt/actions/invoice_ocr.py index 36570097a..a3406ff65 100644 --- a/metagpt/actions/invoice_ocr.py +++ b/metagpt/actions/invoice_ocr.py @@ -41,7 +41,7 @@ class InvoiceOCR(Action): """ name: str = "InvoiceOCR" - context: Optional[str] = None + i_context: Optional[str] = None @staticmethod async def _check_file_type(file_path: Path) -> str: @@ -132,7 +132,7 @@ class GenerateTable(Action): """ name: str = "GenerateTable" - context: Optional[str] = None + i_context: Optional[str] = None llm: BaseLLM = Field(default_factory=LLM) language: str = "ch" @@ -177,7 +177,7 @@ class ReplyQuestion(Action): """ name: str = "ReplyQuestion" - context: Optional[str] = None + i_context: Optional[str] = None llm: BaseLLM = Field(default_factory=LLM) language: str = "ch" diff --git a/metagpt/actions/prepare_documents.py b/metagpt/actions/prepare_documents.py index ae5aaf2b5..8a9e78b2a 100644 --- a/metagpt/actions/prepare_documents.py +++ b/metagpt/actions/prepare_documents.py @@ -22,11 +22,11 @@ class PrepareDocuments(Action): """PrepareDocuments Action: initialize project folder and add new requirements to docs/requirements.txt.""" name: str = "PrepareDocuments" - context: Optional[str] = None + i_context: Optional[str] = None @property def config(self): - return self.g_context.config + return self.context.config def _init_repo(self): """Initialize the Git environment.""" @@ -39,7 +39,7 @@ class PrepareDocuments(Action): shutil.rmtree(path) self.config.project_path = path self.config.project_name = path.name - self.g_context.git_repo = GitRepository(local_path=path, auto_init=True) + self.context.git_repo = GitRepository(local_path=path, auto_init=True) async def run(self, with_messages, **kwargs): """Create and initialize the workspace folder, initialize the Git environment.""" diff --git a/metagpt/actions/project_management.py b/metagpt/actions/project_management.py index b40da824f..bb8141a74 100644 --- a/metagpt/actions/project_management.py +++ b/metagpt/actions/project_management.py @@ -36,7 +36,7 @@ NEW_REQ_TEMPLATE = """ class WriteTasks(Action): name: str = "CreateTasks" - context: Optional[str] = None + i_context: Optional[str] = None async def run(self, with_messages): system_design_file_repo = self.git_repo.new_file_repository(SYSTEM_DESIGN_FILE_REPO) diff --git a/metagpt/actions/rebuild_class_view.py b/metagpt/actions/rebuild_class_view.py index 5128b9fee..876beccec 100644 --- a/metagpt/actions/rebuild_class_view.py +++ b/metagpt/actions/rebuild_class_view.py @@ -32,13 +32,13 @@ class RebuildClassView(Action): async def run(self, with_messages=None, format=CONFIG.prompt_schema): graph_repo_pathname = CONFIG.git_repo.workdir / GRAPH_REPO_FILE_REPO / CONFIG.git_repo.workdir.name graph_db = await DiGraphRepository.load_from(str(graph_repo_pathname.with_suffix(".json"))) - repo_parser = RepoParser(base_directory=Path(self.context)) + repo_parser = RepoParser(base_directory=Path(self.i_context)) # use pylint - class_views, relationship_views, package_root = await repo_parser.rebuild_class_views(path=Path(self.context)) + class_views, relationship_views, package_root = await repo_parser.rebuild_class_views(path=Path(self.i_context)) await GraphRepository.update_graph_db_with_class_views(graph_db, class_views) await GraphRepository.update_graph_db_with_class_relationship_views(graph_db, relationship_views) # use ast - direction, diff_path = self._diff_path(path_root=Path(self.context).resolve(), package_root=package_root) + direction, diff_path = self._diff_path(path_root=Path(self.i_context).resolve(), package_root=package_root) symbols = repo_parser.generate_symbols() for file_info in symbols: # Align to the same root directory in accordance with `class_views`. diff --git a/metagpt/actions/rebuild_sequence_view.py b/metagpt/actions/rebuild_sequence_view.py index 865050c93..bc128d8b0 100644 --- a/metagpt/actions/rebuild_sequence_view.py +++ b/metagpt/actions/rebuild_sequence_view.py @@ -41,7 +41,7 @@ class RebuildSequenceView(Action): async def _rebuild_sequence_view(self, entry, graph_db): filename = entry.subject.split(":", 1)[0] - src_filename = RebuildSequenceView._get_full_filename(root=self.context, pathname=filename) + src_filename = RebuildSequenceView._get_full_filename(root=self.i_context, pathname=filename) content = await aread(filename=src_filename, encoding="utf-8") content = f"```python\n{content}\n```\n\n---\nTranslate the code above into Mermaid Sequence Diagram." data = await self.llm.aask( diff --git a/metagpt/actions/research.py b/metagpt/actions/research.py index 90b08cb6a..84067ad92 100644 --- a/metagpt/actions/research.py +++ b/metagpt/actions/research.py @@ -81,7 +81,7 @@ class CollectLinks(Action): """Action class to collect links from a search engine.""" name: str = "CollectLinks" - context: Optional[str] = None + i_context: Optional[str] = None desc: str = "Collect links from a search engine." search_engine: SearchEngine = Field(default_factory=SearchEngine) @@ -177,7 +177,7 @@ class WebBrowseAndSummarize(Action): """Action class to explore the web and provide summaries of articles and webpages.""" name: str = "WebBrowseAndSummarize" - context: Optional[str] = None + i_context: Optional[str] = None llm: BaseLLM = Field(default_factory=LLM) desc: str = "Explore the web and provide summaries of articles and webpages." browse_func: Union[Callable[[list[str]], None], None] = None @@ -248,7 +248,7 @@ class ConductResearch(Action): """Action class to conduct research and generate a research report.""" name: str = "ConductResearch" - context: Optional[str] = None + i_context: Optional[str] = None llm: BaseLLM = Field(default_factory=LLM) def __init__(self, **kwargs): diff --git a/metagpt/actions/run_code.py b/metagpt/actions/run_code.py index 0d42308c1..8fdda0a0d 100644 --- a/metagpt/actions/run_code.py +++ b/metagpt/actions/run_code.py @@ -76,7 +76,7 @@ standard errors: class RunCode(Action): name: str = "RunCode" - context: RunCodeContext = Field(default_factory=RunCodeContext) + i_context: RunCodeContext = Field(default_factory=RunCodeContext) @classmethod async def run_text(cls, code) -> Tuple[str, str]: @@ -93,7 +93,7 @@ class RunCode(Action): additional_python_paths = [str(path) for path in additional_python_paths] # Copy the current environment variables - env = self.g_context.new_environ() + env = self.context.new_environ() # Modify the PYTHONPATH environment variable additional_python_paths = [working_directory] + additional_python_paths diff --git a/metagpt/actions/search_and_summarize.py b/metagpt/actions/search_and_summarize.py index 39ca23df5..59b35cd58 100644 --- a/metagpt/actions/search_and_summarize.py +++ b/metagpt/actions/search_and_summarize.py @@ -8,10 +8,9 @@ from typing import Any, Optional import pydantic -from pydantic import Field, model_validator +from pydantic import model_validator from metagpt.actions import Action -from metagpt.config import Config from metagpt.logs import logger from metagpt.schema import Message from metagpt.tools import SearchEngineType @@ -106,28 +105,22 @@ You are a member of a professional butler team and will provide helpful suggesti class SearchAndSummarize(Action): name: str = "" content: Optional[str] = None - config: None = Field(default_factory=Config) engine: Optional[SearchEngineType] = None search_func: Optional[Any] = None search_engine: SearchEngine = None result: str = "" - @model_validator(mode="before") - @classmethod - def validate_engine_and_run_func(cls, values): - engine = values.get("engine") - search_func = values.get("search_func") - config = Config() - - if engine is None: - engine = config.search_engine + @model_validator(mode="after") + def validate_engine_and_run_func(self): + if self.engine is None: + self.engine = self.config.search_engine try: - search_engine = SearchEngine(engine=engine, run_func=search_func) + search_engine = SearchEngine(engine=self.engine, run_func=self.search_func) except pydantic.ValidationError: search_engine = None - values["search_engine"] = search_engine - return values + self.search_engine = search_engine + return self async def run(self, context: list[Message], system_text=SEARCH_AND_SUMMARIZE_SYSTEM) -> str: if self.search_engine is None: diff --git a/metagpt/actions/summarize_code.py b/metagpt/actions/summarize_code.py index 948eceab2..690d5c77b 100644 --- a/metagpt/actions/summarize_code.py +++ b/metagpt/actions/summarize_code.py @@ -90,7 +90,7 @@ flowchart TB class SummarizeCode(Action): name: str = "SummarizeCode" - context: CodeSummarizeContext = Field(default_factory=CodeSummarizeContext) + i_context: CodeSummarizeContext = Field(default_factory=CodeSummarizeContext) @retry(stop=stop_after_attempt(2), wait=wait_random_exponential(min=1, max=60)) async def summarize_code(self, prompt): @@ -103,7 +103,7 @@ class SummarizeCode(Action): design_doc = await repo.get_file(filename=design_pathname.name, relative_path=SYSTEM_DESIGN_FILE_REPO) task_pathname = Path(self.context.task_filename) task_doc = await repo.get_file(filename=task_pathname.name, relative_path=TASK_FILE_REPO) - src_file_repo = self.git_repo.new_file_repository(relative_path=self.g_context.src_workspace) + src_file_repo = self.git_repo.new_file_repository(relative_path=self.context.src_workspace) code_blocks = [] for filename in self.context.codes_filenames: code_doc = await src_file_repo.get(filename) diff --git a/metagpt/actions/talk_action.py b/metagpt/actions/talk_action.py index eab1740fc..253b829ed 100644 --- a/metagpt/actions/talk_action.py +++ b/metagpt/actions/talk_action.py @@ -15,18 +15,18 @@ from metagpt.schema import Message class TalkAction(Action): - context: str + i_context: str history_summary: str = "" knowledge: str = "" rsp: Optional[Message] = None @property def agent_description(self): - return self.g_context.kwargs.agent_description + return self.context.kwargs.agent_description @property def language(self): - return self.g_context.kwargs.language or config.language + return self.context.kwargs.language or config.language @property def prompt(self): diff --git a/metagpt/actions/write_code.py b/metagpt/actions/write_code.py index 2b8f91a1d..779fe52a6 100644 --- a/metagpt/actions/write_code.py +++ b/metagpt/actions/write_code.py @@ -85,7 +85,7 @@ ATTENTION: Use '##' to SPLIT SECTIONS, not '#'. Output format carefully referenc class WriteCode(Action): name: str = "WriteCode" - context: Document = Field(default_factory=Document) + i_context: Document = Field(default_factory=Document) @retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(6)) async def write_code(self, prompt) -> str: @@ -116,7 +116,7 @@ class WriteCode(Action): coding_context.task_doc, exclude=self.context.filename, git_repo=self.git_repo, - src_workspace=self.g_context.src_workspace, + src_workspace=self.context.src_workspace, ) prompt = PROMPT_TEMPLATE.format( @@ -132,7 +132,7 @@ class WriteCode(Action): code = await self.write_code(prompt) if not coding_context.code_doc: # avoid root_path pydantic ValidationError if use WriteCode alone - root_path = self.g_context.src_workspace if self.g_context.src_workspace else "" + root_path = self.context.src_workspace if self.context.src_workspace else "" coding_context.code_doc = Document(filename=coding_context.filename, root_path=str(root_path)) coding_context.code_doc.content = code return coding_context diff --git a/metagpt/actions/write_code_review.py b/metagpt/actions/write_code_review.py index 4433a7ab9..6ff9d5aa4 100644 --- a/metagpt/actions/write_code_review.py +++ b/metagpt/actions/write_code_review.py @@ -119,7 +119,7 @@ REWRITE_CODE_TEMPLATE = """ class WriteCodeReview(Action): name: str = "WriteCodeReview" - context: CodingContext = Field(default_factory=CodingContext) + i_context: CodingContext = Field(default_factory=CodingContext) @retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(6)) async def write_code_review_and_rewrite(self, context_prompt, cr_prompt, filename): @@ -136,14 +136,14 @@ class WriteCodeReview(Action): async def run(self, *args, **kwargs) -> CodingContext: iterative_code = self.context.code_doc.content - k = self.g_context.config.code_review_k_times or 1 + k = self.context.config.code_review_k_times or 1 for i in range(k): format_example = FORMAT_EXAMPLE.format(filename=self.context.code_doc.filename) task_content = self.context.task_doc.content if self.context.task_doc else "" code_context = await WriteCode.get_codes( self.context.task_doc, exclude=self.context.filename, - git_repo=self.g_context.git_repo, + git_repo=self.context.git_repo, src_workspace=self.src_workspace, ) context = "\n".join( diff --git a/metagpt/actions/write_docstring.py b/metagpt/actions/write_docstring.py index 8b8335517..79204e6a4 100644 --- a/metagpt/actions/write_docstring.py +++ b/metagpt/actions/write_docstring.py @@ -161,7 +161,7 @@ class WriteDocstring(Action): """ desc: str = "Write docstring for code." - context: Optional[str] = None + i_context: Optional[str] = None async def run( self, diff --git a/metagpt/actions/write_prd_review.py b/metagpt/actions/write_prd_review.py index 2babe38db..68fb5d9e8 100644 --- a/metagpt/actions/write_prd_review.py +++ b/metagpt/actions/write_prd_review.py @@ -13,7 +13,7 @@ from metagpt.actions.action import Action class WritePRDReview(Action): name: str = "" - context: Optional[str] = None + i_context: Optional[str] = None prd: Optional[str] = None desc: str = "Based on the PRD, conduct a PRD Review, providing clear and detailed feedback" diff --git a/metagpt/actions/write_teaching_plan.py b/metagpt/actions/write_teaching_plan.py index 76923a663..04507fda3 100644 --- a/metagpt/actions/write_teaching_plan.py +++ b/metagpt/actions/write_teaching_plan.py @@ -15,7 +15,7 @@ from metagpt.logs import logger class WriteTeachingPlanPart(Action): """Write Teaching Plan Part""" - context: Optional[str] = None + i_context: Optional[str] = None topic: str = "" language: str = "Chinese" rsp: Optional[str] = None diff --git a/metagpt/actions/write_test.py b/metagpt/actions/write_test.py index 96486311f..38b1cf03c 100644 --- a/metagpt/actions/write_test.py +++ b/metagpt/actions/write_test.py @@ -39,7 +39,7 @@ you should correctly import the necessary classes based on these file locations! class WriteTest(Action): name: str = "WriteTest" - context: Optional[TestingContext] = None + i_context: Optional[TestingContext] = None async def write_code(self, prompt): code_rsp = await self._aask(prompt) diff --git a/metagpt/config.py b/metagpt/config.py index 0c7b54f83..952ccc962 100644 --- a/metagpt/config.py +++ b/metagpt/config.py @@ -133,8 +133,8 @@ class Config(metaclass=Singleton): self.ollama_api_base = self._get("OLLAMA_API_BASE") self.ollama_api_model = self._get("OLLAMA_API_MODEL") - if not self._get("DISABLE_LLM_PROVIDER_CHECK"): - _ = self.get_default_llm_provider_enum() + # if not self._get("DISABLE_LLM_PROVIDER_CHECK"): + # _ = self.get_default_llm_provider_enum() self.openai_base_url = self._get("OPENAI_BASE_URL") self.openai_proxy = self._get("OPENAI_PROXY") or self.global_proxy diff --git a/metagpt/config2.py b/metagpt/config2.py index 393c46200..cb5c22ac2 100644 --- a/metagpt/config2.py +++ b/metagpt/config2.py @@ -153,25 +153,4 @@ def merge_dict(dicts: Iterable[Dict]) -> Dict: return result -class ConfigMixin(BaseModel): - """Mixin class for configurable objects""" - - # Env/Role/Action will use this config as private config, or use self.context.config as public config - _config: Optional[Config] = None - - def __init__(self, config: Optional[Config] = None, **kwargs): - """Initialize with config""" - super().__init__(**kwargs) - self.set_config(config) - - def set(self, k, v, override=False): - """Set attribute""" - if override or not self.__dict__.get(k): - self.__dict__[k] = v - - def set_config(self, config: Config, override=False): - """Set config""" - self.set("_config", config, override) - - config = Config.default() diff --git a/metagpt/context.py b/metagpt/context.py index 4016e8d7c..74f7b133d 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -100,5 +100,57 @@ class Context(BaseModel): return llm +class ContextMixin(BaseModel): + """Mixin class for context and config""" + + # Env/Role/Action will use this context as private context, or use self.context as public context + _context: Optional[Context] = None + # Env/Role/Action will use this config as private config, or use self.context.config as public config + _config: Optional[Config] = None + + def __init__(self, context: Optional[Context] = None, config: Optional[Config] = None, **kwargs): + """Initialize with config""" + super().__init__(**kwargs) + self.set_context(context) + self.set_config(config) + + def set(self, k, v, override=False): + """Set attribute""" + if override or not self.__dict__.get(k): + self.__dict__[k] = v + + def set_context(self, context: Context, override=True): + """Set context""" + self.set("_context", context, override) + + def set_config(self, config: Config, override=False): + """Set config""" + self.set("_config", config, override) + + @property + def config(self): + """Role config: role config > context config""" + if self._config: + return self._config + return self.context.config + + @config.setter + def config(self, config: Config): + """Set config""" + self.set_config(config) + + @property + def context(self): + """Role context: role context > context""" + if self._context: + return self._context + return context + + @context.setter + def context(self, context: Context): + """Set context""" + self.set_context(context) + + # Global context, not in Env context = Context() diff --git a/metagpt/roles/engineer.py b/metagpt/roles/engineer.py index ad0c1ac92..dc9f31686 100644 --- a/metagpt/roles/engineer.py +++ b/metagpt/roles/engineer.py @@ -159,9 +159,9 @@ class Engineer(Role): src_relative_path = self.src_workspace.relative_to(self.git_repo.workdir) for todo in self.summarize_todos: summary = await todo.run() - summary_filename = Path(todo.context.design_filename).with_suffix(".md").name - dependencies = {todo.context.design_filename, todo.context.task_filename} - for filename in todo.context.codes_filenames: + summary_filename = Path(todo.i_context.design_filename).with_suffix(".md").name + dependencies = {todo.i_context.design_filename, todo.i_context.task_filename} + for filename in todo.i_context.codes_filenames: rpath = src_relative_path / filename dependencies.add(str(rpath)) await code_summaries_pdf_file_repo.save( @@ -169,15 +169,15 @@ class Engineer(Role): ) is_pass, reason = await self._is_pass(summary) if not is_pass: - todo.context.reason = reason - tasks.append(todo.context.dict()) + todo.i_context.reason = reason + tasks.append(todo.i_context.dict()) await code_summaries_file_repo.save( - filename=Path(todo.context.design_filename).name, - content=todo.context.model_dump_json(), + filename=Path(todo.i_context.design_filename).name, + content=todo.i_context.model_dump_json(), dependencies=dependencies, ) else: - await code_summaries_file_repo.delete(filename=Path(todo.context.design_filename).name) + await code_summaries_file_repo.delete(filename=Path(todo.i_context.design_filename).name) logger.info(f"--max-auto-summarize-code={self.config.max_auto_summarize_code}") if not tasks or self.config.max_auto_summarize_code == 0: diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py index 959b5d00d..e31eabd23 100644 --- a/metagpt/roles/role.py +++ b/metagpt/roles/role.py @@ -30,8 +30,7 @@ from pydantic import BaseModel, ConfigDict, Field, SerializeAsAny, model_validat from metagpt.actions import Action, ActionOutput from metagpt.actions.action_node import ActionNode from metagpt.actions.add_requirement import UserRequirement -from metagpt.config2 import ConfigMixin -from metagpt.context import Context, context +from metagpt.context import ContextMixin from metagpt.llm import LLM from metagpt.logs import logger from metagpt.memory import Memory @@ -120,7 +119,7 @@ class RoleContext(BaseModel): return self.memory.get() -class Role(SerializationMixin, ConfigMixin, BaseModel): +class Role(SerializationMixin, ContextMixin, BaseModel): """Role/Agent""" model_config = ConfigDict(arbitrary_types_allowed=True, exclude=["llm"]) @@ -142,7 +141,7 @@ class Role(SerializationMixin, ConfigMixin, BaseModel): # builtin variables recovered: bool = False # to tag if a recovered role latest_observed_msg: Optional[Message] = None # record the latest observed message when interrupted - context: Optional[Context] = Field(default=context, exclude=True) + # context: Optional[Context] = Field(default=context, exclude=True) __hash__ = object.__hash__ # support Role as hashable type in `Environment.members` @@ -172,16 +171,9 @@ class Role(SerializationMixin, ConfigMixin, BaseModel): def set_todo(self, value: Optional[Action]): """Set action to do and update context""" if value: - value.g_context = self.context + value.context = self.context self.rc.todo = value - @property - def config(self): - """Role config: role config > context config""" - if self._config: - return self._config - return self.context.config - @property def git_repo(self): """Git repo""" diff --git a/tests/metagpt/test_config.py b/tests/metagpt/test_config.py index 0a2c0d462..c74b16930 100644 --- a/tests/metagpt/test_config.py +++ b/tests/metagpt/test_config.py @@ -7,8 +7,9 @@ """ from pydantic import BaseModel -from metagpt.config2 import Config, ConfigMixin, config +from metagpt.config2 import Config, config from metagpt.configs.llm_config import LLMType +from metagpt.context import ContextMixin from tests.metagpt.provider.mock_llm_config import mock_llm_config @@ -29,7 +30,7 @@ def test_config_from_dict(): assert cfg.llm["default"].api_key == "mock_api_key" -class ModelX(ConfigMixin, BaseModel): +class ModelX(ContextMixin, BaseModel): a: str = "a" b: str = "b" From 742891775cfb51b4f53f6a8b10c0e76e19d708bf Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 11:10:51 +0800 Subject: [PATCH 27/61] refine code --- metagpt/roles/role.py | 1 - 1 file changed, 1 deletion(-) diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py index e31eabd23..98cc05234 100644 --- a/metagpt/roles/role.py +++ b/metagpt/roles/role.py @@ -141,7 +141,6 @@ class Role(SerializationMixin, ContextMixin, BaseModel): # builtin variables recovered: bool = False # to tag if a recovered role latest_observed_msg: Optional[Message] = None # record the latest observed message when interrupted - # context: Optional[Context] = Field(default=context, exclude=True) __hash__ = object.__hash__ # support Role as hashable type in `Environment.members` From bee5a973d0baf97593ea33e00e0eef4082340713 Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 13:40:55 +0800 Subject: [PATCH 28/61] disable pretty_exceptions_show_locals --- metagpt/startup.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/metagpt/startup.py b/metagpt/startup.py index cd5b4dac7..14092edd2 100644 --- a/metagpt/startup.py +++ b/metagpt/startup.py @@ -9,7 +9,7 @@ import typer from metagpt.config2 import config from metagpt.const import METAGPT_ROOT -app = typer.Typer(add_completion=False) +app = typer.Typer(add_completion=False, pretty_exceptions_show_locals=False) def generate_repo( From b0b6fbbba45ccad4c9a5315361a0971195c38c17 Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 13:56:02 +0800 Subject: [PATCH 29/61] refine code: gloabl context to CONTEXT --- metagpt/context.py | 4 +-- metagpt/llm.py | 4 +-- metagpt/roles/assistant.py | 6 ++-- tests/conftest.py | 8 ++--- tests/metagpt/actions/test_debug_error.py | 8 ++--- tests/metagpt/actions/test_design_api.py | 4 +-- .../metagpt/actions/test_prepare_documents.py | 14 ++++----- .../actions/test_project_management.py | 8 ++--- tests/metagpt/actions/test_summarize_code.py | 18 +++++------ tests/metagpt/actions/test_write_code.py | 20 ++++++------- tests/metagpt/actions/test_write_prd.py | 4 +-- tests/metagpt/roles/test_architect.py | 4 +-- tests/metagpt/roles/test_assistant.py | 10 +++---- tests/metagpt/roles/test_engineer.py | 30 +++++++++---------- tests/metagpt/roles/test_qa_engineer.py | 8 ++--- tests/metagpt/roles/test_teacher.py | 6 ++-- tests/metagpt/test_context.py | 6 ++-- tests/metagpt/test_environment.py | 8 ++--- 18 files changed, 85 insertions(+), 85 deletions(-) diff --git a/metagpt/context.py b/metagpt/context.py index 74f7b133d..4083a1696 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -144,7 +144,7 @@ class ContextMixin(BaseModel): """Role context: role context > context""" if self._context: return self._context - return context + return CONTEXT @context.setter def context(self, context: Context): @@ -153,4 +153,4 @@ class ContextMixin(BaseModel): # Global context, not in Env -context = Context() +CONTEXT = Context() diff --git a/metagpt/llm.py b/metagpt/llm.py index aff72d3c5..d393738bb 100644 --- a/metagpt/llm.py +++ b/metagpt/llm.py @@ -9,11 +9,11 @@ from typing import Optional from metagpt.configs.llm_config import LLMType -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.provider.base_llm import BaseLLM def LLM(name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: """get the default llm provider if name is None""" # context.use_llm(name=name, provider=provider) - return context.llm(name=name, provider=provider) + return CONTEXT.llm(name=name, provider=provider) diff --git a/metagpt/roles/assistant.py b/metagpt/roles/assistant.py index 90a33ad6a..8939094ed 100644 --- a/metagpt/roles/assistant.py +++ b/metagpt/roles/assistant.py @@ -22,7 +22,7 @@ from pydantic import Field from metagpt.actions.skill_action import ArgumentsParingAction, SkillAction from metagpt.actions.talk_action import TalkAction -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.learn.skill_loader import SkillsDeclaration from metagpt.logs import logger from metagpt.memory.brain_memory import BrainMemory @@ -48,7 +48,7 @@ class Assistant(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self.constraints = self.constraints.format(language=kwargs.get("language") or context.kwargs.language) + self.constraints = self.constraints.format(language=kwargs.get("language") or CONTEXT.kwargs.language) async def think(self) -> bool: """Everything will be done part by part.""" @@ -56,7 +56,7 @@ class Assistant(Role): if not last_talk: return False if not self.skills: - skill_path = Path(context.kwargs.SKILL_PATH) if context.kwargs.SKILL_PATH else None + skill_path = Path(CONTEXT.kwargs.SKILL_PATH) if CONTEXT.kwargs.SKILL_PATH else None self.skills = await SkillsDeclaration.load(skill_yaml_file_name=skill_path) prompt = "" diff --git a/tests/conftest.py b/tests/conftest.py index fab1fa198..faa2d92e9 100644 --- a/tests/conftest.py +++ b/tests/conftest.py @@ -16,7 +16,7 @@ import uuid import pytest from metagpt.const import DEFAULT_WORKSPACE_ROOT, TEST_DATA_PATH -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.llm import LLM from metagpt.logs import logger from metagpt.utils.git_repository import GitRepository @@ -141,12 +141,12 @@ def loguru_caplog(caplog): # init & dispose git repo @pytest.fixture(scope="function", autouse=True) def setup_and_teardown_git_repo(request): - context.git_repo = GitRepository(local_path=DEFAULT_WORKSPACE_ROOT / f"unittest/{uuid.uuid4().hex}") - context.config.git_reinit = True + CONTEXT.git_repo = GitRepository(local_path=DEFAULT_WORKSPACE_ROOT / f"unittest/{uuid.uuid4().hex}") + CONTEXT.config.git_reinit = True # Destroy git repo at the end of the test session. def fin(): - context.git_repo.delete_repository() + CONTEXT.git_repo.delete_repository() # Register the function for destroying the environment. request.addfinalizer(fin) diff --git a/tests/metagpt/actions/test_debug_error.py b/tests/metagpt/actions/test_debug_error.py index ff9e9cd81..922aa8613 100644 --- a/tests/metagpt/actions/test_debug_error.py +++ b/tests/metagpt/actions/test_debug_error.py @@ -12,7 +12,7 @@ import pytest from metagpt.actions.debug_error import DebugError from metagpt.const import TEST_CODES_FILE_REPO, TEST_OUTPUTS_FILE_REPO -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.schema import RunCodeContext, RunCodeResult CODE_CONTENT = ''' @@ -117,7 +117,7 @@ if __name__ == '__main__': @pytest.mark.asyncio async def test_debug_error(): - context.src_workspace = context.git_repo.workdir / uuid.uuid4().hex + CONTEXT.src_workspace = CONTEXT.git_repo.workdir / uuid.uuid4().hex ctx = RunCodeContext( code_filename="player.py", test_filename="test_player.py", @@ -125,8 +125,8 @@ async def test_debug_error(): output_filename="output.log", ) - repo = context.file_repo - await repo.save_file(filename=ctx.code_filename, content=CODE_CONTENT, relative_path=context.src_workspace) + repo = CONTEXT.file_repo + await repo.save_file(filename=ctx.code_filename, content=CODE_CONTENT, relative_path=CONTEXT.src_workspace) await repo.save_file(filename=ctx.test_filename, content=TEST_CONTENT, relative_path=TEST_CODES_FILE_REPO) output_data = RunCodeResult( stdout=";", diff --git a/tests/metagpt/actions/test_design_api.py b/tests/metagpt/actions/test_design_api.py index 88cb612fc..027f7ca20 100644 --- a/tests/metagpt/actions/test_design_api.py +++ b/tests/metagpt/actions/test_design_api.py @@ -10,7 +10,7 @@ import pytest from metagpt.actions.design_api import WriteDesign from metagpt.const import PRDS_FILE_REPO -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.schema import Message @@ -18,7 +18,7 @@ from metagpt.schema import Message @pytest.mark.asyncio async def test_design_api(): inputs = ["我们需要一个音乐播放器，它应该有播放、暂停、上一曲、下一曲等功能。"] # PRD_SAMPLE - repo = context.file_repo + repo = CONTEXT.file_repo for prd in inputs: await repo.save_file("new_prd.txt", content=prd, relative_path=PRDS_FILE_REPO) diff --git a/tests/metagpt/actions/test_prepare_documents.py b/tests/metagpt/actions/test_prepare_documents.py index a67f89874..fde971f3c 100644 --- a/tests/metagpt/actions/test_prepare_documents.py +++ b/tests/metagpt/actions/test_prepare_documents.py @@ -10,7 +10,7 @@ import pytest from metagpt.actions.prepare_documents import PrepareDocuments from metagpt.const import DOCS_FILE_REPO, REQUIREMENT_FILENAME -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.schema import Message @@ -18,12 +18,12 @@ from metagpt.schema import Message async def test_prepare_documents(): msg = Message(content="New user requirements balabala...") - if context.git_repo: - context.git_repo.delete_repository() - context.git_repo = None + if CONTEXT.git_repo: + CONTEXT.git_repo.delete_repository() + CONTEXT.git_repo = None - await PrepareDocuments(g_context=context).run(with_messages=[msg]) - assert context.git_repo - doc = await context.file_repo.get_file(filename=REQUIREMENT_FILENAME, relative_path=DOCS_FILE_REPO) + await PrepareDocuments(g_context=CONTEXT).run(with_messages=[msg]) + assert CONTEXT.git_repo + doc = await CONTEXT.file_repo.get_file(filename=REQUIREMENT_FILENAME, relative_path=DOCS_FILE_REPO) assert doc assert doc.content == msg.content diff --git a/tests/metagpt/actions/test_project_management.py b/tests/metagpt/actions/test_project_management.py index a462319b8..1eadb49fb 100644 --- a/tests/metagpt/actions/test_project_management.py +++ b/tests/metagpt/actions/test_project_management.py @@ -10,7 +10,7 @@ import pytest from metagpt.actions.project_management import WriteTasks from metagpt.const import PRDS_FILE_REPO, SYSTEM_DESIGN_FILE_REPO -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.schema import Message from tests.metagpt.actions.mock_json import DESIGN, PRD @@ -18,9 +18,9 @@ from tests.metagpt.actions.mock_json import DESIGN, PRD @pytest.mark.asyncio async def test_design_api(): - await context.file_repo.save_file("1.txt", content=str(PRD), relative_path=PRDS_FILE_REPO) - await context.file_repo.save_file("1.txt", content=str(DESIGN), relative_path=SYSTEM_DESIGN_FILE_REPO) - logger.info(context.git_repo) + await CONTEXT.file_repo.save_file("1.txt", content=str(PRD), relative_path=PRDS_FILE_REPO) + await CONTEXT.file_repo.save_file("1.txt", content=str(DESIGN), relative_path=SYSTEM_DESIGN_FILE_REPO) + logger.info(CONTEXT.git_repo) action = WriteTasks() diff --git a/tests/metagpt/actions/test_summarize_code.py b/tests/metagpt/actions/test_summarize_code.py index 1c14d256d..2f7b5c61d 100644 --- a/tests/metagpt/actions/test_summarize_code.py +++ b/tests/metagpt/actions/test_summarize_code.py @@ -11,7 +11,7 @@ import pytest from metagpt.actions.summarize_code import SummarizeCode from metagpt.config import CONFIG from metagpt.const import SYSTEM_DESIGN_FILE_REPO, TASK_FILE_REPO -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.schema import CodeSummarizeContext @@ -178,15 +178,15 @@ class Snake: @pytest.mark.asyncio async def test_summarize_code(): - context.src_workspace = context.git_repo.workdir / "src" - await context.file_repo.save_file(filename="1.json", relative_path=SYSTEM_DESIGN_FILE_REPO, content=DESIGN_CONTENT) - await context.file_repo.save_file(filename="1.json", relative_path=TASK_FILE_REPO, content=TASK_CONTENT) - await context.file_repo.save_file(filename="food.py", relative_path=CONFIG.src_workspace, content=FOOD_PY) - await context.file_repo.save_file(filename="game.py", relative_path=CONFIG.src_workspace, content=GAME_PY) - await context.file_repo.save_file(filename="main.py", relative_path=CONFIG.src_workspace, content=MAIN_PY) - await context.file_repo.save_file(filename="snake.py", relative_path=CONFIG.src_workspace, content=SNAKE_PY) + CONTEXT.src_workspace = CONTEXT.git_repo.workdir / "src" + await CONTEXT.file_repo.save_file(filename="1.json", relative_path=SYSTEM_DESIGN_FILE_REPO, content=DESIGN_CONTENT) + await CONTEXT.file_repo.save_file(filename="1.json", relative_path=TASK_FILE_REPO, content=TASK_CONTENT) + await CONTEXT.file_repo.save_file(filename="food.py", relative_path=CONFIG.src_workspace, content=FOOD_PY) + await CONTEXT.file_repo.save_file(filename="game.py", relative_path=CONFIG.src_workspace, content=GAME_PY) + await CONTEXT.file_repo.save_file(filename="main.py", relative_path=CONFIG.src_workspace, content=MAIN_PY) + await CONTEXT.file_repo.save_file(filename="snake.py", relative_path=CONFIG.src_workspace, content=SNAKE_PY) - src_file_repo = context.git_repo.new_file_repository(relative_path=CONFIG.src_workspace) + src_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=CONFIG.src_workspace) all_files = src_file_repo.all_files ctx = CodeSummarizeContext(design_filename="1.json", task_filename="1.json", codes_filenames=all_files) action = SummarizeCode(context=ctx) diff --git a/tests/metagpt/actions/test_write_code.py b/tests/metagpt/actions/test_write_code.py index 2a7b8e696..cfc5863f4 100644 --- a/tests/metagpt/actions/test_write_code.py +++ b/tests/metagpt/actions/test_write_code.py @@ -18,7 +18,7 @@ from metagpt.const import ( TASK_FILE_REPO, TEST_OUTPUTS_FILE_REPO, ) -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.provider.openai_api import OpenAILLM as LLM from metagpt.schema import CodingContext, Document @@ -53,35 +53,35 @@ async def test_write_code_directly(): @pytest.mark.asyncio async def test_write_code_deps(): # Prerequisites - context.src_workspace = context.git_repo.workdir / "snake1/snake1" + CONTEXT.src_workspace = CONTEXT.git_repo.workdir / "snake1/snake1" demo_path = Path(__file__).parent / "../../data/demo_project" - await context.file_repo.save_file( + await CONTEXT.file_repo.save_file( filename="test_game.py.json", content=await aread(str(demo_path / "test_game.py.json")), relative_path=TEST_OUTPUTS_FILE_REPO, ) - await context.file_repo.save_file( + await CONTEXT.file_repo.save_file( filename="20231221155954.json", content=await aread(str(demo_path / "code_summaries.json")), relative_path=CODE_SUMMARIES_FILE_REPO, ) - await context.file_repo.save_file( + await CONTEXT.file_repo.save_file( filename="20231221155954.json", content=await aread(str(demo_path / "system_design.json")), relative_path=SYSTEM_DESIGN_FILE_REPO, ) - await context.file_repo.save_file( + await CONTEXT.file_repo.save_file( filename="20231221155954.json", content=await aread(str(demo_path / "tasks.json")), relative_path=TASK_FILE_REPO ) - await context.file_repo.save_file( - filename="main.py", content='if __name__ == "__main__":\nmain()', relative_path=context.src_workspace + await CONTEXT.file_repo.save_file( + filename="main.py", content='if __name__ == "__main__":\nmain()', relative_path=CONTEXT.src_workspace ) ccontext = CodingContext( filename="game.py", - design_doc=await context.file_repo.get_file( + design_doc=await CONTEXT.file_repo.get_file( filename="20231221155954.json", relative_path=SYSTEM_DESIGN_FILE_REPO ), - task_doc=await context.file_repo.get_file(filename="20231221155954.json", relative_path=TASK_FILE_REPO), + task_doc=await CONTEXT.file_repo.get_file(filename="20231221155954.json", relative_path=TASK_FILE_REPO), code_doc=Document(filename="game.py", content="", root_path="snake1"), ) coding_doc = Document(root_path="snake1", filename="game.py", content=ccontext.json()) diff --git a/tests/metagpt/actions/test_write_prd.py b/tests/metagpt/actions/test_write_prd.py index 1f92c079b..faa5b77a4 100644 --- a/tests/metagpt/actions/test_write_prd.py +++ b/tests/metagpt/actions/test_write_prd.py @@ -10,7 +10,7 @@ import pytest from metagpt.actions import UserRequirement, WritePRD from metagpt.const import DOCS_FILE_REPO, PRDS_FILE_REPO, REQUIREMENT_FILENAME -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.roles.product_manager import ProductManager from metagpt.roles.role import RoleReactMode @@ -33,7 +33,7 @@ async def test_write_prd(new_filename): # Assert the prd is not None or empty assert prd is not None assert prd.content != "" - assert context.git_repo.new_file_repository(relative_path=PRDS_FILE_REPO).changed_files + assert CONTEXT.git_repo.new_file_repository(relative_path=PRDS_FILE_REPO).changed_files if __name__ == "__main__": diff --git a/tests/metagpt/roles/test_architect.py b/tests/metagpt/roles/test_architect.py index 69afbcfe1..f9d6606ac 100644 --- a/tests/metagpt/roles/test_architect.py +++ b/tests/metagpt/roles/test_architect.py @@ -13,7 +13,7 @@ import pytest from metagpt.actions import WriteDesign, WritePRD from metagpt.const import PRDS_FILE_REPO -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.roles import Architect from metagpt.schema import Message @@ -25,7 +25,7 @@ from tests.metagpt.roles.mock import MockMessages async def test_architect(): # Prerequisites filename = uuid.uuid4().hex + ".json" - await awrite(context.git_repo.workdir / PRDS_FILE_REPO / filename, data=MockMessages.prd.content) + await awrite(CONTEXT.git_repo.workdir / PRDS_FILE_REPO / filename, data=MockMessages.prd.content) role = Architect() rsp = await role.run(with_message=Message(content="", cause_by=WritePRD)) diff --git a/tests/metagpt/roles/test_assistant.py b/tests/metagpt/roles/test_assistant.py index 8797ba7f1..4ef44d77a 100644 --- a/tests/metagpt/roles/test_assistant.py +++ b/tests/metagpt/roles/test_assistant.py @@ -12,7 +12,7 @@ from pydantic import BaseModel from metagpt.actions.skill_action import SkillAction from metagpt.actions.talk_action import TalkAction -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.memory.brain_memory import BrainMemory from metagpt.roles.assistant import Assistant from metagpt.schema import Message @@ -21,7 +21,7 @@ from metagpt.utils.common import any_to_str @pytest.mark.asyncio async def test_run(): - context.kwargs.language = "Chinese" + CONTEXT.kwargs.language = "Chinese" class Input(BaseModel): memory: BrainMemory @@ -65,7 +65,7 @@ async def test_run(): "cause_by": any_to_str(SkillAction), }, ] - context.kwargs.agent_skills = [ + CONTEXT.kwargs.agent_skills = [ {"id": 1, "name": "text_to_speech", "type": "builtin", "config": {}, "enabled": True}, {"id": 2, "name": "text_to_image", "type": "builtin", "config": {}, "enabled": True}, {"id": 3, "name": "ai_call", "type": "builtin", "config": {}, "enabled": True}, @@ -77,8 +77,8 @@ async def test_run(): for i in inputs: seed = Input(**i) - context.kwargs.language = seed.language - context.kwargs.agent_description = seed.agent_description + CONTEXT.kwargs.language = seed.language + CONTEXT.kwargs.agent_description = seed.agent_description role = Assistant(language="Chinese") role.memory = seed.memory # Restore historical conversation content. while True: diff --git a/tests/metagpt/roles/test_engineer.py b/tests/metagpt/roles/test_engineer.py index b35321a1b..710e74b8f 100644 --- a/tests/metagpt/roles/test_engineer.py +++ b/tests/metagpt/roles/test_engineer.py @@ -19,7 +19,7 @@ from metagpt.const import ( SYSTEM_DESIGN_FILE_REPO, TASK_FILE_REPO, ) -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.roles.engineer import Engineer from metagpt.schema import CodingContext, Message @@ -32,19 +32,19 @@ from tests.metagpt.roles.mock import STRS_FOR_PARSING, TASKS, MockMessages async def test_engineer(): # Prerequisites rqno = "20231221155954.json" - await context.file_repo.save_file(REQUIREMENT_FILENAME, content=MockMessages.req.content) - await context.file_repo.save_file(rqno, relative_path=PRDS_FILE_REPO, content=MockMessages.prd.content) - await context.file_repo.save_file( + await CONTEXT.file_repo.save_file(REQUIREMENT_FILENAME, content=MockMessages.req.content) + await CONTEXT.file_repo.save_file(rqno, relative_path=PRDS_FILE_REPO, content=MockMessages.prd.content) + await CONTEXT.file_repo.save_file( rqno, relative_path=SYSTEM_DESIGN_FILE_REPO, content=MockMessages.system_design.content ) - await context.file_repo.save_file(rqno, relative_path=TASK_FILE_REPO, content=MockMessages.json_tasks.content) + await CONTEXT.file_repo.save_file(rqno, relative_path=TASK_FILE_REPO, content=MockMessages.json_tasks.content) engineer = Engineer() rsp = await engineer.run(Message(content="", cause_by=WriteTasks)) logger.info(rsp) assert rsp.cause_by == any_to_str(WriteCode) - src_file_repo = context.git_repo.new_file_repository(context.src_workspace) + src_file_repo = CONTEXT.git_repo.new_file_repository(CONTEXT.src_workspace) assert src_file_repo.changed_files @@ -116,19 +116,19 @@ async def test_new_coding_context(): # Prerequisites demo_path = Path(__file__).parent / "../../data/demo_project" deps = json.loads(await aread(demo_path / "dependencies.json")) - dependency = await context.git_repo.get_dependency() + dependency = await CONTEXT.git_repo.get_dependency() for k, v in deps.items(): await dependency.update(k, set(v)) data = await aread(demo_path / "system_design.json") rqno = "20231221155954.json" - await awrite(context.git_repo.workdir / SYSTEM_DESIGN_FILE_REPO / rqno, data) + await awrite(CONTEXT.git_repo.workdir / SYSTEM_DESIGN_FILE_REPO / rqno, data) data = await aread(demo_path / "tasks.json") - await awrite(context.git_repo.workdir / TASK_FILE_REPO / rqno, data) + await awrite(CONTEXT.git_repo.workdir / TASK_FILE_REPO / rqno, data) - context.src_workspace = Path(context.git_repo.workdir) / "game_2048" - src_file_repo = context.git_repo.new_file_repository(relative_path=context.src_workspace) - task_file_repo = context.git_repo.new_file_repository(relative_path=TASK_FILE_REPO) - design_file_repo = context.git_repo.new_file_repository(relative_path=SYSTEM_DESIGN_FILE_REPO) + CONTEXT.src_workspace = Path(CONTEXT.git_repo.workdir) / "game_2048" + src_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=CONTEXT.src_workspace) + task_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=TASK_FILE_REPO) + design_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=SYSTEM_DESIGN_FILE_REPO) filename = "game.py" ctx_doc = await Engineer._new_coding_doc( @@ -149,8 +149,8 @@ async def test_new_coding_context(): assert ctx.task_doc.content assert ctx.code_doc - context.git_repo.add_change({f"{TASK_FILE_REPO}/{rqno}": ChangeType.UNTRACTED}) - context.git_repo.commit("mock env") + CONTEXT.git_repo.add_change({f"{TASK_FILE_REPO}/{rqno}": ChangeType.UNTRACTED}) + CONTEXT.git_repo.commit("mock env") await src_file_repo.save(filename=filename, content="content") role = Engineer() assert not role.code_todos diff --git a/tests/metagpt/roles/test_qa_engineer.py b/tests/metagpt/roles/test_qa_engineer.py index 825fe58a3..c51642e6a 100644 --- a/tests/metagpt/roles/test_qa_engineer.py +++ b/tests/metagpt/roles/test_qa_engineer.py @@ -13,7 +13,7 @@ from pydantic import Field from metagpt.actions import DebugError, RunCode, WriteTest from metagpt.actions.summarize_code import SummarizeCode -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.environment import Environment from metagpt.roles import QaEngineer from metagpt.schema import Message @@ -23,10 +23,10 @@ from metagpt.utils.common import any_to_str, aread, awrite async def test_qa(): # Prerequisites demo_path = Path(__file__).parent / "../../data/demo_project" - context.src_workspace = Path(context.git_repo.workdir) / "qa/game_2048" + CONTEXT.src_workspace = Path(CONTEXT.git_repo.workdir) / "qa/game_2048" data = await aread(filename=demo_path / "game.py", encoding="utf-8") - await awrite(filename=context.src_workspace / "game.py", data=data, encoding="utf-8") - await awrite(filename=Path(context.git_repo.workdir) / "requirements.txt", data="") + await awrite(filename=CONTEXT.src_workspace / "game.py", data=data, encoding="utf-8") + await awrite(filename=Path(CONTEXT.git_repo.workdir) / "requirements.txt", data="") class MockEnv(Environment): msgs: List[Message] = Field(default_factory=list) diff --git a/tests/metagpt/roles/test_teacher.py b/tests/metagpt/roles/test_teacher.py index ff2139929..8bd37f482 100644 --- a/tests/metagpt/roles/test_teacher.py +++ b/tests/metagpt/roles/test_teacher.py @@ -10,7 +10,7 @@ from typing import Dict, Optional import pytest from pydantic import BaseModel -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.roles.teacher import Teacher from metagpt.schema import Message @@ -97,8 +97,8 @@ async def test_new_file_name(): @pytest.mark.asyncio async def test_run(): - context.kwargs.language = "Chinese" - context.kwargs.teaching_language = "English" + CONTEXT.kwargs.language = "Chinese" + CONTEXT.kwargs.teaching_language = "English" lesson = """ UNIT 1 Making New Friends TOPIC 1 Welcome to China! diff --git a/tests/metagpt/test_context.py b/tests/metagpt/test_context.py index 2d52325bc..f1c9da4e7 100644 --- a/tests/metagpt/test_context.py +++ b/tests/metagpt/test_context.py @@ -6,7 +6,7 @@ @File : test_context.py """ from metagpt.configs.llm_config import LLMType -from metagpt.context import AttrDict, Context, context +from metagpt.context import CONTEXT, AttrDict, Context def test_attr_dict_1(): @@ -52,11 +52,11 @@ def test_context_1(): def test_context_2(): - llm = context.config.get_openai_llm() + llm = CONTEXT.config.get_openai_llm() assert llm is not None assert llm.api_type == LLMType.OPENAI - kwargs = context.kwargs + kwargs = CONTEXT.kwargs assert kwargs is not None kwargs.test_key = "test_value" diff --git a/tests/metagpt/test_environment.py b/tests/metagpt/test_environment.py index d7d8d990a..49fd8a5fc 100644 --- a/tests/metagpt/test_environment.py +++ b/tests/metagpt/test_environment.py @@ -13,7 +13,7 @@ from pathlib import Path import pytest from metagpt.actions import UserRequirement -from metagpt.context import context +from metagpt.context import CONTEXT from metagpt.environment import Environment from metagpt.logs import logger from metagpt.roles import Architect, ProductManager, Role @@ -46,9 +46,9 @@ def test_get_roles(env: Environment): @pytest.mark.asyncio async def test_publish_and_process_message(env: Environment): - if context.git_repo: - context.git_repo.delete_repository() - context.git_repo = None + if CONTEXT.git_repo: + CONTEXT.git_repo.delete_repository() + CONTEXT.git_repo = None product_manager = ProductManager(name="Alice", profile="Product Manager", goal="做AI Native产品", constraints="资源有限") architect = Architect( From ba477a93d55377c76e93f5395a3f1320b4518aa7 Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 15:34:49 +0800 Subject: [PATCH 30/61] refine code --- metagpt/actions/action.py | 3 - metagpt/actions/invoice_ocr.py | 1 - metagpt/actions/research.py | 1 - metagpt/context.py | 89 ++++++++++++++++---------- metagpt/roles/engineer.py | 2 +- metagpt/roles/role.py | 3 - metagpt/roles/sk_agent.py | 3 - metagpt/tools/moderation.py | 6 +- metagpt/tools/openai_text_to_image.py | 3 - tests/metagpt/test_config.py | 3 + tests/metagpt/test_context.py | 6 +- tests/metagpt/tools/test_moderation.py | 3 +- 12 files changed, 67 insertions(+), 56 deletions(-) diff --git a/metagpt/actions/action.py b/metagpt/actions/action.py index cabab784f..cad8112d2 100644 --- a/metagpt/actions/action.py +++ b/metagpt/actions/action.py @@ -14,8 +14,6 @@ from pydantic import BaseModel, ConfigDict, Field, model_validator from metagpt.actions.action_node import ActionNode from metagpt.context import ContextMixin -from metagpt.llm import LLM -from metagpt.provider.base_llm import BaseLLM from metagpt.schema import ( CodeSummarizeContext, CodingContext, @@ -30,7 +28,6 @@ class Action(SerializationMixin, ContextMixin, BaseModel): model_config = ConfigDict(arbitrary_types_allowed=True, exclude=["llm"]) name: str = "" - llm: BaseLLM = Field(default_factory=LLM, exclude=True) i_context: Union[dict, CodingContext, CodeSummarizeContext, TestingContext, RunCodeContext, str, None] = "" prefix: str = "" # aask*时会加上prefix，作为system_message desc: str = "" # for skill manager diff --git a/metagpt/actions/invoice_ocr.py b/metagpt/actions/invoice_ocr.py index a3406ff65..60939d2eb 100644 --- a/metagpt/actions/invoice_ocr.py +++ b/metagpt/actions/invoice_ocr.py @@ -133,7 +133,6 @@ class GenerateTable(Action): name: str = "GenerateTable" i_context: Optional[str] = None - llm: BaseLLM = Field(default_factory=LLM) language: str = "ch" async def run(self, ocr_results: list, filename: str, *args, **kwargs) -> dict[str, str]: diff --git a/metagpt/actions/research.py b/metagpt/actions/research.py index 84067ad92..ce366e3d2 100644 --- a/metagpt/actions/research.py +++ b/metagpt/actions/research.py @@ -178,7 +178,6 @@ class WebBrowseAndSummarize(Action): name: str = "WebBrowseAndSummarize" i_context: Optional[str] = None - llm: BaseLLM = Field(default_factory=LLM) desc: str = "Explore the web and provide summaries of articles and webpages." browse_func: Union[Callable[[list[str]], None], None] = None web_browser_engine: Optional[WebBrowserEngine] = None diff --git a/metagpt/context.py b/metagpt/context.py index 4083a1696..bd86fb039 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -42,28 +42,6 @@ class AttrDict(BaseModel): raise AttributeError(f"No such attribute: {key}") -class LLMInstance: - """Mixin class for LLM""" - - # _config: Optional[Config] = None - _llm_config: Optional[LLMConfig] = None - _llm_instance: Optional[BaseLLM] = None - - def __init__(self, config: Config, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI): - """Use a LLM provider""" - # 更新LLM配置 - self._llm_config = config.get_llm_config(name, provider) - # 重置LLM实例 - self._llm_instance = None - - @property - def instance(self) -> BaseLLM: - """Return the LLM instance""" - if not self._llm_instance and self._llm_config: - self._llm_instance = create_llm_instance(self._llm_config) - return self._llm_instance - - class Context(BaseModel): """Env context for MetaGPT""" @@ -74,7 +52,8 @@ class Context(BaseModel): git_repo: Optional[GitRepository] = None src_workspace: Optional[Path] = None cost_manager: CostManager = CostManager() - _llm: Optional[LLMInstance] = None + + _llm: Optional[BaseLLM] = None @property def file_repo(self): @@ -92,12 +71,19 @@ class Context(BaseModel): env.update({k: v for k, v in i.items() if isinstance(v, str)}) return env + # def use_llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: + # """Use a LLM instance""" + # self._llm_config = self.config.get_llm_config(name, provider) + # self._llm = None + # return self._llm + def llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: - """Return a LLM instance""" - llm = LLMInstance(self.config, name, provider).instance - if llm.cost_manager is None: - llm.cost_manager = self.cost_manager - return llm + """Return a LLM instance, fixme: support multiple llm instances""" + if self._llm is None: + self._llm = create_llm_instance(self.config.get_llm_config(name, provider)) + if self._llm.cost_manager is None: + self._llm.cost_manager = self.cost_manager + return self._llm class ContextMixin(BaseModel): @@ -108,11 +94,22 @@ class ContextMixin(BaseModel): # Env/Role/Action will use this config as private config, or use self.context.config as public config _config: Optional[Config] = None - def __init__(self, context: Optional[Context] = None, config: Optional[Config] = None, **kwargs): + # Env/Role/Action will use this llm as private llm, or use self.context._llm instance + _llm_config: Optional[LLMConfig] = None + _llm: Optional[BaseLLM] = None + + def __init__( + self, + context: Optional[Context] = None, + config: Optional[Config] = None, + llm: Optional[BaseLLM] = None, + **kwargs, + ): """Initialize with config""" super().__init__(**kwargs) self.set_context(context) self.set_config(config) + self.set_llm(llm) def set(self, k, v, override=False): """Set attribute""" @@ -127,30 +124,56 @@ class ContextMixin(BaseModel): """Set config""" self.set("_config", config, override) + def set_llm_config(self, llm_config: LLMConfig, override=False): + """Set llm config""" + self.set("_llm_config", llm_config, override) + + def set_llm(self, llm: BaseLLM, override=False): + """Set llm""" + self.set("_llm", llm, override) + + def use_llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: + """Use a LLM instance""" + self._llm_config = self.config.get_llm_config(name, provider) + self._llm = None + return self.llm + @property - def config(self): + def config(self) -> Config: """Role config: role config > context config""" if self._config: return self._config return self.context.config @config.setter - def config(self, config: Config): + def config(self, config: Config) -> None: """Set config""" self.set_config(config) @property - def context(self): + def context(self) -> Context: """Role context: role context > context""" if self._context: return self._context return CONTEXT @context.setter - def context(self, context: Context): + def context(self, context: Context) -> None: """Set context""" self.set_context(context) + @property + def llm(self) -> BaseLLM: + """Role llm: role llm > context llm""" + if self._llm_config and not self._llm: + self._llm = self.context.llm(self._llm_config.name, self._llm_config.provider) + return self._llm or self.context.llm() + + @llm.setter + def llm(self, llm: BaseLLM) -> None: + """Set llm""" + self._llm = llm + # Global context, not in Env CONTEXT = Context() diff --git a/metagpt/roles/engineer.py b/metagpt/roles/engineer.py index dc9f31686..364566b37 100644 --- a/metagpt/roles/engineer.py +++ b/metagpt/roles/engineer.py @@ -109,7 +109,7 @@ class Engineer(Role): coding_context = await todo.run() # Code review if review: - action = WriteCodeReview(context=coding_context, g_context=self.context, llm=self.llm) + action = WriteCodeReview(context=coding_context, _context=self.context, llm=self.llm) self._init_action_system_message(action) coding_context = await action.run() await src_file_repo.save( diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py index 98cc05234..9c6832d8f 100644 --- a/metagpt/roles/role.py +++ b/metagpt/roles/role.py @@ -31,11 +31,9 @@ from metagpt.actions import Action, ActionOutput from metagpt.actions.action_node import ActionNode from metagpt.actions.add_requirement import UserRequirement from metagpt.context import ContextMixin -from metagpt.llm import LLM from metagpt.logs import logger from metagpt.memory import Memory from metagpt.provider import HumanProvider -from metagpt.provider.base_llm import BaseLLM from metagpt.schema import Message, MessageQueue, SerializationMixin from metagpt.utils.common import any_to_name, any_to_str, role_raise_decorator from metagpt.utils.repair_llm_raw_output import extract_state_value_from_output @@ -131,7 +129,6 @@ class Role(SerializationMixin, ContextMixin, BaseModel): desc: str = "" is_human: bool = False - llm: BaseLLM = Field(default_factory=LLM, exclude=True) # Each role has its own LLM, use different system message role_id: str = "" states: list[str] = [] actions: list[SerializeAsAny[Action]] = Field(default=[], validate_default=True) diff --git a/metagpt/roles/sk_agent.py b/metagpt/roles/sk_agent.py index 468905fce..200ed5051 100644 --- a/metagpt/roles/sk_agent.py +++ b/metagpt/roles/sk_agent.py @@ -17,9 +17,7 @@ from semantic_kernel.planning.basic_planner import BasicPlanner, Plan from metagpt.actions import UserRequirement from metagpt.actions.execute_task import ExecuteTask -from metagpt.llm import LLM from metagpt.logs import logger -from metagpt.provider.base_llm import BaseLLM from metagpt.roles import Role from metagpt.schema import Message from metagpt.utils.make_sk_kernel import make_sk_kernel @@ -44,7 +42,6 @@ class SkAgent(Role): plan: Plan = Field(default=None, exclude=True) planner_cls: Any = None planner: Union[BasicPlanner, SequentialPlanner, ActionPlanner] = None - llm: BaseLLM = Field(default_factory=LLM) kernel: Kernel = Field(default_factory=Kernel) import_semantic_skill_from_directory: Callable = Field(default=None, exclude=True) import_skill: Callable = Field(default=None, exclude=True) diff --git a/metagpt/tools/moderation.py b/metagpt/tools/moderation.py index cda164ec5..f00b0e1f2 100644 --- a/metagpt/tools/moderation.py +++ b/metagpt/tools/moderation.py @@ -7,12 +7,12 @@ """ from typing import Union -from metagpt.llm import LLM +from metagpt.provider.base_llm import BaseLLM class Moderation: - def __init__(self): - self.llm = LLM() + def __init__(self, llm: BaseLLM): + self.llm = llm def handle_moderation_results(self, results): resp = [] diff --git a/metagpt/tools/openai_text_to_image.py b/metagpt/tools/openai_text_to_image.py index fc31b95f7..bf7c5e799 100644 --- a/metagpt/tools/openai_text_to_image.py +++ b/metagpt/tools/openai_text_to_image.py @@ -16,9 +16,6 @@ from metagpt.provider.base_llm import BaseLLM class OpenAIText2Image: def __init__(self, llm: BaseLLM): - """ - :param openai_api_key: OpenAI API key, For more details, checkout: `https://platform.openai.com/account/api-keys` - """ self.llm = llm async def text_2_image(self, text, size_type="1024x1024"): diff --git a/tests/metagpt/test_config.py b/tests/metagpt/test_config.py index c74b16930..cfde7a04c 100644 --- a/tests/metagpt/test_config.py +++ b/tests/metagpt/test_config.py @@ -79,3 +79,6 @@ def test_config_mixin_3(): assert obj.b == "b" assert obj.c == "c" assert obj.d == "d" + + print(obj.__dict__.keys()) + assert "_config" in obj.__dict__.keys() diff --git a/tests/metagpt/test_context.py b/tests/metagpt/test_context.py index f1c9da4e7..255794c41 100644 --- a/tests/metagpt/test_context.py +++ b/tests/metagpt/test_context.py @@ -66,7 +66,5 @@ def test_context_2(): def test_context_3(): ctx = Context() ctx.use_llm(provider=LLMType.OPENAI) - assert ctx.llm_config is not None - assert ctx.llm_config.api_type == LLMType.OPENAI - assert ctx.llm is not None - assert "gpt" in ctx.llm.model + assert ctx.llm() is not None + assert "gpt" in ctx.llm().model diff --git a/tests/metagpt/tools/test_moderation.py b/tests/metagpt/tools/test_moderation.py index 534fe812a..d265c3f78 100644 --- a/tests/metagpt/tools/test_moderation.py +++ b/tests/metagpt/tools/test_moderation.py @@ -9,6 +9,7 @@ import pytest from metagpt.config import CONFIG +from metagpt.context import CONTEXT from metagpt.tools.moderation import Moderation @@ -27,7 +28,7 @@ async def test_amoderation(content): assert not CONFIG.OPENAI_API_TYPE assert CONFIG.OPENAI_API_MODEL - moderation = Moderation() + moderation = Moderation(CONTEXT.llm()) results = await moderation.amoderation(content=content) assert isinstance(results, list) assert len(results) == len(content) From cd29edcc4f3479dbff6fa2be873ae5a738d93e8e Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 16:02:05 +0800 Subject: [PATCH 31/61] refine code --- metagpt/actions/invoice_ocr.py | 6 ------ metagpt/actions/research.py | 6 ------ metagpt/context.py | 10 +++++----- tests/metagpt/test_context.py | 11 +++++++---- tests/metagpt/tools/test_moderation.py | 4 ++-- 5 files changed, 14 insertions(+), 23 deletions(-) diff --git a/metagpt/actions/invoice_ocr.py b/metagpt/actions/invoice_ocr.py index 60939d2eb..7cf71a8ff 100644 --- a/metagpt/actions/invoice_ocr.py +++ b/metagpt/actions/invoice_ocr.py @@ -16,17 +16,14 @@ from typing import Optional import pandas as pd from paddleocr import PaddleOCR -from pydantic import Field from metagpt.actions import Action from metagpt.const import INVOICE_OCR_TABLE_PATH -from metagpt.llm import LLM from metagpt.logs import logger from metagpt.prompts.invoice_ocr import ( EXTRACT_OCR_MAIN_INFO_PROMPT, REPLY_OCR_QUESTION_PROMPT, ) -from metagpt.provider.base_llm import BaseLLM from metagpt.utils.common import OutputParser from metagpt.utils.file import File @@ -175,9 +172,6 @@ class ReplyQuestion(Action): """ - name: str = "ReplyQuestion" - i_context: Optional[str] = None - llm: BaseLLM = Field(default_factory=LLM) language: str = "ch" async def run(self, query: str, ocr_result: list, *args, **kwargs) -> str: diff --git a/metagpt/actions/research.py b/metagpt/actions/research.py index ce366e3d2..d2db228ae 100644 --- a/metagpt/actions/research.py +++ b/metagpt/actions/research.py @@ -9,9 +9,7 @@ from pydantic import Field, parse_obj_as from metagpt.actions import Action from metagpt.config import CONFIG -from metagpt.llm import LLM from metagpt.logs import logger -from metagpt.provider.base_llm import BaseLLM from metagpt.tools.search_engine import SearchEngine from metagpt.tools.web_browser_engine import WebBrowserEngine, WebBrowserEngineType from metagpt.utils.common import OutputParser @@ -246,10 +244,6 @@ class WebBrowseAndSummarize(Action): class ConductResearch(Action): """Action class to conduct research and generate a research report.""" - name: str = "ConductResearch" - i_context: Optional[str] = None - llm: BaseLLM = Field(default_factory=LLM) - def __init__(self, **kwargs): super().__init__(**kwargs) if CONFIG.model_for_researcher_report: diff --git a/metagpt/context.py b/metagpt/context.py index bd86fb039..0686aedc3 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -78,11 +78,11 @@ class Context(BaseModel): # return self._llm def llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: - """Return a LLM instance, fixme: support multiple llm instances""" - if self._llm is None: - self._llm = create_llm_instance(self.config.get_llm_config(name, provider)) - if self._llm.cost_manager is None: - self._llm.cost_manager = self.cost_manager + """Return a LLM instance, fixme: support cache""" + # if self._llm is None: + self._llm = create_llm_instance(self.config.get_llm_config(name, provider)) + if self._llm.cost_manager is None: + self._llm.cost_manager = self.cost_manager return self._llm diff --git a/tests/metagpt/test_context.py b/tests/metagpt/test_context.py index 255794c41..d662a906a 100644 --- a/tests/metagpt/test_context.py +++ b/tests/metagpt/test_context.py @@ -64,7 +64,10 @@ def test_context_2(): def test_context_3(): - ctx = Context() - ctx.use_llm(provider=LLMType.OPENAI) - assert ctx.llm() is not None - assert "gpt" in ctx.llm().model + # ctx = Context() + # ctx.use_llm(provider=LLMType.OPENAI) + # assert ctx._llm_config is not None + # assert ctx._llm_config.api_type == LLMType.OPENAI + # assert ctx.llm() is not None + # assert "gpt" in ctx.llm().model + pass diff --git a/tests/metagpt/tools/test_moderation.py b/tests/metagpt/tools/test_moderation.py index d265c3f78..e1226484a 100644 --- a/tests/metagpt/tools/test_moderation.py +++ b/tests/metagpt/tools/test_moderation.py @@ -9,7 +9,7 @@ import pytest from metagpt.config import CONFIG -from metagpt.context import CONTEXT +from metagpt.llm import LLM from metagpt.tools.moderation import Moderation @@ -28,7 +28,7 @@ async def test_amoderation(content): assert not CONFIG.OPENAI_API_TYPE assert CONFIG.OPENAI_API_MODEL - moderation = Moderation(CONTEXT.llm()) + moderation = Moderation(LLM()) results = await moderation.amoderation(content=content) assert isinstance(results, list) assert len(results) == len(content) From 00a212b52b69b9a17ed071d52ca1f64a8eeba25f Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 16:17:48 +0800 Subject: [PATCH 32/61] refine code --- metagpt/context.py | 1 + metagpt/roles/engineer.py | 8 ++++---- metagpt/roles/qa_engineer.py | 6 +++--- metagpt/roles/teacher.py | 2 +- 4 files changed, 9 insertions(+), 8 deletions(-) diff --git a/metagpt/context.py b/metagpt/context.py index 0686aedc3..4badafcc4 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -165,6 +165,7 @@ class ContextMixin(BaseModel): @property def llm(self) -> BaseLLM: """Role llm: role llm > context llm""" + # logger.info(f"class:{self.__class__.__name__}, llm: {self._llm}, llm_config: {self._llm_config}") if self._llm_config and not self._llm: self._llm = self.context.llm(self._llm_config.name, self._llm_config.provider) return self._llm or self.context.llm() diff --git a/metagpt/roles/engineer.py b/metagpt/roles/engineer.py index 364566b37..0d277813e 100644 --- a/metagpt/roles/engineer.py +++ b/metagpt/roles/engineer.py @@ -109,7 +109,7 @@ class Engineer(Role): coding_context = await todo.run() # Code review if review: - action = WriteCodeReview(context=coding_context, _context=self.context, llm=self.llm) + action = WriteCodeReview(i_context=coding_context, context=self.context, llm=self.llm) self._init_action_system_message(action) coding_context = await action.run() await src_file_repo.save( @@ -282,7 +282,7 @@ class Engineer(Role): ) changed_files.docs[task_filename] = coding_doc self.code_todos = [ - WriteCode(context=i, g_context=self.context, llm=self.llm) for i in changed_files.docs.values() + WriteCode(i_context=i, context=self.context, llm=self.llm) for i in changed_files.docs.values() ] # Code directly modified by the user. dependency = await self.git_repo.get_dependency() @@ -297,7 +297,7 @@ class Engineer(Role): dependency=dependency, ) changed_files.docs[filename] = coding_doc - self.code_todos.append(WriteCode(context=coding_doc, g_context=self.context, llm=self.llm)) + self.code_todos.append(WriteCode(i_context=coding_doc, context=self.context, llm=self.llm)) if self.code_todos: self.set_todo(self.code_todos[0]) @@ -313,7 +313,7 @@ class Engineer(Role): summarizations[ctx].append(filename) for ctx, filenames in summarizations.items(): ctx.codes_filenames = filenames - self.summarize_todos.append(SummarizeCode(context=ctx, llm=self.llm)) + self.summarize_todos.append(SummarizeCode(i_context=ctx, llm=self.llm)) if self.summarize_todos: self.set_todo(self.summarize_todos[0]) diff --git a/metagpt/roles/qa_engineer.py b/metagpt/roles/qa_engineer.py index 80b0fd39a..9483ea260 100644 --- a/metagpt/roles/qa_engineer.py +++ b/metagpt/roles/qa_engineer.py @@ -71,7 +71,7 @@ class QaEngineer(Role): ) logger.info(f"Writing {test_doc.filename}..") context = TestingContext(filename=test_doc.filename, test_doc=test_doc, code_doc=code_doc) - context = await WriteTest(context=context, g_context=self.context, llm=self.llm).run() + context = await WriteTest(i_context=context, context=self.context, llm=self.llm).run() await tests_file_repo.save( filename=context.test_doc.filename, content=context.test_doc.content, @@ -112,7 +112,7 @@ class QaEngineer(Role): return run_code_context.code = src_doc.content run_code_context.test_code = test_doc.content - result = await RunCode(context=run_code_context, g_context=self.context, llm=self.llm).run() + result = await RunCode(i_context=run_code_context, context=self.context, llm=self.llm).run() run_code_context.output_filename = run_code_context.test_filename + ".json" await self.context.git_repo.new_file_repository(TEST_OUTPUTS_FILE_REPO).save( filename=run_code_context.output_filename, @@ -136,7 +136,7 @@ class QaEngineer(Role): async def _debug_error(self, msg): run_code_context = RunCodeContext.loads(msg.content) - code = await DebugError(context=run_code_context, g_context=self.context, llm=self.llm).run() + code = await DebugError(i_context=run_code_context, context=self.context, llm=self.llm).run() await self.context.file_repo.save_file( filename=run_code_context.test_filename, content=code, relative_path=TEST_CODES_FILE_REPO ) diff --git a/metagpt/roles/teacher.py b/metagpt/roles/teacher.py index b4ffd01d3..9206d5f80 100644 --- a/metagpt/roles/teacher.py +++ b/metagpt/roles/teacher.py @@ -45,7 +45,7 @@ class Teacher(Role): actions = [] print(TeachingPlanBlock.TOPICS) for topic in TeachingPlanBlock.TOPICS: - act = WriteTeachingPlanPart(context=self.rc.news[0].content, topic=topic, llm=self.llm) + act = WriteTeachingPlanPart(i_context=self.rc.news[0].content, topic=topic, llm=self.llm) actions.append(act) self.add_actions(actions) From bd63df212db9d5307786ae944e6ffacfe0baac31 Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 16:18:55 +0800 Subject: [PATCH 33/61] refine code --- metagpt/actions/write_code.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/metagpt/actions/write_code.py b/metagpt/actions/write_code.py index 779fe52a6..1aa76b67e 100644 --- a/metagpt/actions/write_code.py +++ b/metagpt/actions/write_code.py @@ -95,7 +95,7 @@ class WriteCode(Action): async def run(self, *args, **kwargs) -> CodingContext: bug_feedback = await self.file_repo.get_file(filename=BUGFIX_FILENAME, relative_path=DOCS_FILE_REPO) - coding_context = CodingContext.loads(self.context.content) + coding_context = CodingContext.loads(self.i_context.content) test_doc = await self.file_repo.get_file( filename="test_" + coding_context.filename + ".json", relative_path=TEST_OUTPUTS_FILE_REPO ) From eea66bad19f1def32a674f83ff80f78b528e719f Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 16:24:21 +0800 Subject: [PATCH 34/61] refine code --- metagpt/actions/debug_error.py | 8 ++++---- metagpt/actions/run_code.py | 24 ++++++++++++------------ metagpt/actions/summarize_code.py | 6 +++--- metagpt/actions/write_code.py | 6 +++--- metagpt/actions/write_code_review.py | 28 ++++++++++++++-------------- metagpt/actions/write_test.py | 16 ++++++++-------- 6 files changed, 44 insertions(+), 44 deletions(-) diff --git a/metagpt/actions/debug_error.py b/metagpt/actions/debug_error.py index 3647640c0..bb57e1927 100644 --- a/metagpt/actions/debug_error.py +++ b/metagpt/actions/debug_error.py @@ -51,7 +51,7 @@ class DebugError(Action): async def run(self, *args, **kwargs) -> str: output_doc = await self.file_repo.get_file( - filename=self.context.output_filename, relative_path=TEST_OUTPUTS_FILE_REPO + filename=self.i_context.output_filename, relative_path=TEST_OUTPUTS_FILE_REPO ) if not output_doc: return "" @@ -61,14 +61,14 @@ class DebugError(Action): if matches: return "" - logger.info(f"Debug and rewrite {self.context.test_filename}") + logger.info(f"Debug and rewrite {self.i_context.test_filename}") code_doc = await self.file_repo.get_file( - filename=self.context.code_filename, relative_path=self.context.src_workspace + filename=self.i_context.code_filename, relative_path=self.i_context.src_workspace ) if not code_doc: return "" test_doc = await self.file_repo.get_file( - filename=self.context.test_filename, relative_path=TEST_CODES_FILE_REPO + filename=self.i_context.test_filename, relative_path=TEST_CODES_FILE_REPO ) if not test_doc: return "" diff --git a/metagpt/actions/run_code.py b/metagpt/actions/run_code.py index 8fdda0a0d..072ee8f22 100644 --- a/metagpt/actions/run_code.py +++ b/metagpt/actions/run_code.py @@ -117,25 +117,25 @@ class RunCode(Action): return stdout.decode("utf-8"), stderr.decode("utf-8") async def run(self, *args, **kwargs) -> RunCodeResult: - logger.info(f"Running {' '.join(self.context.command)}") - if self.context.mode == "script": + logger.info(f"Running {' '.join(self.i_context.command)}") + if self.i_context.mode == "script": outs, errs = await self.run_script( - command=self.context.command, - working_directory=self.context.working_directory, - additional_python_paths=self.context.additional_python_paths, + command=self.i_context.command, + working_directory=self.i_context.working_directory, + additional_python_paths=self.i_context.additional_python_paths, ) - elif self.context.mode == "text": - outs, errs = await self.run_text(code=self.context.code) + elif self.i_context.mode == "text": + outs, errs = await self.run_text(code=self.i_context.code) logger.info(f"{outs=}") logger.info(f"{errs=}") context = CONTEXT.format( - code=self.context.code, - code_file_name=self.context.code_filename, - test_code=self.context.test_code, - test_file_name=self.context.test_filename, - command=" ".join(self.context.command), + code=self.i_context.code, + code_file_name=self.i_context.code_filename, + test_code=self.i_context.test_code, + test_file_name=self.i_context.test_filename, + command=" ".join(self.i_context.command), outs=outs[:500], # outs might be long but they are not important, truncate them to avoid token overflow errs=errs[:10000], # truncate errors to avoid token overflow ) diff --git a/metagpt/actions/summarize_code.py b/metagpt/actions/summarize_code.py index 690d5c77b..dde41d3c6 100644 --- a/metagpt/actions/summarize_code.py +++ b/metagpt/actions/summarize_code.py @@ -98,14 +98,14 @@ class SummarizeCode(Action): return code_rsp async def run(self): - design_pathname = Path(self.context.design_filename) + design_pathname = Path(self.i_context.design_filename) repo = self.file_repo design_doc = await repo.get_file(filename=design_pathname.name, relative_path=SYSTEM_DESIGN_FILE_REPO) - task_pathname = Path(self.context.task_filename) + task_pathname = Path(self.i_context.task_filename) task_doc = await repo.get_file(filename=task_pathname.name, relative_path=TASK_FILE_REPO) src_file_repo = self.git_repo.new_file_repository(relative_path=self.context.src_workspace) code_blocks = [] - for filename in self.context.codes_filenames: + for filename in self.i_context.codes_filenames: code_doc = await src_file_repo.get(filename) code_block = f"```python\n{code_doc.content}\n```\n-----" code_blocks.append(code_block) diff --git a/metagpt/actions/write_code.py b/metagpt/actions/write_code.py index 1aa76b67e..62de34ef4 100644 --- a/metagpt/actions/write_code.py +++ b/metagpt/actions/write_code.py @@ -114,7 +114,7 @@ class WriteCode(Action): else: code_context = await self.get_codes( coding_context.task_doc, - exclude=self.context.filename, + exclude=self.i_context.filename, git_repo=self.git_repo, src_workspace=self.context.src_workspace, ) @@ -125,14 +125,14 @@ class WriteCode(Action): code=code_context, logs=logs, feedback=bug_feedback.content if bug_feedback else "", - filename=self.context.filename, + filename=self.i_context.filename, summary_log=summary_doc.content if summary_doc else "", ) logger.info(f"Writing {coding_context.filename}..") code = await self.write_code(prompt) if not coding_context.code_doc: # avoid root_path pydantic ValidationError if use WriteCode alone - root_path = self.context.src_workspace if self.context.src_workspace else "" + root_path = self.i_context.src_workspace if self.i_context.src_workspace else "" coding_context.code_doc = Document(filename=coding_context.filename, root_path=str(root_path)) coding_context.code_doc.content = code return coding_context diff --git a/metagpt/actions/write_code_review.py b/metagpt/actions/write_code_review.py index 6ff9d5aa4..b25f1ab69 100644 --- a/metagpt/actions/write_code_review.py +++ b/metagpt/actions/write_code_review.py @@ -135,20 +135,20 @@ class WriteCodeReview(Action): return result, code async def run(self, *args, **kwargs) -> CodingContext: - iterative_code = self.context.code_doc.content + iterative_code = self.i_context.code_doc.content k = self.context.config.code_review_k_times or 1 for i in range(k): - format_example = FORMAT_EXAMPLE.format(filename=self.context.code_doc.filename) - task_content = self.context.task_doc.content if self.context.task_doc else "" + format_example = FORMAT_EXAMPLE.format(filename=self.i_context.code_doc.filename) + task_content = self.i_context.task_doc.content if self.i_context.task_doc else "" code_context = await WriteCode.get_codes( - self.context.task_doc, - exclude=self.context.filename, + self.i_context.task_doc, + exclude=self.i_context.filename, git_repo=self.context.git_repo, src_workspace=self.src_workspace, ) context = "\n".join( [ - "## System Design\n" + str(self.context.design_doc) + "\n", + "## System Design\n" + str(self.i_context.design_doc) + "\n", "## Tasks\n" + task_content + "\n", "## Code Files\n" + code_context + "\n", ] @@ -156,25 +156,25 @@ class WriteCodeReview(Action): context_prompt = PROMPT_TEMPLATE.format( context=context, code=iterative_code, - filename=self.context.code_doc.filename, + filename=self.i_context.code_doc.filename, ) cr_prompt = EXAMPLE_AND_INSTRUCTION.format( format_example=format_example, ) logger.info( - f"Code review and rewrite {self.context.code_doc.filename}: {i + 1}/{k} | {len(iterative_code)=}, " - f"{len(self.context.code_doc.content)=}" + f"Code review and rewrite {self.i_context.code_doc.filename}: {i + 1}/{k} | {len(iterative_code)=}, " + f"{len(self.i_context.code_doc.content)=}" ) result, rewrited_code = await self.write_code_review_and_rewrite( - context_prompt, cr_prompt, self.context.code_doc.filename + context_prompt, cr_prompt, self.i_context.code_doc.filename ) if "LBTM" in result: iterative_code = rewrited_code elif "LGTM" in result: - self.context.code_doc.content = iterative_code - return self.context + self.i_context.code_doc.content = iterative_code + return self.i_context # code_rsp = await self._aask_v1(prompt, "code_rsp", OUTPUT_MAPPING) # self._save(context, filename, code) # 如果rewrited_code是None（原code perfect），那么直接返回code - self.context.code_doc.content = iterative_code - return self.context + self.i_context.code_doc.content = iterative_code + return self.i_context diff --git a/metagpt/actions/write_test.py b/metagpt/actions/write_test.py index 38b1cf03c..978fa20a6 100644 --- a/metagpt/actions/write_test.py +++ b/metagpt/actions/write_test.py @@ -55,16 +55,16 @@ class WriteTest(Action): return code async def run(self, *args, **kwargs) -> TestingContext: - if not self.context.test_doc: - self.context.test_doc = Document( - filename="test_" + self.context.code_doc.filename, root_path=TEST_CODES_FILE_REPO + if not self.i_context.test_doc: + self.i_context.test_doc = Document( + filename="test_" + self.i_context.code_doc.filename, root_path=TEST_CODES_FILE_REPO ) fake_root = "/data" prompt = PROMPT_TEMPLATE.format( - code_to_test=self.context.code_doc.content, - test_file_name=self.context.test_doc.filename, - source_file_path=fake_root + "/" + self.context.code_doc.root_relative_path, + code_to_test=self.i_context.code_doc.content, + test_file_name=self.i_context.test_doc.filename, + source_file_path=fake_root + "/" + self.i_context.code_doc.root_relative_path, workspace=fake_root, ) - self.context.test_doc.content = await self.write_code(prompt) - return self.context + self.i_context.test_doc.content = await self.write_code(prompt) + return self.i_context From c1d21b96f9cc54c5e9db26301b5f69493d100924 Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 16:28:01 +0800 Subject: [PATCH 35/61] refine code --- metagpt/actions/write_teaching_plan.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/metagpt/actions/write_teaching_plan.py b/metagpt/actions/write_teaching_plan.py index 04507fda3..6ea3c3099 100644 --- a/metagpt/actions/write_teaching_plan.py +++ b/metagpt/actions/write_teaching_plan.py @@ -35,7 +35,7 @@ class WriteTeachingPlanPart(Action): formation=TeachingPlanBlock.FORMATION, role=self.prefix, statements="\n".join(statements), - lesson=self.context, + lesson=self.i_context, topic=self.topic, language=self.language, ) From 9559d83d106a9507083ba0e40243f8e7f6d7445e Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 17:17:27 +0800 Subject: [PATCH 36/61] extra='ignore' --- metagpt/actions/action.py | 2 +- metagpt/context.py | 2 +- metagpt/roles/role.py | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/metagpt/actions/action.py b/metagpt/actions/action.py index cad8112d2..a3f7163c3 100644 --- a/metagpt/actions/action.py +++ b/metagpt/actions/action.py @@ -73,7 +73,7 @@ class Action(SerializationMixin, ContextMixin, BaseModel): def _init_with_instruction(cls, values): if "instruction" in values: name = values["name"] - i = values["instruction"] + i = values.pop("instruction") values["node"] = ActionNode(key=name, expected_type=str, instruction=i, example="", schema="raw") return values diff --git a/metagpt/context.py b/metagpt/context.py index 4badafcc4..406be1f53 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -165,7 +165,7 @@ class ContextMixin(BaseModel): @property def llm(self) -> BaseLLM: """Role llm: role llm > context llm""" - # logger.info(f"class:{self.__class__.__name__}, llm: {self._llm}, llm_config: {self._llm_config}") + print(f"class:{self.__class__.__name__}, llm: {self._llm}, llm_config: {self._llm_config}") if self._llm_config and not self._llm: self._llm = self.context.llm(self._llm_config.name, self._llm_config.provider) return self._llm or self.context.llm() diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py index 9c6832d8f..72ee1175b 100644 --- a/metagpt/roles/role.py +++ b/metagpt/roles/role.py @@ -120,7 +120,7 @@ class RoleContext(BaseModel): class Role(SerializationMixin, ContextMixin, BaseModel): """Role/Agent""" - model_config = ConfigDict(arbitrary_types_allowed=True, exclude=["llm"]) + model_config = ConfigDict(arbitrary_types_allowed=True, extra="ignore") name: str = "" profile: str = "" From 0157a1d8a1fe710a7f25af0ad4fafca4f54c60db Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 17:31:55 +0800 Subject: [PATCH 37/61] extra='ignore' --- metagpt/context.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/metagpt/context.py b/metagpt/context.py index 406be1f53..e2bead828 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -165,7 +165,7 @@ class ContextMixin(BaseModel): @property def llm(self) -> BaseLLM: """Role llm: role llm > context llm""" - print(f"class:{self.__class__.__name__}, llm: {self._llm}, llm_config: {self._llm_config}") + # print(f"class:{self.__class__.__name__}({self.name}), llm: {self._llm}, llm_config: {self._llm_config}") if self._llm_config and not self._llm: self._llm = self.context.llm(self._llm_config.name, self._llm_config.provider) return self._llm or self.context.llm() From 0d742654d40836f5484bcbbeaff2c0a6997bbe94 Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 17:54:13 +0800 Subject: [PATCH 38/61] modify add action to set action --- examples/agent_creator.py | 2 +- examples/build_customized_agent.py | 4 ++-- examples/build_customized_multi_agents.py | 6 +++--- examples/debate.py | 2 +- metagpt/roles/architect.py | 2 +- metagpt/roles/engineer.py | 2 +- metagpt/roles/invoice_ocr_assistant.py | 6 +++--- metagpt/roles/product_manager.py | 2 +- metagpt/roles/project_manager.py | 2 +- metagpt/roles/qa_engineer.py | 2 +- metagpt/roles/researcher.py | 2 +- metagpt/roles/role.py | 7 ++++--- metagpt/roles/sales.py | 2 +- metagpt/roles/searcher.py | 4 ++-- metagpt/roles/sk_agent.py | 2 +- metagpt/roles/teacher.py | 2 +- metagpt/roles/tutorial_assistant.py | 4 ++-- tests/metagpt/serialize_deserialize/test_serdeser_base.py | 6 +++--- tests/metagpt/test_role.py | 8 ++++---- 19 files changed, 34 insertions(+), 33 deletions(-) diff --git a/examples/agent_creator.py b/examples/agent_creator.py index fe883bdf4..bd58840ce 100644 --- a/examples/agent_creator.py +++ b/examples/agent_creator.py @@ -61,7 +61,7 @@ class AgentCreator(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self.add_actions([CreateAgent]) + self.set_actions([CreateAgent]) async def _act(self) -> Message: logger.info(f"{self._setting}: to do {self.rc.todo}({self.rc.todo.name})") diff --git a/examples/build_customized_agent.py b/examples/build_customized_agent.py index a0c8ddfb3..cfe264b47 100644 --- a/examples/build_customized_agent.py +++ b/examples/build_customized_agent.py @@ -57,7 +57,7 @@ class SimpleCoder(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self.add_actions([SimpleWriteCode]) + self.set_actions([SimpleWriteCode]) async def _act(self) -> Message: logger.info(f"{self._setting}: to do {self.rc.todo}({self.rc.todo.name})") @@ -76,7 +76,7 @@ class RunnableCoder(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self.add_actions([SimpleWriteCode, SimpleRunCode]) + self.set_actions([SimpleWriteCode, SimpleRunCode]) self._set_react_mode(react_mode=RoleReactMode.BY_ORDER.value) async def _act(self) -> Message: diff --git a/examples/build_customized_multi_agents.py b/examples/build_customized_multi_agents.py index aceb3f2ab..296323cea 100644 --- a/examples/build_customized_multi_agents.py +++ b/examples/build_customized_multi_agents.py @@ -46,7 +46,7 @@ class SimpleCoder(Role): def __init__(self, **kwargs): super().__init__(**kwargs) self._watch([UserRequirement]) - self.add_actions([SimpleWriteCode]) + self.set_actions([SimpleWriteCode]) class SimpleWriteTest(Action): @@ -75,7 +75,7 @@ class SimpleTester(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self.add_actions([SimpleWriteTest]) + self.set_actions([SimpleWriteTest]) # self._watch([SimpleWriteCode]) self._watch([SimpleWriteCode, SimpleWriteReview]) # feel free to try this too @@ -114,7 +114,7 @@ class SimpleReviewer(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self.add_actions([SimpleWriteReview]) + self.set_actions([SimpleWriteReview]) self._watch([SimpleWriteTest]) diff --git a/examples/debate.py b/examples/debate.py index b47eba3cd..72ab8796d 100644 --- a/examples/debate.py +++ b/examples/debate.py @@ -49,7 +49,7 @@ class Debator(Role): def __init__(self, **data: Any): super().__init__(**data) - self.add_actions([SpeakAloud]) + self.set_actions([SpeakAloud]) self._watch([UserRequirement, SpeakAloud]) async def _observe(self) -> int: diff --git a/metagpt/roles/architect.py b/metagpt/roles/architect.py index a22a1c926..166f8cfd0 100644 --- a/metagpt/roles/architect.py +++ b/metagpt/roles/architect.py @@ -33,7 +33,7 @@ class Architect(Role): def __init__(self, **kwargs) -> None: super().__init__(**kwargs) # Initialize actions specific to the Architect role - self.add_actions([WriteDesign]) + self.set_actions([WriteDesign]) # Set events or actions the Architect should watch or be aware of self._watch({WritePRD}) diff --git a/metagpt/roles/engineer.py b/metagpt/roles/engineer.py index 0d277813e..bc56ca813 100644 --- a/metagpt/roles/engineer.py +++ b/metagpt/roles/engineer.py @@ -84,7 +84,7 @@ class Engineer(Role): def __init__(self, **kwargs) -> None: super().__init__(**kwargs) - self.add_actions([WriteCode]) + self.set_actions([WriteCode]) self._watch([WriteTasks, SummarizeCode, WriteCode, WriteCodeReview, FixBug]) self.code_todos = [] self.summarize_todos = [] diff --git a/metagpt/roles/invoice_ocr_assistant.py b/metagpt/roles/invoice_ocr_assistant.py index de7d3f8a3..a39a48b97 100644 --- a/metagpt/roles/invoice_ocr_assistant.py +++ b/metagpt/roles/invoice_ocr_assistant.py @@ -60,7 +60,7 @@ class InvoiceOCRAssistant(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self.add_actions([InvoiceOCR]) + self.set_actions([InvoiceOCR]) self._set_react_mode(react_mode=RoleReactMode.BY_ORDER.value) async def _act(self) -> Message: @@ -82,10 +82,10 @@ class InvoiceOCRAssistant(Role): resp = await todo.run(file_path) if len(resp) == 1: # Single file support for questioning based on OCR recognition results - self.add_actions([GenerateTable, ReplyQuestion]) + self.set_actions([GenerateTable, ReplyQuestion]) self.orc_data = resp[0] else: - self.add_actions([GenerateTable]) + self.set_actions([GenerateTable]) self.set_todo(None) content = INVOICE_OCR_SUCCESS diff --git a/metagpt/roles/product_manager.py b/metagpt/roles/product_manager.py index a35dcb3a0..ec80d7bb0 100644 --- a/metagpt/roles/product_manager.py +++ b/metagpt/roles/product_manager.py @@ -33,7 +33,7 @@ class ProductManager(Role): def __init__(self, **kwargs) -> None: super().__init__(**kwargs) - self.add_actions([PrepareDocuments, WritePRD]) + self.set_actions([PrepareDocuments, WritePRD]) self._watch([UserRequirement, PrepareDocuments]) self.todo_action = any_to_name(PrepareDocuments) diff --git a/metagpt/roles/project_manager.py b/metagpt/roles/project_manager.py index 7fa16b1e5..422d2889b 100644 --- a/metagpt/roles/project_manager.py +++ b/metagpt/roles/project_manager.py @@ -33,5 +33,5 @@ class ProjectManager(Role): def __init__(self, **kwargs) -> None: super().__init__(**kwargs) - self.add_actions([WriteTasks]) + self.set_actions([WriteTasks]) self._watch([WriteDesign]) diff --git a/metagpt/roles/qa_engineer.py b/metagpt/roles/qa_engineer.py index 9483ea260..783fde9b6 100644 --- a/metagpt/roles/qa_engineer.py +++ b/metagpt/roles/qa_engineer.py @@ -44,7 +44,7 @@ class QaEngineer(Role): # FIXME: a bit hack here, only init one action to circumvent _think() logic, # will overwrite _think() in future updates - self.add_actions([WriteTest]) + self.set_actions([WriteTest]) self._watch([SummarizeCode, WriteTest, RunCode, DebugError]) self.test_round = 0 diff --git a/metagpt/roles/researcher.py b/metagpt/roles/researcher.py index e877778f6..137cfdb4c 100644 --- a/metagpt/roles/researcher.py +++ b/metagpt/roles/researcher.py @@ -34,7 +34,7 @@ class Researcher(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self.add_actions( + self.set_actions( [CollectLinks(name=self.name), WebBrowseAndSummarize(name=self.name), ConductResearch(name=self.name)] ) self._set_react_mode(react_mode=RoleReactMode.BY_ORDER.value) diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py index 72ee1175b..e467ef83e 100644 --- a/metagpt/roles/role.py +++ b/metagpt/roles/role.py @@ -222,16 +222,17 @@ class Role(SerializationMixin, ContextMixin, BaseModel): def _init_action_system_message(self, action: Action): action.set_prefix(self._get_prefix()) - def add_action(self, action: Action): + def set_action(self, action: Action): """Add action to the role.""" - self.add_actions([action]) + self.set_actions([action]) - def add_actions(self, actions: list[Union[Action, Type[Action]]]): + def set_actions(self, actions: list[Union[Action, Type[Action]]]): """Add actions to the role. Args: actions: list of Action classes or instances """ + self._reset() for action in actions: if not isinstance(action, Action): i = action(name="", llm=self.llm) diff --git a/metagpt/roles/sales.py b/metagpt/roles/sales.py index 8da930888..7929ce7fe 100644 --- a/metagpt/roles/sales.py +++ b/metagpt/roles/sales.py @@ -38,5 +38,5 @@ class Sales(Role): action = SearchAndSummarize(name="", engine=SearchEngineType.CUSTOM_ENGINE, search_func=store.asearch) else: action = SearchAndSummarize() - self.add_actions([action]) + self.set_actions([action]) self._watch([UserRequirement]) diff --git a/metagpt/roles/searcher.py b/metagpt/roles/searcher.py index f37bd4704..e0d2dbb65 100644 --- a/metagpt/roles/searcher.py +++ b/metagpt/roles/searcher.py @@ -48,12 +48,12 @@ class Searcher(Role): engine (SearchEngineType): The type of search engine to use. """ super().__init__(**kwargs) - self.add_actions([SearchAndSummarize(engine=self.engine)]) + self.set_actions([SearchAndSummarize(engine=self.engine)]) def set_search_func(self, search_func): """Sets a custom search function for the searcher.""" action = SearchAndSummarize(name="", engine=SearchEngineType.CUSTOM_ENGINE, search_func=search_func) - self.add_actions([action]) + self.set_actions([action]) async def _act_sp(self) -> Message: """Performs the search action in a single process.""" diff --git a/metagpt/roles/sk_agent.py b/metagpt/roles/sk_agent.py index 200ed5051..71df55fcc 100644 --- a/metagpt/roles/sk_agent.py +++ b/metagpt/roles/sk_agent.py @@ -49,7 +49,7 @@ class SkAgent(Role): def __init__(self, **data: Any) -> None: """Initializes the Engineer role with given attributes.""" super().__init__(**data) - self.add_actions([ExecuteTask()]) + self.set_actions([ExecuteTask()]) self._watch([UserRequirement]) self.kernel = make_sk_kernel() diff --git a/metagpt/roles/teacher.py b/metagpt/roles/teacher.py index 9206d5f80..d47f4af5b 100644 --- a/metagpt/roles/teacher.py +++ b/metagpt/roles/teacher.py @@ -47,7 +47,7 @@ class Teacher(Role): for topic in TeachingPlanBlock.TOPICS: act = WriteTeachingPlanPart(i_context=self.rc.news[0].content, topic=topic, llm=self.llm) actions.append(act) - self.add_actions(actions) + self.set_actions(actions) if self.rc.todo is None: self._set_state(0) diff --git a/metagpt/roles/tutorial_assistant.py b/metagpt/roles/tutorial_assistant.py index d296c7b3f..6cf3a6469 100644 --- a/metagpt/roles/tutorial_assistant.py +++ b/metagpt/roles/tutorial_assistant.py @@ -40,7 +40,7 @@ class TutorialAssistant(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self.add_actions([WriteDirectory(language=self.language)]) + self.set_actions([WriteDirectory(language=self.language)]) self._set_react_mode(react_mode=RoleReactMode.BY_ORDER.value) async def _handle_directory(self, titles: Dict) -> Message: @@ -63,7 +63,7 @@ class TutorialAssistant(Role): directory += f"- {key}\n" for second_dir in first_dir[key]: directory += f" - {second_dir}\n" - self.add_actions(actions) + self.set_actions(actions) async def _act(self) -> Message: """Perform an action as determined by the role. diff --git a/tests/metagpt/serialize_deserialize/test_serdeser_base.py b/tests/metagpt/serialize_deserialize/test_serdeser_base.py index c97cea597..62ab26d72 100644 --- a/tests/metagpt/serialize_deserialize/test_serdeser_base.py +++ b/tests/metagpt/serialize_deserialize/test_serdeser_base.py @@ -67,7 +67,7 @@ class RoleA(Role): def __init__(self, **kwargs): super(RoleA, self).__init__(**kwargs) - self.add_actions([ActionPass]) + self.set_actions([ActionPass]) self._watch([UserRequirement]) @@ -79,7 +79,7 @@ class RoleB(Role): def __init__(self, **kwargs): super(RoleB, self).__init__(**kwargs) - self.add_actions([ActionOK, ActionRaise]) + self.set_actions([ActionOK, ActionRaise]) self._watch([ActionPass]) self.rc.react_mode = RoleReactMode.BY_ORDER @@ -92,7 +92,7 @@ class RoleC(Role): def __init__(self, **kwargs): super(RoleC, self).__init__(**kwargs) - self.add_actions([ActionOK, ActionRaise]) + self.set_actions([ActionOK, ActionRaise]) self._watch([UserRequirement]) self.rc.react_mode = RoleReactMode.BY_ORDER self.rc.memory.ignore_id = True diff --git a/tests/metagpt/test_role.py b/tests/metagpt/test_role.py index c67a8ad8a..351ba9051 100644 --- a/tests/metagpt/test_role.py +++ b/tests/metagpt/test_role.py @@ -33,7 +33,7 @@ class MockAction(Action): class MockRole(Role): def __init__(self, name="", profile="", goal="", constraints="", desc=""): super().__init__(name=name, profile=profile, goal=goal, constraints=constraints, desc=desc) - self.add_actions([MockAction()]) + self.set_actions([MockAction()]) def test_basic(): @@ -111,7 +111,7 @@ async def test_send_to(): def test_init_action(): role = Role() - role.add_actions([MockAction, MockAction]) + role.set_actions([MockAction, MockAction]) assert len(role.actions) == 2 @@ -127,7 +127,7 @@ async def test_recover(): role.publish_message(None) role.llm = mock_llm - role.add_actions([MockAction, MockAction]) + role.set_actions([MockAction, MockAction]) role.recovered = True role.latest_observed_msg = Message(content="recover_test") role.rc.state = 0 @@ -144,7 +144,7 @@ async def test_think_act(): mock_llm.aask.side_effect = ["ok"] role = Role() - role.add_actions([MockAction]) + role.set_actions([MockAction]) await role.think() role.rc.memory.add(Message("run")) assert len(role.get_memories()) == 1 From ae0a91c0250a7ed9334d807a4b4d7e6f3a165c69 Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 18:32:03 +0800 Subject: [PATCH 39/61] fix bug --- metagpt/actions/write_code.py | 2 +- metagpt/config2.py | 4 +--- metagpt/context.py | 16 ++++++++++++---- tests/metagpt/actions/test_write_code.py | 6 +++--- 4 files changed, 17 insertions(+), 11 deletions(-) diff --git a/metagpt/actions/write_code.py b/metagpt/actions/write_code.py index 62de34ef4..1b3dcf5f0 100644 --- a/metagpt/actions/write_code.py +++ b/metagpt/actions/write_code.py @@ -132,7 +132,7 @@ class WriteCode(Action): code = await self.write_code(prompt) if not coding_context.code_doc: # avoid root_path pydantic ValidationError if use WriteCode alone - root_path = self.i_context.src_workspace if self.i_context.src_workspace else "" + root_path = self.context.src_workspace if self.context.src_workspace else "" coding_context.code_doc = Document(filename=coding_context.filename, root_path=str(root_path)) coding_context.code_doc.content = code return coding_context diff --git a/metagpt/config2.py b/metagpt/config2.py index cb5c22ac2..30d3818f6 100644 --- a/metagpt/config2.py +++ b/metagpt/config2.py @@ -121,12 +121,10 @@ class Config(CLIParams, YamlModel): return llm[0] return None - def get_llm_config(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> LLMConfig: + def get_llm_config(self, name: Optional[str] = None, provider: LLMType = None) -> LLMConfig: """Return a LLMConfig instance""" if provider: llm_configs = self.get_llm_configs_by_type(provider) - if name: - llm_configs = [c for c in llm_configs if c.name == name] if len(llm_configs) == 0: raise ValueError(f"Cannot find llm config with name {name} and provider {provider}") diff --git a/metagpt/context.py b/metagpt/context.py index e2bead828..35892f3f3 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -77,7 +77,7 @@ class Context(BaseModel): # self._llm = None # return self._llm - def llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: + def llm(self, name: Optional[str] = None, provider: LLMType = None) -> BaseLLM: """Return a LLM instance, fixme: support cache""" # if self._llm is None: self._llm = create_llm_instance(self.config.get_llm_config(name, provider)) @@ -85,6 +85,14 @@ class Context(BaseModel): self._llm.cost_manager = self.cost_manager return self._llm + def llm_with_cost_manager_from_llm_config(self, llm_config: LLMConfig) -> BaseLLM: + """Return a LLM instance, fixme: support cache""" + # if self._llm is None: + llm = create_llm_instance(llm_config) + if llm.cost_manager is None: + llm.cost_manager = self.cost_manager + return llm + class ContextMixin(BaseModel): """Mixin class for context and config""" @@ -132,7 +140,7 @@ class ContextMixin(BaseModel): """Set llm""" self.set("_llm", llm, override) - def use_llm(self, name: Optional[str] = None, provider: LLMType = LLMType.OPENAI) -> BaseLLM: + def use_llm(self, name: Optional[str] = None, provider: LLMType = None) -> BaseLLM: """Use a LLM instance""" self._llm_config = self.config.get_llm_config(name, provider) self._llm = None @@ -165,9 +173,9 @@ class ContextMixin(BaseModel): @property def llm(self) -> BaseLLM: """Role llm: role llm > context llm""" - # print(f"class:{self.__class__.__name__}({self.name}), llm: {self._llm}, llm_config: {self._llm_config}") + print(f"class:{self.__class__.__name__}({self.name}), llm: {self._llm}, llm_config: {self._llm_config}") if self._llm_config and not self._llm: - self._llm = self.context.llm(self._llm_config.name, self._llm_config.provider) + self._llm = self.context.llm_with_cost_manager_from_llm_config(self._llm_config) return self._llm or self.context.llm() @llm.setter diff --git a/tests/metagpt/actions/test_write_code.py b/tests/metagpt/actions/test_write_code.py index cfc5863f4..792b89d90 100644 --- a/tests/metagpt/actions/test_write_code.py +++ b/tests/metagpt/actions/test_write_code.py @@ -19,8 +19,8 @@ from metagpt.const import ( TEST_OUTPUTS_FILE_REPO, ) from metagpt.context import CONTEXT +from metagpt.llm import LLM from metagpt.logs import logger -from metagpt.provider.openai_api import OpenAILLM as LLM from metagpt.schema import CodingContext, Document from metagpt.utils.common import aread from tests.metagpt.actions.mock_markdown import TASKS_2, WRITE_CODE_PROMPT_SAMPLE @@ -32,7 +32,7 @@ async def test_write_code(): filename="task_filename.py", design_doc=Document(content="设计一个名为'add'的函数，该函数接受两个整数作为输入，并返回它们的和。") ) doc = Document(content=ccontext.model_dump_json()) - write_code = WriteCode(context=doc) + write_code = WriteCode(i_context=doc) code = await write_code.run() logger.info(code.model_dump_json()) @@ -86,7 +86,7 @@ async def test_write_code_deps(): ) coding_doc = Document(root_path="snake1", filename="game.py", content=ccontext.json()) - action = WriteCode(context=coding_doc) + action = WriteCode(i_context=coding_doc) rsp = await action.run() assert rsp assert rsp.code_doc.content From d334377275e1200c5c4fd448a0e4f0b240c64c7f Mon Sep 17 00:00:00 2001 From: better629 Date: Wed, 10 Jan 2024 19:13:19 +0800 Subject: [PATCH 40/61] add action_outcls decorator to support init same class with same class name and fields --- metagpt/actions/action_node.py | 2 + metagpt/actions/action_outcls_registry.py | 42 +++++++++++++++++ .../actions/test_action_outcls_registry.py | 46 +++++++++++++++++++ .../serialize_deserialize/test_architect.py | 1 + .../serialize_deserialize/test_schema.py | 9 +++- 5 files changed, 98 insertions(+), 2 deletions(-) create mode 100644 metagpt/actions/action_outcls_registry.py create mode 100644 tests/metagpt/actions/test_action_outcls_registry.py diff --git a/metagpt/actions/action_node.py b/metagpt/actions/action_node.py index 286cf534d..b4d8c32df 100644 --- a/metagpt/actions/action_node.py +++ b/metagpt/actions/action_node.py @@ -15,6 +15,7 @@ from typing import Any, Dict, List, Optional, Tuple, Type, Union from pydantic import BaseModel, create_model, model_validator from tenacity import retry, stop_after_attempt, wait_random_exponential +from metagpt.actions.action_outcls_registry import register_action_outcls from metagpt.llm import BaseLLM from metagpt.logs import logger from metagpt.provider.postprocess.llm_output_postprocess import llm_output_postprocess @@ -201,6 +202,7 @@ class ActionNode: return {} if exclude and self.key in exclude else self.get_self_mapping() @classmethod + @register_action_outcls def create_model_class(cls, class_name: str, mapping: Dict[str, Tuple[Type, Any]]): """基于pydantic v1的模型动态生成，用来检验结果类型正确性""" diff --git a/metagpt/actions/action_outcls_registry.py b/metagpt/actions/action_outcls_registry.py new file mode 100644 index 000000000..780a061b4 --- /dev/null +++ b/metagpt/actions/action_outcls_registry.py @@ -0,0 +1,42 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +# @Desc : registry to store Dynamic Model from ActionNode.create_model_class to keep it as same Class +# with same class name and mapping + +from functools import wraps + + +action_outcls_registry = dict() + + +def register_action_outcls(func): + """ + Due to `create_model` return different Class even they have same class name and mapping. + In order to do a comparison, use outcls_id to identify same Class with same class name and field definition + """ + @wraps(func) + def decorater(*args, **kwargs): + """ + arr example + [, 'test', {'field': (str, Ellipsis)}] + """ + arr = list(args) + list(kwargs.values()) + """ + outcls_id example + "_test_{'field': (str, Ellipsis)}" + """ + for idx, item in enumerate(arr): + if isinstance(item, dict): + arr[idx] = dict(sorted(item.items())) + outcls_id = "_".join([str(i) for i in arr]) + # eliminate typing influence + outcls_id = outcls_id.replace("typing.List", "list").replace("typing.Dict", "dict") + + if outcls_id in action_outcls_registry: + return action_outcls_registry[outcls_id] + + out_cls = func(*args, **kwargs) + action_outcls_registry[outcls_id] = out_cls + return out_cls + + return decorater diff --git a/tests/metagpt/actions/test_action_outcls_registry.py b/tests/metagpt/actions/test_action_outcls_registry.py new file mode 100644 index 000000000..e949ac16b --- /dev/null +++ b/tests/metagpt/actions/test_action_outcls_registry.py @@ -0,0 +1,46 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +# @Desc : unittest of action_outcls_registry + +from typing import List +from metagpt.actions.action_node import ActionNode + + +def test_action_outcls_registry(): + class_name = "test" + out_mapping = {"field": (list[str], ...), "field1": (str, ...)} + out_data = {"field": ["field value1", "field value2"], "field1": "field1 value1"} + + outcls = ActionNode.create_model_class(class_name, mapping=out_mapping) + outinst = outcls(**out_data) + + outcls1 = ActionNode.create_model_class(class_name=class_name, mapping=out_mapping) + outinst1 = outcls1(**out_data) + assert outinst1 == outinst + + outcls2 = ActionNode(key="", + expected_type=str, + instruction="", + example="").create_model_class(class_name, out_mapping) + outinst2 = outcls2(**out_data) + assert outinst2 == outinst + + out_mapping = {"field1": (str, ...), "field": (list[str], ...)} # different order + outcls3 = ActionNode.create_model_class(class_name=class_name, mapping=out_mapping) + outinst3 = outcls3(**out_data) + assert outinst3 == outinst + + out_mapping2 = {"field1": (str, ...), "field": (List[str], ...)} # typing case + outcls4 = ActionNode.create_model_class(class_name=class_name, mapping=out_mapping2) + outinst4 = outcls4(**out_data) + assert outinst4 == outinst + + out_data2 = {"field2": ["field2 value1", "field2 value2"], "field1": "field1 value1"} + out_mapping = {"field1": (str, ...), "field2": (List[str], ...)} # List first + outcls5 = ActionNode.create_model_class(class_name, out_mapping) + outinst5 = outcls5(**out_data2) + + out_mapping = {"field1": (str, ...), "field2": (list[str], ...)} + outcls6 = ActionNode.create_model_class(class_name, out_mapping) + outinst6 = outcls6(**out_data2) + assert outinst5 == outinst6 diff --git a/tests/metagpt/serialize_deserialize/test_architect.py b/tests/metagpt/serialize_deserialize/test_architect.py index 343662494..a6823197a 100644 --- a/tests/metagpt/serialize_deserialize/test_architect.py +++ b/tests/metagpt/serialize_deserialize/test_architect.py @@ -19,5 +19,6 @@ async def test_architect_serdeser(): new_role = Architect(**ser_role_dict) assert new_role.name == "Bob" assert len(new_role.actions) == 1 + assert len(new_role.rc.watch) == 1 assert isinstance(new_role.actions[0], Action) await new_role.actions[0].run(with_messages="write a cli snake game") diff --git a/tests/metagpt/serialize_deserialize/test_schema.py b/tests/metagpt/serialize_deserialize/test_schema.py index b55b82088..c5a457a1e 100644 --- a/tests/metagpt/serialize_deserialize/test_schema.py +++ b/tests/metagpt/serialize_deserialize/test_schema.py @@ -31,15 +31,17 @@ def test_message_serdeser_from_create_model(): assert new_message.cause_by == any_to_str(WriteCode) assert new_message.cause_by in [any_to_str(WriteCode)] - assert new_message.instruct_content != ic_obj(**out_data) # TODO find why `!=` - assert new_message.instruct_content != ic_inst + assert new_message.instruct_content == ic_obj(**out_data) + assert new_message.instruct_content == ic_inst assert new_message.instruct_content.model_dump() == ic_obj(**out_data).model_dump() + assert new_message == message mock_msg = MockMessage() message = Message(content="test_ic", instruct_content=mock_msg) ser_data = message.model_dump() new_message = Message(**ser_data) assert new_message.instruct_content == mock_msg + assert new_message == message def test_message_without_postprocess(): @@ -54,6 +56,7 @@ def test_message_without_postprocess(): ser_data["instruct_content"] = None new_message = MockICMessage(**ser_data) assert new_message.instruct_content != ic_obj(**out_data) + assert new_message != message def test_message_serdeser_from_basecontext(): @@ -83,6 +86,7 @@ def test_message_serdeser_from_basecontext(): new_code_ctxt_msg = Message(**ser_data) assert new_code_ctxt_msg.instruct_content == code_ctxt assert new_code_ctxt_msg.instruct_content.code_doc.filename == "game.py" + assert new_code_ctxt_msg == code_ctxt_msg testing_ctxt = TestingContext( filename="test.py", @@ -94,3 +98,4 @@ def test_message_serdeser_from_basecontext(): new_testing_ctxt_msg = Message(**ser_data) assert new_testing_ctxt_msg.instruct_content == testing_ctxt assert new_testing_ctxt_msg.instruct_content.test_doc.filename == "test.py" + assert new_testing_ctxt_msg == testing_ctxt_msg From d63860f972fd70ae55020ec265e04a846d1257cc Mon Sep 17 00:00:00 2001 From: better629 Date: Wed, 10 Jan 2024 19:27:33 +0800 Subject: [PATCH 41/61] fix format --- metagpt/actions/action_outcls_registry.py | 2 +- tests/metagpt/actions/test_action_outcls_registry.py | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/metagpt/actions/action_outcls_registry.py b/metagpt/actions/action_outcls_registry.py index 780a061b4..6baa4cea9 100644 --- a/metagpt/actions/action_outcls_registry.py +++ b/metagpt/actions/action_outcls_registry.py @@ -5,7 +5,6 @@ from functools import wraps - action_outcls_registry = dict() @@ -14,6 +13,7 @@ def register_action_outcls(func): Due to `create_model` return different Class even they have same class name and mapping. In order to do a comparison, use outcls_id to identify same Class with same class name and field definition """ + @wraps(func) def decorater(*args, **kwargs): """ diff --git a/tests/metagpt/actions/test_action_outcls_registry.py b/tests/metagpt/actions/test_action_outcls_registry.py index e949ac16b..eac0ba4d9 100644 --- a/tests/metagpt/actions/test_action_outcls_registry.py +++ b/tests/metagpt/actions/test_action_outcls_registry.py @@ -3,6 +3,7 @@ # @Desc : unittest of action_outcls_registry from typing import List + from metagpt.actions.action_node import ActionNode @@ -18,10 +19,9 @@ def test_action_outcls_registry(): outinst1 = outcls1(**out_data) assert outinst1 == outinst - outcls2 = ActionNode(key="", - expected_type=str, - instruction="", - example="").create_model_class(class_name, out_mapping) + outcls2 = ActionNode(key="", expected_type=str, instruction="", example="").create_model_class( + class_name, out_mapping + ) outinst2 = outcls2(**out_data) assert outinst2 == outinst From 2d048e91b104aee900a56ba97564c681320ac9db Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 20:19:56 +0800 Subject: [PATCH 42/61] use config --- metagpt/actions/rebuild_class_view.py | 11 +- metagpt/actions/rebuild_sequence_view.py | 5 +- metagpt/actions/research.py | 9 +- metagpt/actions/write_teaching_plan.py | 4 +- metagpt/config2.py | 3 + metagpt/learn/skill_loader.py | 4 +- metagpt/learn/text_to_embedding.py | 5 +- metagpt/learn/text_to_speech.py | 3 +- metagpt/tools/openai_text_to_embedding.py | 9 +- metagpt/tools/sd_engine.py | 133 ------------------ metagpt/tools/search_engine_ddg.py | 8 +- metagpt/tools/search_engine_googleapi.py | 10 +- metagpt/tools/search_engine_serpapi.py | 4 +- metagpt/tools/search_engine_serper.py | 4 +- metagpt/tools/web_browser_engine.py | 2 - .../tools/web_browser_engine_playwright.py | 12 +- metagpt/tools/web_browser_engine_selenium.py | 12 +- metagpt/utils/mermaid.py | 14 +- metagpt/utils/mmdc_pyppeteer.py | 6 +- metagpt/utils/repair_llm_raw_output.py | 8 +- .../actions/test_rebuild_class_view.py | 3 +- .../actions/test_rebuild_sequence_view.py | 9 +- tests/metagpt/actions/test_summarize_code.py | 11 +- tests/metagpt/learn/test_skill_loader.py | 4 +- tests/metagpt/learn/test_text_to_embedding.py | 4 +- tests/metagpt/tools/test_azure_tts.py | 3 +- .../tools/test_metagpt_oas3_api_svc.py | 4 +- .../tools/test_metagpt_text_to_image.py | 4 +- tests/metagpt/tools/test_moderation.py | 6 +- .../tools/test_openai_text_to_embedding.py | 6 +- .../tools/test_openai_text_to_image.py | 6 +- tests/metagpt/tools/test_openapi_v3_hello.py | 4 +- tests/metagpt/tools/test_sd_tool.py | 26 ---- tests/metagpt/tools/test_search_engine.py | 9 +- tests/metagpt/tools/test_ut_writer.py | 6 +- tests/metagpt/utils/test_mermaid.py | 3 +- .../utils/test_repair_llm_raw_output.py | 4 +- 37 files changed, 102 insertions(+), 276 deletions(-) delete mode 100644 metagpt/tools/sd_engine.py delete mode 100644 tests/metagpt/tools/test_sd_tool.py diff --git a/metagpt/actions/rebuild_class_view.py b/metagpt/actions/rebuild_class_view.py index 876beccec..d25d9e49b 100644 --- a/metagpt/actions/rebuild_class_view.py +++ b/metagpt/actions/rebuild_class_view.py @@ -12,7 +12,7 @@ from pathlib import Path import aiofiles from metagpt.actions import Action -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.const import ( AGGREGATION, COMPOSITION, @@ -20,6 +20,7 @@ from metagpt.const import ( GENERALIZATION, GRAPH_REPO_FILE_REPO, ) +from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.repo_parser import RepoParser from metagpt.schema import ClassAttribute, ClassMethod, ClassView @@ -29,8 +30,8 @@ from metagpt.utils.graph_repository import GraphKeyword, GraphRepository class RebuildClassView(Action): - async def run(self, with_messages=None, format=CONFIG.prompt_schema): - graph_repo_pathname = CONFIG.git_repo.workdir / GRAPH_REPO_FILE_REPO / CONFIG.git_repo.workdir.name + async def run(self, with_messages=None, format=config.prompt_schema): + graph_repo_pathname = CONTEXT.git_repo.workdir / GRAPH_REPO_FILE_REPO / CONTEXT.git_repo.workdir.name graph_db = await DiGraphRepository.load_from(str(graph_repo_pathname.with_suffix(".json"))) repo_parser = RepoParser(base_directory=Path(self.i_context)) # use pylint @@ -48,9 +49,9 @@ class RebuildClassView(Action): await graph_db.save() async def _create_mermaid_class_views(self, graph_db): - path = Path(CONFIG.git_repo.workdir) / DATA_API_DESIGN_FILE_REPO + path = Path(CONTEXT.git_repo.workdir) / DATA_API_DESIGN_FILE_REPO path.mkdir(parents=True, exist_ok=True) - pathname = path / CONFIG.git_repo.workdir.name + pathname = path / CONTEXT.git_repo.workdir.name async with aiofiles.open(str(pathname.with_suffix(".mmd")), mode="w", encoding="utf-8") as writer: content = "classDiagram\n" logger.debug(content) diff --git a/metagpt/actions/rebuild_sequence_view.py b/metagpt/actions/rebuild_sequence_view.py index bc128d8b0..8785e6245 100644 --- a/metagpt/actions/rebuild_sequence_view.py +++ b/metagpt/actions/rebuild_sequence_view.py @@ -12,7 +12,6 @@ from pathlib import Path from typing import List from metagpt.actions import Action -from metagpt.config import CONFIG from metagpt.const import GRAPH_REPO_FILE_REPO from metagpt.logs import logger from metagpt.utils.common import aread, list_files @@ -21,8 +20,8 @@ from metagpt.utils.graph_repository import GraphKeyword class RebuildSequenceView(Action): - async def run(self, with_messages=None, format=CONFIG.prompt_schema): - graph_repo_pathname = CONFIG.git_repo.workdir / GRAPH_REPO_FILE_REPO / CONFIG.git_repo.workdir.name + async def run(self, with_messages=None, format=config.prompt_schema): + graph_repo_pathname = CONTEXT.git_repo.workdir / GRAPH_REPO_FILE_REPO / CONTEXT.git_repo.workdir.name graph_db = await DiGraphRepository.load_from(str(graph_repo_pathname.with_suffix(".json"))) entries = await RebuildSequenceView._search_main_entry(graph_db) for entry in entries: diff --git a/metagpt/actions/research.py b/metagpt/actions/research.py index d2db228ae..a635714ef 100644 --- a/metagpt/actions/research.py +++ b/metagpt/actions/research.py @@ -9,6 +9,7 @@ from pydantic import Field, parse_obj_as from metagpt.actions import Action from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.logs import logger from metagpt.tools.search_engine import SearchEngine from metagpt.tools.web_browser_engine import WebBrowserEngine, WebBrowserEngineType @@ -127,8 +128,8 @@ class CollectLinks(Action): if len(remove) == 0: break - model_name = CONFIG.get_model_name(CONFIG.get_default_llm_provider_enum()) - prompt = reduce_message_length(gen_msg(), model_name, system_text, CONFIG.max_tokens_rsp) + model_name = config.get_openai_llm().model + prompt = reduce_message_length(gen_msg(), model_name, system_text, 4096) logger.debug(prompt) queries = await self._aask(prompt, [system_text]) try: @@ -182,8 +183,6 @@ class WebBrowseAndSummarize(Action): def __init__(self, **kwargs): super().__init__(**kwargs) - if CONFIG.model_for_researcher_summary: - self.llm.model = CONFIG.model_for_researcher_summary self.web_browser_engine = WebBrowserEngine( engine=WebBrowserEngineType.CUSTOM if self.browse_func else None, @@ -246,8 +245,6 @@ class ConductResearch(Action): def __init__(self, **kwargs): super().__init__(**kwargs) - if CONFIG.model_for_researcher_report: - self.llm.model = CONFIG.model_for_researcher_report async def run( self, diff --git a/metagpt/actions/write_teaching_plan.py b/metagpt/actions/write_teaching_plan.py index 6ea3c3099..1678bc8dc 100644 --- a/metagpt/actions/write_teaching_plan.py +++ b/metagpt/actions/write_teaching_plan.py @@ -8,7 +8,7 @@ from typing import Optional from metagpt.actions import Action -from metagpt.config import CONFIG +from metagpt.context import CONTEXT from metagpt.logs import logger @@ -76,7 +76,7 @@ class WriteTeachingPlanPart(Action): return value # FIXME: 从Context中获取参数，而非从options - merged_opts = CONFIG.options or {} + merged_opts = CONTEXT.options or {} try: return value.format(**merged_opts) except KeyError as e: diff --git a/metagpt/config2.py b/metagpt/config2.py index 30d3818f6..2a9611627 100644 --- a/metagpt/config2.py +++ b/metagpt/config2.py @@ -71,6 +71,9 @@ class Config(CLIParams, YamlModel): METAGPT_TEXT_TO_IMAGE_MODEL_URL: str = "" language: str = "English" redis_key: str = "placeholder" + mmdc: str = "mmdc" + puppeteer_config: str = "" + pyppeteer_executable_path: str = "" @classmethod def default(cls): diff --git a/metagpt/learn/skill_loader.py b/metagpt/learn/skill_loader.py index 7383af66d..b60fa9093 100644 --- a/metagpt/learn/skill_loader.py +++ b/metagpt/learn/skill_loader.py @@ -13,7 +13,7 @@ import aiofiles import yaml from pydantic import BaseModel, Field -from metagpt.config import CONFIG +from metagpt.context import CONTEXT class Example(BaseModel): @@ -80,7 +80,7 @@ class SkillsDeclaration(BaseModel): return {} # List of skills that the agent chooses to activate. - agent_skills = CONFIG.agent_skills + agent_skills = CONTEXT.kwargs.agent_skills if not agent_skills: return {} diff --git a/metagpt/learn/text_to_embedding.py b/metagpt/learn/text_to_embedding.py index 26dab0419..6a4342b06 100644 --- a/metagpt/learn/text_to_embedding.py +++ b/metagpt/learn/text_to_embedding.py @@ -7,7 +7,6 @@ @Desc : Text-to-Embedding skill, which provides text-to-embedding functionality. """ -from metagpt.config import CONFIG from metagpt.tools.openai_text_to_embedding import oas3_openai_text_to_embedding @@ -19,6 +18,4 @@ async def text_to_embedding(text, model="text-embedding-ada-002", openai_api_key :param openai_api_key: OpenAI API key, For more details, checkout: `https://platform.openai.com/account/api-keys` :return: A json object of :class:`ResultEmbedding` class if successful, otherwise `{}`. """ - if CONFIG.OPENAI_API_KEY or openai_api_key: - return await oas3_openai_text_to_embedding(text, model=model, openai_api_key=openai_api_key) - raise EnvironmentError + return await oas3_openai_text_to_embedding(text, model=model, openai_api_key=openai_api_key) diff --git a/metagpt/learn/text_to_speech.py b/metagpt/learn/text_to_speech.py index 9ee3d64ee..f12e52b8e 100644 --- a/metagpt/learn/text_to_speech.py +++ b/metagpt/learn/text_to_speech.py @@ -8,6 +8,7 @@ """ from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.const import BASE64_FORMAT from metagpt.tools.azure_tts import oas3_azsure_tts from metagpt.tools.iflytek_tts import oas3_iflytek_tts @@ -47,7 +48,7 @@ async def text_to_speech( if (CONFIG.AZURE_TTS_SUBSCRIPTION_KEY and CONFIG.AZURE_TTS_REGION) or (subscription_key and region): audio_declaration = "data:audio/wav;base64," base64_data = await oas3_azsure_tts(text, lang, voice, style, role, subscription_key, region) - s3 = S3() + s3 = S3(config.s3) url = await s3.cache(data=base64_data, file_ext=".wav", format=BASE64_FORMAT) if url: return f"[{text}]({url})" diff --git a/metagpt/tools/openai_text_to_embedding.py b/metagpt/tools/openai_text_to_embedding.py index 52b2cc9eb..3eb9faac4 100644 --- a/metagpt/tools/openai_text_to_embedding.py +++ b/metagpt/tools/openai_text_to_embedding.py @@ -13,7 +13,7 @@ import aiohttp import requests from pydantic import BaseModel, Field -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.logs import logger @@ -47,7 +47,8 @@ class OpenAIText2Embedding: """ :param openai_api_key: OpenAI API key, For more details, checkout: `https://platform.openai.com/account/api-keys` """ - self.openai_api_key = openai_api_key or CONFIG.OPENAI_API_KEY + self.openai_llm = config.get_openai_llm() + self.openai_api_key = openai_api_key or self.openai_llm.api_key async def text_2_embedding(self, text, model="text-embedding-ada-002"): """Text to embedding @@ -57,7 +58,7 @@ class OpenAIText2Embedding: :return: A json object of :class:`ResultEmbedding` class if successful, otherwise `{}`. """ - proxies = {"proxy": CONFIG.openai_proxy} if CONFIG.openai_proxy else {} + proxies = {"proxy": self.openai_llm.proxy} if self.openai_llm.proxy else {} headers = {"Content-Type": "application/json", "Authorization": f"Bearer {self.openai_api_key}"} data = {"input": text, "model": model} url = "https://api.openai.com/v1/embeddings" @@ -83,5 +84,5 @@ async def oas3_openai_text_to_embedding(text, model="text-embedding-ada-002", op if not text: return "" if not openai_api_key: - openai_api_key = CONFIG.OPENAI_API_KEY + openai_api_key = config.get_openai_llm().api_key return await OpenAIText2Embedding(openai_api_key).text_2_embedding(text, model=model) diff --git a/metagpt/tools/sd_engine.py b/metagpt/tools/sd_engine.py deleted file mode 100644 index c56b335ca..000000000 --- a/metagpt/tools/sd_engine.py +++ /dev/null @@ -1,133 +0,0 @@ -# -*- coding: utf-8 -*- -# @Date : 2023/7/19 16:28 -# @Author : stellahong (stellahong@deepwisdom.ai) -# @Desc : -import asyncio -import base64 -import io -import json -from os.path import join -from typing import List - -from aiohttp import ClientSession -from PIL import Image, PngImagePlugin - -from metagpt.config import CONFIG -from metagpt.const import SD_OUTPUT_FILE_REPO -from metagpt.logs import logger - -payload = { - "prompt": "", - "negative_prompt": "(easynegative:0.8),black, dark,Low resolution", - "override_settings": {"sd_model_checkpoint": "galaxytimemachinesGTM_photoV20"}, - "seed": -1, - "batch_size": 1, - "n_iter": 1, - "steps": 20, - "cfg_scale": 7, - "width": 512, - "height": 768, - "restore_faces": False, - "tiling": False, - "do_not_save_samples": False, - "do_not_save_grid": False, - "enable_hr": False, - "hr_scale": 2, - "hr_upscaler": "Latent", - "hr_second_pass_steps": 0, - "hr_resize_x": 0, - "hr_resize_y": 0, - "hr_upscale_to_x": 0, - "hr_upscale_to_y": 0, - "truncate_x": 0, - "truncate_y": 0, - "applied_old_hires_behavior_to": None, - "eta": None, - "sampler_index": "DPM++ SDE Karras", - "alwayson_scripts": {}, -} - -default_negative_prompt = "(easynegative:0.8),black, dark,Low resolution" - - -class SDEngine: - def __init__(self): - # Initialize the SDEngine with configuration - self.sd_url = CONFIG.get("SD_URL") - self.sd_t2i_url = f"{self.sd_url}{CONFIG.get('SD_T2I_API')}" - # Define default payload settings for SD API - self.payload = payload - logger.info(self.sd_t2i_url) - - def construct_payload( - self, - prompt, - negtive_prompt=default_negative_prompt, - width=512, - height=512, - sd_model="galaxytimemachinesGTM_photoV20", - ): - # Configure the payload with provided inputs - self.payload["prompt"] = prompt - self.payload["negtive_prompt"] = negtive_prompt - self.payload["width"] = width - self.payload["height"] = height - self.payload["override_settings"]["sd_model_checkpoint"] = sd_model - logger.info(f"call sd payload is {self.payload}") - return self.payload - - def _save(self, imgs, save_name=""): - save_dir = CONFIG.path / SD_OUTPUT_FILE_REPO - if not save_dir.exists(): - save_dir.mkdir(parents=True, exist_ok=True) - batch_decode_base64_to_image(imgs, str(save_dir), save_name=save_name) - - async def run_t2i(self, prompts: List): - # Asynchronously run the SD API for multiple prompts - session = ClientSession() - for payload_idx, payload in enumerate(prompts): - results = await self.run(url=self.sd_t2i_url, payload=payload, session=session) - self._save(results, save_name=f"output_{payload_idx}") - await session.close() - - async def run(self, url, payload, session): - # Perform the HTTP POST request to the SD API - async with session.post(url, json=payload, timeout=600) as rsp: - data = await rsp.read() - - rsp_json = json.loads(data) - imgs = rsp_json["images"] - logger.info(f"callback rsp json is {rsp_json.keys()}") - return imgs - - async def run_i2i(self): - # todo: 添加图生图接口调用 - raise NotImplementedError - - async def run_sam(self): - # todo：添加SAM接口调用 - raise NotImplementedError - - -def decode_base64_to_image(img, save_name): - image = Image.open(io.BytesIO(base64.b64decode(img.split(",", 1)[0]))) - pnginfo = PngImagePlugin.PngInfo() - logger.info(save_name) - image.save(f"{save_name}.png", pnginfo=pnginfo) - return pnginfo, image - - -def batch_decode_base64_to_image(imgs, save_dir="", save_name=""): - for idx, _img in enumerate(imgs): - save_name = join(save_dir, save_name) - decode_base64_to_image(_img, save_name=save_name) - - -if __name__ == "__main__": - engine = SDEngine() - prompt = "pixel style, game design, a game interface should be minimalistic and intuitive with the score and high score displayed at the top. The snake and its food should be easily distinguishable. The game should have a simple color scheme, with a contrasting color for the snake and its food. Complete interface boundary" - - engine.construct_payload(prompt) - - event_loop = asyncio.get_event_loop() - event_loop.run_until_complete(engine.run_t2i(prompt)) diff --git a/metagpt/tools/search_engine_ddg.py b/metagpt/tools/search_engine_ddg.py index 57bc61b82..3d004a4ee 100644 --- a/metagpt/tools/search_engine_ddg.py +++ b/metagpt/tools/search_engine_ddg.py @@ -7,6 +7,8 @@ import json from concurrent import futures from typing import Literal, overload +from metagpt.config2 import config + try: from duckduckgo_search import DDGS except ImportError: @@ -15,8 +17,6 @@ except ImportError: "You can install it by running the command: `pip install -e.[search-ddg]`" ) -from metagpt.config import CONFIG - class DDGAPIWrapper: """Wrapper around duckduckgo_search API. @@ -31,8 +31,8 @@ class DDGAPIWrapper: executor: futures.Executor | None = None, ): kwargs = {} - if CONFIG.global_proxy: - kwargs["proxies"] = CONFIG.global_proxy + if config.proxy: + kwargs["proxies"] = config.proxy self.loop = loop self.executor = executor self.ddgs = DDGS(**kwargs) diff --git a/metagpt/tools/search_engine_googleapi.py b/metagpt/tools/search_engine_googleapi.py index 8aca3aee2..65e1af109 100644 --- a/metagpt/tools/search_engine_googleapi.py +++ b/metagpt/tools/search_engine_googleapi.py @@ -11,7 +11,7 @@ from urllib.parse import urlparse import httplib2 from pydantic import BaseModel, ConfigDict, Field, field_validator -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.logs import logger try: @@ -35,7 +35,7 @@ class GoogleAPIWrapper(BaseModel): @field_validator("google_api_key", mode="before") @classmethod def check_google_api_key(cls, val: str): - val = val or CONFIG.google_api_key + val = val or config.search["google"].api_key if not val: raise ValueError( "To use, make sure you provide the google_api_key when constructing an object. Alternatively, " @@ -47,7 +47,7 @@ class GoogleAPIWrapper(BaseModel): @field_validator("google_cse_id", mode="before") @classmethod def check_google_cse_id(cls, val: str): - val = val or CONFIG.google_cse_id + val = val or config.search["google"].cse_id if not val: raise ValueError( "To use, make sure you provide the google_cse_id when constructing an object. Alternatively, " @@ -59,8 +59,8 @@ class GoogleAPIWrapper(BaseModel): @property def google_api_client(self): build_kwargs = {"developerKey": self.google_api_key} - if CONFIG.global_proxy: - parse_result = urlparse(CONFIG.global_proxy) + if config.proxy: + parse_result = urlparse(config.proxy) proxy_type = parse_result.scheme if proxy_type == "https": proxy_type = "http" diff --git a/metagpt/tools/search_engine_serpapi.py b/metagpt/tools/search_engine_serpapi.py index 9d2d20af6..2d21aa85c 100644 --- a/metagpt/tools/search_engine_serpapi.py +++ b/metagpt/tools/search_engine_serpapi.py @@ -10,7 +10,7 @@ from typing import Any, Dict, Optional, Tuple import aiohttp from pydantic import BaseModel, ConfigDict, Field, field_validator -from metagpt.config import CONFIG +from metagpt.config2 import config class SerpAPIWrapper(BaseModel): @@ -32,7 +32,7 @@ class SerpAPIWrapper(BaseModel): @field_validator("serpapi_api_key", mode="before") @classmethod def check_serpapi_api_key(cls, val: str): - val = val or CONFIG.serpapi_api_key + val = val or config.search["serpapi"].api_key if not val: raise ValueError( "To use, make sure you provide the serpapi_api_key when constructing an object. Alternatively, " diff --git a/metagpt/tools/search_engine_serper.py b/metagpt/tools/search_engine_serper.py index 3dc1d3591..d67148e14 100644 --- a/metagpt/tools/search_engine_serper.py +++ b/metagpt/tools/search_engine_serper.py @@ -11,7 +11,7 @@ from typing import Any, Dict, Optional, Tuple import aiohttp from pydantic import BaseModel, ConfigDict, Field, field_validator -from metagpt.config import CONFIG +from metagpt.config2 import config class SerperWrapper(BaseModel): @@ -25,7 +25,7 @@ class SerperWrapper(BaseModel): @field_validator("serper_api_key", mode="before") @classmethod def check_serper_api_key(cls, val: str): - val = val or CONFIG.serper_api_key + val = val or config.search["serper"].api_key if not val: raise ValueError( "To use, make sure you provide the serper_api_key when constructing an object. Alternatively, " diff --git a/metagpt/tools/web_browser_engine.py b/metagpt/tools/web_browser_engine.py index abd84cc8d..3493a5398 100644 --- a/metagpt/tools/web_browser_engine.py +++ b/metagpt/tools/web_browser_engine.py @@ -8,7 +8,6 @@ from __future__ import annotations import importlib from typing import Any, Callable, Coroutine, overload -from metagpt.config import CONFIG from metagpt.tools import WebBrowserEngineType from metagpt.utils.parse_html import WebPage @@ -19,7 +18,6 @@ class WebBrowserEngine: engine: WebBrowserEngineType | None = None, run_func: Callable[..., Coroutine[Any, Any, WebPage | list[WebPage]]] | None = None, ): - engine = engine or CONFIG.web_browser_engine if engine is None: raise NotImplementedError diff --git a/metagpt/tools/web_browser_engine_playwright.py b/metagpt/tools/web_browser_engine_playwright.py index a45f6a12e..00f2c6bab 100644 --- a/metagpt/tools/web_browser_engine_playwright.py +++ b/metagpt/tools/web_browser_engine_playwright.py @@ -12,7 +12,7 @@ from typing import Literal from playwright.async_api import async_playwright -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.logs import logger from metagpt.utils.parse_html import WebPage @@ -33,13 +33,13 @@ class PlaywrightWrapper: **kwargs, ) -> None: if browser_type is None: - browser_type = CONFIG.playwright_browser_type + browser_type = config.browser["playwright"].driver self.browser_type = browser_type launch_kwargs = launch_kwargs or {} - if CONFIG.global_proxy and "proxy" not in launch_kwargs: + if config.proxy and "proxy" not in launch_kwargs: args = launch_kwargs.get("args", []) if not any(str.startswith(i, "--proxy-server=") for i in args): - launch_kwargs["proxy"] = {"server": CONFIG.global_proxy} + launch_kwargs["proxy"] = {"server": config.proxy} self.launch_kwargs = launch_kwargs context_kwargs = {} if "ignore_https_errors" in kwargs: @@ -79,8 +79,8 @@ class PlaywrightWrapper: executable_path = Path(browser_type.executable_path) if not executable_path.exists() and "executable_path" not in self.launch_kwargs: kwargs = {} - if CONFIG.global_proxy: - kwargs["env"] = {"ALL_PROXY": CONFIG.global_proxy} + if config.proxy: + kwargs["env"] = {"ALL_PROXY": config.proxy} await _install_browsers(self.browser_type, **kwargs) if self._has_run_precheck: diff --git a/metagpt/tools/web_browser_engine_selenium.py b/metagpt/tools/web_browser_engine_selenium.py index 70b651935..18e5db974 100644 --- a/metagpt/tools/web_browser_engine_selenium.py +++ b/metagpt/tools/web_browser_engine_selenium.py @@ -17,7 +17,7 @@ from selenium.webdriver.support.wait import WebDriverWait from webdriver_manager.core.download_manager import WDMDownloadManager from webdriver_manager.core.http import WDMHttpClient -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.utils.parse_html import WebPage @@ -41,12 +41,10 @@ class SeleniumWrapper: loop: asyncio.AbstractEventLoop | None = None, executor: futures.Executor | None = None, ) -> None: - if browser_type is None: - browser_type = CONFIG.selenium_browser_type self.browser_type = browser_type launch_kwargs = launch_kwargs or {} - if CONFIG.global_proxy and "proxy-server" not in launch_kwargs: - launch_kwargs["proxy-server"] = CONFIG.global_proxy + if config.proxy and "proxy-server" not in launch_kwargs: + launch_kwargs["proxy-server"] = config.proxy self.executable_path = launch_kwargs.pop("executable_path", None) self.launch_args = [f"--{k}={v}" for k, v in launch_kwargs.items()] @@ -97,8 +95,8 @@ _webdriver_manager_types = { class WDMHttpProxyClient(WDMHttpClient): def get(self, url, **kwargs): - if "proxies" not in kwargs and CONFIG.global_proxy: - kwargs["proxies"] = {"all_proxy": CONFIG.global_proxy} + if "proxies" not in kwargs and config.proxy: + kwargs["proxies"] = {"all_proxy": config.proxy} return super().get(url, **kwargs) diff --git a/metagpt/utils/mermaid.py b/metagpt/utils/mermaid.py index 235b4979c..893d05be0 100644 --- a/metagpt/utils/mermaid.py +++ b/metagpt/utils/mermaid.py @@ -12,7 +12,7 @@ from pathlib import Path import aiofiles -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.logs import logger from metagpt.utils.common import check_cmd_exists @@ -35,9 +35,9 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048, await f.write(mermaid_code) # tmp.write_text(mermaid_code, encoding="utf-8") - engine = CONFIG.mermaid_engine.lower() + engine = config.mermaid["default"].engine if engine == "nodejs": - if check_cmd_exists(CONFIG.mmdc) != 0: + if check_cmd_exists(config.mmdc) != 0: logger.warning( "RUN `npm install -g @mermaid-js/mermaid-cli` to install mmdc," "or consider changing MERMAID_ENGINE to `playwright`, `pyppeteer`, or `ink`." @@ -49,11 +49,11 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048, # Call the `mmdc` command to convert the Mermaid code to a PNG logger.info(f"Generating {output_file}..") - if CONFIG.puppeteer_config: + if config.puppeteer_config: commands = [ - CONFIG.mmdc, + config.mmdc, "-p", - CONFIG.puppeteer_config, + config.puppeteer_config, "-i", str(tmp), "-o", @@ -64,7 +64,7 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048, str(height), ] else: - commands = [CONFIG.mmdc, "-i", str(tmp), "-o", output_file, "-w", str(width), "-H", str(height)] + commands = [config.mmdc, "-i", str(tmp), "-o", output_file, "-w", str(width), "-H", str(height)] process = await asyncio.create_subprocess_shell( " ".join(commands), stdout=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.PIPE ) diff --git a/metagpt/utils/mmdc_pyppeteer.py b/metagpt/utils/mmdc_pyppeteer.py index 7125cafc5..d80098b7d 100644 --- a/metagpt/utils/mmdc_pyppeteer.py +++ b/metagpt/utils/mmdc_pyppeteer.py @@ -10,7 +10,7 @@ from urllib.parse import urljoin from pyppeteer import launch -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.logs import logger @@ -30,10 +30,10 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048, suffixes = ["png", "svg", "pdf"] __dirname = os.path.dirname(os.path.abspath(__file__)) - if CONFIG.pyppeteer_executable_path: + if config.pyppeteer_executable_path: browser = await launch( headless=True, - executablePath=CONFIG.pyppeteer_executable_path, + executablePath=config.pyppeteer_executable_path, args=["--disable-extensions", "--no-sandbox"], ) else: diff --git a/metagpt/utils/repair_llm_raw_output.py b/metagpt/utils/repair_llm_raw_output.py index a96c3dce0..ec2da53f8 100644 --- a/metagpt/utils/repair_llm_raw_output.py +++ b/metagpt/utils/repair_llm_raw_output.py @@ -9,7 +9,7 @@ from typing import Callable, Union import regex as re from tenacity import RetryCallState, retry, stop_after_attempt, wait_fixed -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.logs import logger from metagpt.utils.custom_decoder import CustomDecoder @@ -152,7 +152,7 @@ def repair_llm_raw_output(output: str, req_keys: list[str], repair_type: RepairT target: { xxx } output: { xxx }] """ - if not CONFIG.repair_llm_output: + if not config.repair_llm_output: return output # do the repairation usually for non-openai models @@ -231,7 +231,7 @@ def run_after_exp_and_passon_next_retry(logger: "loguru.Logger") -> Callable[["R func_param_output = retry_state.kwargs.get("output", "") exp_str = str(retry_state.outcome.exception()) - fix_str = "try to fix it, " if CONFIG.repair_llm_output else "" + fix_str = "try to fix it, " if config.repair_llm_output else "" logger.warning( f"parse json from content inside [CONTENT][/CONTENT] failed at retry " f"{retry_state.attempt_number}, {fix_str}exp: {exp_str}" @@ -244,7 +244,7 @@ def run_after_exp_and_passon_next_retry(logger: "loguru.Logger") -> Callable[["R @retry( - stop=stop_after_attempt(3 if CONFIG.repair_llm_output else 0), + stop=stop_after_attempt(3 if config.repair_llm_output else 0), wait=wait_fixed(1), after=run_after_exp_and_passon_next_retry(logger), ) diff --git a/tests/metagpt/actions/test_rebuild_class_view.py b/tests/metagpt/actions/test_rebuild_class_view.py index 207ba4be1..cc23cc8dc 100644 --- a/tests/metagpt/actions/test_rebuild_class_view.py +++ b/tests/metagpt/actions/test_rebuild_class_view.py @@ -11,7 +11,6 @@ from pathlib import Path import pytest from metagpt.actions.rebuild_class_view import RebuildClassView -from metagpt.config import CONFIG from metagpt.const import GRAPH_REPO_FILE_REPO from metagpt.llm import LLM @@ -22,7 +21,7 @@ async def test_rebuild(): name="RedBean", context=str(Path(__file__).parent.parent.parent.parent / "metagpt"), llm=LLM() ) await action.run() - graph_file_repo = CONFIG.git_repo.new_file_repository(relative_path=GRAPH_REPO_FILE_REPO) + graph_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=GRAPH_REPO_FILE_REPO) assert graph_file_repo.changed_files diff --git a/tests/metagpt/actions/test_rebuild_sequence_view.py b/tests/metagpt/actions/test_rebuild_sequence_view.py index 939412fe7..62f64b666 100644 --- a/tests/metagpt/actions/test_rebuild_sequence_view.py +++ b/tests/metagpt/actions/test_rebuild_sequence_view.py @@ -10,7 +10,6 @@ from pathlib import Path import pytest from metagpt.actions.rebuild_sequence_view import RebuildSequenceView -from metagpt.config import CONFIG from metagpt.const import GRAPH_REPO_FILE_REPO from metagpt.llm import LLM from metagpt.utils.common import aread @@ -22,20 +21,20 @@ from metagpt.utils.git_repository import ChangeType async def test_rebuild(): # Mock data = await aread(filename=Path(__file__).parent / "../../data/graph_db/networkx.json") - graph_db_filename = Path(CONFIG.git_repo.workdir.name).with_suffix(".json") + graph_db_filename = Path(CONTEXT.git_repo.workdir.name).with_suffix(".json") await FileRepository.save_file( filename=str(graph_db_filename), relative_path=GRAPH_REPO_FILE_REPO, content=data, ) - CONFIG.git_repo.add_change({f"{GRAPH_REPO_FILE_REPO}/{graph_db_filename}": ChangeType.UNTRACTED}) - CONFIG.git_repo.commit("commit1") + CONTEXT.git_repo.add_change({f"{GRAPH_REPO_FILE_REPO}/{graph_db_filename}": ChangeType.UNTRACTED}) + CONTEXT.git_repo.commit("commit1") action = RebuildSequenceView( name="RedBean", context=str(Path(__file__).parent.parent.parent.parent / "metagpt"), llm=LLM() ) await action.run() - graph_file_repo = CONFIG.git_repo.new_file_repository(relative_path=GRAPH_REPO_FILE_REPO) + graph_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=GRAPH_REPO_FILE_REPO) assert graph_file_repo.changed_files diff --git a/tests/metagpt/actions/test_summarize_code.py b/tests/metagpt/actions/test_summarize_code.py index 2f7b5c61d..081636a21 100644 --- a/tests/metagpt/actions/test_summarize_code.py +++ b/tests/metagpt/actions/test_summarize_code.py @@ -9,7 +9,6 @@ import pytest from metagpt.actions.summarize_code import SummarizeCode -from metagpt.config import CONFIG from metagpt.const import SYSTEM_DESIGN_FILE_REPO, TASK_FILE_REPO from metagpt.context import CONTEXT from metagpt.logs import logger @@ -181,12 +180,12 @@ async def test_summarize_code(): CONTEXT.src_workspace = CONTEXT.git_repo.workdir / "src" await CONTEXT.file_repo.save_file(filename="1.json", relative_path=SYSTEM_DESIGN_FILE_REPO, content=DESIGN_CONTENT) await CONTEXT.file_repo.save_file(filename="1.json", relative_path=TASK_FILE_REPO, content=TASK_CONTENT) - await CONTEXT.file_repo.save_file(filename="food.py", relative_path=CONFIG.src_workspace, content=FOOD_PY) - await CONTEXT.file_repo.save_file(filename="game.py", relative_path=CONFIG.src_workspace, content=GAME_PY) - await CONTEXT.file_repo.save_file(filename="main.py", relative_path=CONFIG.src_workspace, content=MAIN_PY) - await CONTEXT.file_repo.save_file(filename="snake.py", relative_path=CONFIG.src_workspace, content=SNAKE_PY) + await CONTEXT.file_repo.save_file(filename="food.py", relative_path=CONTEXT.src_workspace, content=FOOD_PY) + await CONTEXT.file_repo.save_file(filename="game.py", relative_path=CONTEXT.src_workspace, content=GAME_PY) + await CONTEXT.file_repo.save_file(filename="main.py", relative_path=CONTEXT.src_workspace, content=MAIN_PY) + await CONTEXT.file_repo.save_file(filename="snake.py", relative_path=CONTEXT.src_workspace, content=SNAKE_PY) - src_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=CONFIG.src_workspace) + src_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=CONTEXT.src_workspace) all_files = src_file_repo.all_files ctx = CodeSummarizeContext(design_filename="1.json", task_filename="1.json", codes_filenames=all_files) action = SummarizeCode(context=ctx) diff --git a/tests/metagpt/learn/test_skill_loader.py b/tests/metagpt/learn/test_skill_loader.py index 529a490c8..45697160b 100644 --- a/tests/metagpt/learn/test_skill_loader.py +++ b/tests/metagpt/learn/test_skill_loader.py @@ -10,13 +10,13 @@ from pathlib import Path import pytest -from metagpt.config import CONFIG +from metagpt.context import CONTEXT from metagpt.learn.skill_loader import SkillsDeclaration @pytest.mark.asyncio async def test_suite(): - CONFIG.agent_skills = [ + CONTEXT.kwargs.agent_skills = [ {"id": 1, "name": "text_to_speech", "type": "builtin", "config": {}, "enabled": True}, {"id": 2, "name": "text_to_image", "type": "builtin", "config": {}, "enabled": True}, {"id": 3, "name": "ai_call", "type": "builtin", "config": {}, "enabled": True}, diff --git a/tests/metagpt/learn/test_text_to_embedding.py b/tests/metagpt/learn/test_text_to_embedding.py index cbd1bbbbc..cbc8ddf18 100644 --- a/tests/metagpt/learn/test_text_to_embedding.py +++ b/tests/metagpt/learn/test_text_to_embedding.py @@ -9,14 +9,14 @@ import pytest -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.learn.text_to_embedding import text_to_embedding @pytest.mark.asyncio async def test_text_to_embedding(): # Prerequisites - assert CONFIG.OPENAI_API_KEY + assert config.get_openai_llm() v = await text_to_embedding(text="Panda emoji") assert len(v.data) > 0 diff --git a/tests/metagpt/tools/test_azure_tts.py b/tests/metagpt/tools/test_azure_tts.py index dca71544e..a33925a5c 100644 --- a/tests/metagpt/tools/test_azure_tts.py +++ b/tests/metagpt/tools/test_azure_tts.py @@ -12,6 +12,7 @@ import pytest from azure.cognitiveservices.speech import ResultReason from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.tools.azure_tts import AzureTTS @@ -32,7 +33,7 @@ async def test_azure_tts(): “Writing a binary file in Python is similar to writing a regular text file, but you'll work with bytes instead of strings.” """ - path = CONFIG.path / "tts" + path = config.workspace.path / "tts" path.mkdir(exist_ok=True, parents=True) filename = path / "girl.wav" filename.unlink(missing_ok=True) diff --git a/tests/metagpt/tools/test_metagpt_oas3_api_svc.py b/tests/metagpt/tools/test_metagpt_oas3_api_svc.py index 5f52b28cc..3cf5e515b 100644 --- a/tests/metagpt/tools/test_metagpt_oas3_api_svc.py +++ b/tests/metagpt/tools/test_metagpt_oas3_api_svc.py @@ -12,14 +12,14 @@ from pathlib import Path import pytest import requests -from metagpt.config import CONFIG +from metagpt.context import CONTEXT @pytest.mark.asyncio async def test_oas2_svc(): workdir = Path(__file__).parent.parent.parent.parent script_pathname = workdir / "metagpt/tools/metagpt_oas3_api_svc.py" - env = CONFIG.new_environ() + env = CONTEXT.new_environ() env["PYTHONPATH"] = str(workdir) + ":" + env.get("PYTHONPATH", "") process = subprocess.Popen(["python", str(script_pathname)], cwd=str(workdir), env=env) await asyncio.sleep(5) diff --git a/tests/metagpt/tools/test_metagpt_text_to_image.py b/tests/metagpt/tools/test_metagpt_text_to_image.py index b765119f0..0dcad20d2 100644 --- a/tests/metagpt/tools/test_metagpt_text_to_image.py +++ b/tests/metagpt/tools/test_metagpt_text_to_image.py @@ -10,7 +10,7 @@ from unittest.mock import AsyncMock import pytest -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.tools.metagpt_text_to_image import oas3_metagpt_text_to_image @@ -24,7 +24,7 @@ async def test_draw(mocker): mock_post.return_value.__aenter__.return_value = mock_response # Prerequisites - assert CONFIG.METAGPT_TEXT_TO_IMAGE_MODEL_URL + assert config.METAGPT_TEXT_TO_IMAGE_MODEL_URL binary_data = await oas3_metagpt_text_to_image("Panda emoji") assert binary_data diff --git a/tests/metagpt/tools/test_moderation.py b/tests/metagpt/tools/test_moderation.py index e1226484a..8dc9e9d5e 100644 --- a/tests/metagpt/tools/test_moderation.py +++ b/tests/metagpt/tools/test_moderation.py @@ -8,7 +8,7 @@ import pytest -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.llm import LLM from metagpt.tools.moderation import Moderation @@ -24,9 +24,7 @@ from metagpt.tools.moderation import Moderation ) async def test_amoderation(content): # Prerequisites - assert CONFIG.OPENAI_API_KEY and CONFIG.OPENAI_API_KEY != "YOUR_API_KEY" - assert not CONFIG.OPENAI_API_TYPE - assert CONFIG.OPENAI_API_MODEL + assert config.get_openai_llm() moderation = Moderation(LLM()) results = await moderation.amoderation(content=content) diff --git a/tests/metagpt/tools/test_openai_text_to_embedding.py b/tests/metagpt/tools/test_openai_text_to_embedding.py index 086c9d45b..58c38d480 100644 --- a/tests/metagpt/tools/test_openai_text_to_embedding.py +++ b/tests/metagpt/tools/test_openai_text_to_embedding.py @@ -8,16 +8,14 @@ import pytest -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.tools.openai_text_to_embedding import oas3_openai_text_to_embedding @pytest.mark.asyncio async def test_embedding(): # Prerequisites - assert CONFIG.OPENAI_API_KEY and CONFIG.OPENAI_API_KEY != "YOUR_API_KEY" - assert not CONFIG.OPENAI_API_TYPE - assert CONFIG.OPENAI_API_MODEL + assert config.get_openai_llm() result = await oas3_openai_text_to_embedding("Panda emoji") assert result diff --git a/tests/metagpt/tools/test_openai_text_to_image.py b/tests/metagpt/tools/test_openai_text_to_image.py index e560da798..1a1c9540f 100644 --- a/tests/metagpt/tools/test_openai_text_to_image.py +++ b/tests/metagpt/tools/test_openai_text_to_image.py @@ -8,7 +8,7 @@ import pytest -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.tools.openai_text_to_image import ( OpenAIText2Image, oas3_openai_text_to_image, @@ -18,9 +18,7 @@ from metagpt.tools.openai_text_to_image import ( @pytest.mark.asyncio async def test_draw(): # Prerequisites - assert CONFIG.OPENAI_API_KEY and CONFIG.OPENAI_API_KEY != "YOUR_API_KEY" - assert not CONFIG.OPENAI_API_TYPE - assert CONFIG.OPENAI_API_MODEL + assert config.get_openai_llm() binary_data = await oas3_openai_text_to_image("Panda emoji") assert binary_data diff --git a/tests/metagpt/tools/test_openapi_v3_hello.py b/tests/metagpt/tools/test_openapi_v3_hello.py index 5726cf8e0..daa5d21c6 100644 --- a/tests/metagpt/tools/test_openapi_v3_hello.py +++ b/tests/metagpt/tools/test_openapi_v3_hello.py @@ -12,14 +12,14 @@ from pathlib import Path import pytest import requests -from metagpt.config import CONFIG +from metagpt.context import CONTEXT @pytest.mark.asyncio async def test_hello(): workdir = Path(__file__).parent.parent.parent.parent script_pathname = workdir / "metagpt/tools/openapi_v3_hello.py" - env = CONFIG.new_environ() + env = CONTEXT.new_environ() env["PYTHONPATH"] = str(workdir) + ":" + env.get("PYTHONPATH", "") process = subprocess.Popen(["python", str(script_pathname)], cwd=workdir, env=env) await asyncio.sleep(5) diff --git a/tests/metagpt/tools/test_sd_tool.py b/tests/metagpt/tools/test_sd_tool.py deleted file mode 100644 index 52b970229..000000000 --- a/tests/metagpt/tools/test_sd_tool.py +++ /dev/null @@ -1,26 +0,0 @@ -# -*- coding: utf-8 -*- -# @Date : 2023/7/22 02:40 -# @Author : stellahong (stellahong@deepwisdom.ai) -# -import os - -from metagpt.config import CONFIG -from metagpt.tools.sd_engine import SDEngine - - -def test_sd_engine_init(): - sd_engine = SDEngine() - assert sd_engine.payload["seed"] == -1 - - -def test_sd_engine_generate_prompt(): - sd_engine = SDEngine() - sd_engine.construct_payload(prompt="test") - assert sd_engine.payload["prompt"] == "test" - - -async def test_sd_engine_run_t2i(): - sd_engine = SDEngine() - await sd_engine.run_t2i(prompts=["test"]) - img_path = CONFIG.path / "resources" / "SD_Output" / "output_0.png" - assert os.path.exists(img_path) diff --git a/tests/metagpt/tools/test_search_engine.py b/tests/metagpt/tools/test_search_engine.py index dab466af7..411929f64 100644 --- a/tests/metagpt/tools/test_search_engine.py +++ b/tests/metagpt/tools/test_search_engine.py @@ -14,7 +14,7 @@ from typing import Callable import pytest import tests.data.search -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.logs import logger from metagpt.tools import SearchEngineType from metagpt.tools.search_engine import SearchEngine @@ -50,13 +50,12 @@ async def test_search_engine(search_engine_type, run_func: Callable, max_results # Prerequisites cache_json_path = None if search_engine_type is SearchEngineType.SERPAPI_GOOGLE: - assert CONFIG.SERPAPI_API_KEY and CONFIG.SERPAPI_API_KEY != "YOUR_API_KEY" + assert config.search["serpapi"] cache_json_path = search_cache_path / f"serpapi-metagpt-{max_results}.json" elif search_engine_type is SearchEngineType.DIRECT_GOOGLE: - assert CONFIG.GOOGLE_API_KEY and CONFIG.GOOGLE_API_KEY != "YOUR_API_KEY" - assert CONFIG.GOOGLE_CSE_ID and CONFIG.GOOGLE_CSE_ID != "YOUR_CSE_ID" + assert config.search["google"] elif search_engine_type is SearchEngineType.SERPER_GOOGLE: - assert CONFIG.SERPER_API_KEY and CONFIG.SERPER_API_KEY != "YOUR_API_KEY" + assert config.search["serper"] cache_json_path = search_cache_path / f"serper-metagpt-{max_results}.json" if cache_json_path: diff --git a/tests/metagpt/tools/test_ut_writer.py b/tests/metagpt/tools/test_ut_writer.py index eac28d56f..29b6572c2 100644 --- a/tests/metagpt/tools/test_ut_writer.py +++ b/tests/metagpt/tools/test_ut_writer.py @@ -9,7 +9,7 @@ from pathlib import Path import pytest -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.const import API_QUESTIONS_PATH, UT_PY_PATH from metagpt.tools.ut_writer import YFT_PROMPT_PREFIX, UTGenerator @@ -20,9 +20,7 @@ class TestUTWriter: # Prerequisites swagger_file = Path(__file__).parent / "../../data/ut_writer/yft_swaggerApi.json" assert swagger_file.exists() - assert CONFIG.OPENAI_API_KEY and CONFIG.OPENAI_API_KEY != "YOUR_API_KEY" - assert not CONFIG.OPENAI_API_TYPE - assert CONFIG.OPENAI_API_MODEL + assert config.get_openai_llm() tags = ["测试", "作业"] # 这里在文件中手动加入了两个测试标签的API diff --git a/tests/metagpt/utils/test_mermaid.py b/tests/metagpt/utils/test_mermaid.py index 486742524..6345e9c51 100644 --- a/tests/metagpt/utils/test_mermaid.py +++ b/tests/metagpt/utils/test_mermaid.py @@ -9,6 +9,7 @@ import pytest from metagpt.config import CONFIG +from metagpt.context import CONTEXT from metagpt.utils.common import check_cmd_exists from metagpt.utils.mermaid import MMC1, mermaid_to_file @@ -22,7 +23,7 @@ async def test_mermaid(engine): assert check_cmd_exists("npm") == 0 CONFIG.mermaid_engine = engine - save_to = CONFIG.git_repo.workdir / f"{CONFIG.mermaid_engine}/1" + save_to = CONTEXT.git_repo.workdir / f"{CONFIG.mermaid_engine}/1" await mermaid_to_file(MMC1, save_to) # ink does not support pdf diff --git a/tests/metagpt/utils/test_repair_llm_raw_output.py b/tests/metagpt/utils/test_repair_llm_raw_output.py index 1970c6443..bd6169d71 100644 --- a/tests/metagpt/utils/test_repair_llm_raw_output.py +++ b/tests/metagpt/utils/test_repair_llm_raw_output.py @@ -2,13 +2,13 @@ # -*- coding: utf-8 -*- # @Desc : unittest of repair_llm_raw_output -from metagpt.config import CONFIG +from metagpt.config2 import config """ CONFIG.repair_llm_output should be True before retry_parse_json_text imported. so we move `from ... impot ...` into each `test_xx` to avoid `Module level import not at top of file` format warning. """ -CONFIG.repair_llm_output = True +config.repair_llm_output = True def test_repair_case_sensitivity(): From d823f3a52ec9f5223c2340725a143b0a83d4bfb2 Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 20:21:06 +0800 Subject: [PATCH 43/61] fix bug --- metagpt/context.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/metagpt/context.py b/metagpt/context.py index 35892f3f3..1c351ef22 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -173,7 +173,7 @@ class ContextMixin(BaseModel): @property def llm(self) -> BaseLLM: """Role llm: role llm > context llm""" - print(f"class:{self.__class__.__name__}({self.name}), llm: {self._llm}, llm_config: {self._llm_config}") + # print(f"class:{self.__class__.__name__}({self.name}), llm: {self._llm}, llm_config: {self._llm_config}") if self._llm_config and not self._llm: self._llm = self.context.llm_with_cost_manager_from_llm_config(self._llm_config) return self._llm or self.context.llm() From 001ec115d75873f1ed0cfc3b19d1b51c2da45995 Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 20:34:42 +0800 Subject: [PATCH 44/61] use config --- metagpt/actions/design_api.py | 9 ++-- metagpt/actions/research.py | 5 +-- metagpt/config2.py | 6 +++ metagpt/learn/text_to_speech.py | 9 ++-- metagpt/tools/azure_tts.py | 9 +--- metagpt/tools/iflytek_tts.py | 15 ++----- metagpt/tools/search_engine.py | 2 - metagpt/utils/mermaid.py | 3 +- tests/metagpt/learn/test_text_to_speech.py | 41 +++++++++++-------- tests/metagpt/tools/test_azure_tts.py | 5 +-- tests/metagpt/tools/test_iflytek_tts.py | 14 +++---- .../test_web_browser_engine_playwright.py | 8 ++-- .../tools/test_web_browser_engine_selenium.py | 8 ++-- tests/metagpt/utils/test_mermaid.py | 6 +-- 14 files changed, 64 insertions(+), 76 deletions(-) diff --git a/metagpt/actions/design_api.py b/metagpt/actions/design_api.py index 3e978f823..5f973bb60 100644 --- a/metagpt/actions/design_api.py +++ b/metagpt/actions/design_api.py @@ -110,7 +110,7 @@ class WriteDesign(Action): if not data_api_design: return pathname = self.git_repo.workdir / DATA_API_DESIGN_FILE_REPO / Path(design_doc.filename).with_suffix("") - await WriteDesign._save_mermaid_file(data_api_design, pathname) + await self._save_mermaid_file(data_api_design, pathname) logger.info(f"Save class view to {str(pathname)}") async def _save_seq_flow(self, design_doc): @@ -119,13 +119,12 @@ class WriteDesign(Action): if not seq_flow: return pathname = self.git_repo.workdir / Path(SEQ_FLOW_FILE_REPO) / Path(design_doc.filename).with_suffix("") - await WriteDesign._save_mermaid_file(seq_flow, pathname) + await self._save_mermaid_file(seq_flow, pathname) logger.info(f"Saving sequence flow to {str(pathname)}") async def _save_pdf(self, design_doc): await self.file_repo.save_as(doc=design_doc, with_suffix=".md", relative_path=SYSTEM_DESIGN_PDF_FILE_REPO) - @staticmethod - async def _save_mermaid_file(data: str, pathname: Path): + async def _save_mermaid_file(self, data: str, pathname: Path): pathname.parent.mkdir(parents=True, exist_ok=True) - await mermaid_to_file(data, pathname) + await mermaid_to_file(self.config.mermaid_engine, data, pathname) diff --git a/metagpt/actions/research.py b/metagpt/actions/research.py index a635714ef..0af49a1cf 100644 --- a/metagpt/actions/research.py +++ b/metagpt/actions/research.py @@ -8,7 +8,6 @@ from typing import Callable, Optional, Union from pydantic import Field, parse_obj_as from metagpt.actions import Action -from metagpt.config import CONFIG from metagpt.config2 import config from metagpt.logs import logger from metagpt.tools.search_engine import SearchEngine @@ -216,9 +215,7 @@ class WebBrowseAndSummarize(Action): for u, content in zip([url, *urls], contents): content = content.inner_text chunk_summaries = [] - for prompt in generate_prompt_chunk( - content, prompt_template, self.llm.model, system_text, CONFIG.max_tokens_rsp - ): + for prompt in generate_prompt_chunk(content, prompt_template, self.llm.model, system_text, 4096): logger.debug(prompt) summary = await self._aask(prompt, [system_text]) if summary == "Not relevant.": diff --git a/metagpt/config2.py b/metagpt/config2.py index 2a9611627..6345c1b8c 100644 --- a/metagpt/config2.py +++ b/metagpt/config2.py @@ -74,6 +74,12 @@ class Config(CLIParams, YamlModel): mmdc: str = "mmdc" puppeteer_config: str = "" pyppeteer_executable_path: str = "" + IFLYTEK_APP_ID: str = "" + IFLYTEK_APP_SECRET: str = "" + IFLYTEK_APP_KEY: str = "" + AZURE_TTS_SUBSCRIPTION_KEY: str = "" + AZURE_TTS_REGION: str = "" + mermaid_engine: str = "nodejs" @classmethod def default(cls): diff --git a/metagpt/learn/text_to_speech.py b/metagpt/learn/text_to_speech.py index f12e52b8e..8ffafbd0e 100644 --- a/metagpt/learn/text_to_speech.py +++ b/metagpt/learn/text_to_speech.py @@ -7,7 +7,6 @@ @Desc : Text-to-Speech skill, which provides text-to-speech functionality """ -from metagpt.config import CONFIG from metagpt.config2 import config from metagpt.const import BASE64_FORMAT from metagpt.tools.azure_tts import oas3_azsure_tts @@ -45,7 +44,7 @@ async def text_to_speech( """ - if (CONFIG.AZURE_TTS_SUBSCRIPTION_KEY and CONFIG.AZURE_TTS_REGION) or (subscription_key and region): + if subscription_key and region: audio_declaration = "data:audio/wav;base64," base64_data = await oas3_azsure_tts(text, lang, voice, style, role, subscription_key, region) s3 = S3(config.s3) @@ -53,14 +52,12 @@ async def text_to_speech( if url: return f"[{text}]({url})" return audio_declaration + base64_data if base64_data else base64_data - if (CONFIG.IFLYTEK_APP_ID and CONFIG.IFLYTEK_API_KEY and CONFIG.IFLYTEK_API_SECRET) or ( - iflytek_app_id and iflytek_api_key and iflytek_api_secret - ): + if iflytek_app_id and iflytek_api_key and iflytek_api_secret: audio_declaration = "data:audio/mp3;base64," base64_data = await oas3_iflytek_tts( text=text, app_id=iflytek_app_id, api_key=iflytek_api_key, api_secret=iflytek_api_secret ) - s3 = S3() + s3 = S3(config.s3) url = await s3.cache(data=base64_data, file_ext=".mp3", format=BASE64_FORMAT) if url: return f"[{text}]({url})" diff --git a/metagpt/tools/azure_tts.py b/metagpt/tools/azure_tts.py index f4f8aa0a2..2e0e2267c 100644 --- a/metagpt/tools/azure_tts.py +++ b/metagpt/tools/azure_tts.py @@ -13,7 +13,6 @@ from uuid import uuid4 import aiofiles from azure.cognitiveservices.speech import AudioConfig, SpeechConfig, SpeechSynthesizer -from metagpt.config import CONFIG from metagpt.logs import logger @@ -25,8 +24,8 @@ class AzureTTS: :param subscription_key: key is used to access your Azure AI service API, see: `https://portal.azure.com/` > `Resource Management` > `Keys and Endpoint` :param region: This is the location (or region) of your resource. You may need to use this field when making calls to this API. """ - self.subscription_key = subscription_key if subscription_key else CONFIG.AZURE_TTS_SUBSCRIPTION_KEY - self.region = region if region else CONFIG.AZURE_TTS_REGION + self.subscription_key = subscription_key + self.region = region # 参数参考：https://learn.microsoft.com/zh-cn/azure/cognitive-services/speech-service/language-support?tabs=tts#voice-styles-and-roles async def synthesize_speech(self, lang, voice, text, output_file): @@ -83,10 +82,6 @@ async def oas3_azsure_tts(text, lang="", voice="", style="", role="", subscripti role = "Girl" if not style: style = "affectionate" - if not subscription_key: - subscription_key = CONFIG.AZURE_TTS_SUBSCRIPTION_KEY - if not region: - region = CONFIG.AZURE_TTS_REGION xml_value = AzureTTS.role_style_text(role=role, style=style, text=text) tts = AzureTTS(subscription_key=subscription_key, region=region) diff --git a/metagpt/tools/iflytek_tts.py b/metagpt/tools/iflytek_tts.py index ad2395362..6ce48826b 100644 --- a/metagpt/tools/iflytek_tts.py +++ b/metagpt/tools/iflytek_tts.py @@ -23,7 +23,6 @@ import aiofiles import websockets as websockets from pydantic import BaseModel -from metagpt.config import CONFIG from metagpt.logs import logger @@ -56,9 +55,9 @@ class IFlyTekTTS(object): :param api_key: WebAPI argument, see: `https://console.xfyun.cn/services/tts` :param api_secret: WebAPI argument, see: `https://console.xfyun.cn/services/tts` """ - self.app_id = app_id or CONFIG.IFLYTEK_APP_ID - self.api_key = api_key or CONFIG.IFLYTEK_API_KEY - self.api_secret = api_secret or CONFIG.API_SECRET + self.app_id = app_id + self.api_key = api_key + self.api_secret = api_secret async def synthesize_speech(self, text, output_file: str, voice=DEFAULT_IFLYTEK_VOICE): url = self._create_url() @@ -127,14 +126,6 @@ async def oas3_iflytek_tts(text: str, voice: str = "", app_id: str = "", api_key :return: Returns the Base64-encoded .mp3 file data if successful, otherwise an empty string. """ - if not app_id: - app_id = CONFIG.IFLYTEK_APP_ID - if not api_key: - api_key = CONFIG.IFLYTEK_API_KEY - if not api_secret: - api_secret = CONFIG.IFLYTEK_API_SECRET - if not voice: - voice = CONFIG.IFLYTEK_VOICE or DEFAULT_IFLYTEK_VOICE filename = Path(__file__).parent / (uuid.uuid4().hex + ".mp3") try: diff --git a/metagpt/tools/search_engine.py b/metagpt/tools/search_engine.py index 64388a11f..fd237d537 100644 --- a/metagpt/tools/search_engine.py +++ b/metagpt/tools/search_engine.py @@ -10,7 +10,6 @@ from typing import Callable, Coroutine, Literal, Optional, Union, overload from semantic_kernel.skill_definition import sk_function -from metagpt.config import CONFIG from metagpt.tools import SearchEngineType @@ -46,7 +45,6 @@ class SearchEngine: engine: Optional[SearchEngineType] = None, run_func: Callable[[str, int, bool], Coroutine[None, None, Union[str, list[str]]]] = None, ): - engine = engine or CONFIG.search_engine if engine == SearchEngineType.SERPAPI_GOOGLE: module = "metagpt.tools.search_engine_serpapi" run_func = importlib.import_module(module).SerpAPIWrapper().run diff --git a/metagpt/utils/mermaid.py b/metagpt/utils/mermaid.py index 893d05be0..3f6a2ef12 100644 --- a/metagpt/utils/mermaid.py +++ b/metagpt/utils/mermaid.py @@ -17,7 +17,7 @@ from metagpt.logs import logger from metagpt.utils.common import check_cmd_exists -async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048, height=2048) -> int: +async def mermaid_to_file(engine, mermaid_code, output_file_without_suffix, width=2048, height=2048) -> int: """suffix: png/svg/pdf :param mermaid_code: mermaid code @@ -35,7 +35,6 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048, await f.write(mermaid_code) # tmp.write_text(mermaid_code, encoding="utf-8") - engine = config.mermaid["default"].engine if engine == "nodejs": if check_cmd_exists(config.mmdc) != 0: logger.warning( diff --git a/tests/metagpt/learn/test_text_to_speech.py b/tests/metagpt/learn/test_text_to_speech.py index aca08b9a2..41611171c 100644 --- a/tests/metagpt/learn/test_text_to_speech.py +++ b/tests/metagpt/learn/test_text_to_speech.py @@ -9,34 +9,43 @@ import pytest -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.learn.text_to_speech import text_to_speech @pytest.mark.asyncio async def test_text_to_speech(): # Prerequisites - assert CONFIG.IFLYTEK_APP_ID - assert CONFIG.IFLYTEK_API_KEY - assert CONFIG.IFLYTEK_API_SECRET - assert CONFIG.AZURE_TTS_SUBSCRIPTION_KEY and CONFIG.AZURE_TTS_SUBSCRIPTION_KEY != "YOUR_API_KEY" - assert CONFIG.AZURE_TTS_REGION + assert config.IFLYTEK_APP_ID + assert config.IFLYTEK_API_KEY + assert config.IFLYTEK_API_SECRET + assert config.AZURE_TTS_SUBSCRIPTION_KEY and config.AZURE_TTS_SUBSCRIPTION_KEY != "YOUR_API_KEY" + assert config.AZURE_TTS_REGION + i = config.copy() # test azure - data = await text_to_speech("panda emoji") + data = await text_to_speech( + "panda emoji", + subscription_key=i.AZURE_TTS_SUBSCRIPTION_KEY, + region=i.AZURE_TTS_REGION, + iflytek_api_key=i.IFLYTEK_API_KEY, + iflytek_api_secret=i.IFLYTEK_API_SECRET, + iflytek_app_id=i.IFLYTEK_APP_ID, + ) assert "base64" in data or "http" in data # test iflytek ## Mock session env - old_options = CONFIG.options.copy() - new_options = old_options.copy() - new_options["AZURE_TTS_SUBSCRIPTION_KEY"] = "" - CONFIG.set_context(new_options) - try: - data = await text_to_speech("panda emoji") - assert "base64" in data or "http" in data - finally: - CONFIG.set_context(old_options) + i.AZURE_TTS_SUBSCRIPTION_KEY = "" + data = await text_to_speech( + "panda emoji", + subscription_key=i.AZURE_TTS_SUBSCRIPTION_KEY, + region=i.AZURE_TTS_REGION, + iflytek_api_key=i.IFLYTEK_API_KEY, + iflytek_api_secret=i.IFLYTEK_API_SECRET, + iflytek_app_id=i.IFLYTEK_APP_ID, + ) + assert "base64" in data or "http" in data if __name__ == "__main__": diff --git a/tests/metagpt/tools/test_azure_tts.py b/tests/metagpt/tools/test_azure_tts.py index a33925a5c..e856d3b27 100644 --- a/tests/metagpt/tools/test_azure_tts.py +++ b/tests/metagpt/tools/test_azure_tts.py @@ -11,7 +11,6 @@ import pytest from azure.cognitiveservices.speech import ResultReason -from metagpt.config import CONFIG from metagpt.config2 import config from metagpt.tools.azure_tts import AzureTTS @@ -19,8 +18,8 @@ from metagpt.tools.azure_tts import AzureTTS @pytest.mark.asyncio async def test_azure_tts(): # Prerequisites - assert CONFIG.AZURE_TTS_SUBSCRIPTION_KEY and CONFIG.AZURE_TTS_SUBSCRIPTION_KEY != "YOUR_API_KEY" - assert CONFIG.AZURE_TTS_REGION + assert config.AZURE_TTS_SUBSCRIPTION_KEY and config.AZURE_TTS_SUBSCRIPTION_KEY != "YOUR_API_KEY" + assert config.AZURE_TTS_REGION azure_tts = AzureTTS(subscription_key="", region="") text = """ diff --git a/tests/metagpt/tools/test_iflytek_tts.py b/tests/metagpt/tools/test_iflytek_tts.py index 58d8a83ce..18af0a723 100644 --- a/tests/metagpt/tools/test_iflytek_tts.py +++ b/tests/metagpt/tools/test_iflytek_tts.py @@ -7,22 +7,22 @@ """ import pytest -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.tools.iflytek_tts import oas3_iflytek_tts @pytest.mark.asyncio async def test_tts(): # Prerequisites - assert CONFIG.IFLYTEK_APP_ID - assert CONFIG.IFLYTEK_API_KEY - assert CONFIG.IFLYTEK_API_SECRET + assert config.IFLYTEK_APP_ID + assert config.IFLYTEK_API_KEY + assert config.IFLYTEK_API_SECRET result = await oas3_iflytek_tts( text="你好，hello", - app_id=CONFIG.IFLYTEK_APP_ID, - api_key=CONFIG.IFLYTEK_API_KEY, - api_secret=CONFIG.IFLYTEK_API_SECRET, + app_id=config.IFLYTEK_APP_ID, + api_key=config.IFLYTEK_API_KEY, + api_secret=config.IFLYTEK_API_SECRET, ) assert result diff --git a/tests/metagpt/tools/test_web_browser_engine_playwright.py b/tests/metagpt/tools/test_web_browser_engine_playwright.py index 0f2679531..32019bad9 100644 --- a/tests/metagpt/tools/test_web_browser_engine_playwright.py +++ b/tests/metagpt/tools/test_web_browser_engine_playwright.py @@ -4,7 +4,7 @@ import pytest -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.tools import web_browser_engine_playwright from metagpt.utils.parse_html import WebPage @@ -20,11 +20,11 @@ from metagpt.utils.parse_html import WebPage ids=["chromium-normal", "firefox-normal", "webkit-normal"], ) async def test_scrape_web_page(browser_type, use_proxy, kwagrs, url, urls, proxy, capfd): - global_proxy = CONFIG.global_proxy + global_proxy = config.proxy try: if use_proxy: server, proxy = await proxy - CONFIG.global_proxy = proxy + config.proxy = proxy browser = web_browser_engine_playwright.PlaywrightWrapper(browser_type=browser_type, **kwagrs) result = await browser.run(url) assert isinstance(result, WebPage) @@ -39,7 +39,7 @@ async def test_scrape_web_page(browser_type, use_proxy, kwagrs, url, urls, proxy server.close() assert "Proxy:" in capfd.readouterr().out finally: - CONFIG.global_proxy = global_proxy + config.proxy = global_proxy if __name__ == "__main__": diff --git a/tests/metagpt/tools/test_web_browser_engine_selenium.py b/tests/metagpt/tools/test_web_browser_engine_selenium.py index 8fe365352..bd5abcb9b 100644 --- a/tests/metagpt/tools/test_web_browser_engine_selenium.py +++ b/tests/metagpt/tools/test_web_browser_engine_selenium.py @@ -4,7 +4,7 @@ import pytest -from metagpt.config import CONFIG +from metagpt.config2 import config from metagpt.tools import web_browser_engine_selenium from metagpt.utils.parse_html import WebPage @@ -23,11 +23,11 @@ async def test_scrape_web_page(browser_type, use_proxy, url, urls, proxy, capfd) # Prerequisites # firefox, chrome, Microsoft Edge - global_proxy = CONFIG.global_proxy + global_proxy = config.proxy try: if use_proxy: server, proxy = await proxy - CONFIG.global_proxy = proxy + config.proxy = proxy browser = web_browser_engine_selenium.SeleniumWrapper(browser_type=browser_type) result = await browser.run(url) assert isinstance(result, WebPage) @@ -42,7 +42,7 @@ async def test_scrape_web_page(browser_type, use_proxy, url, urls, proxy, capfd) server.close() assert "Proxy:" in capfd.readouterr().out finally: - CONFIG.global_proxy = global_proxy + config.proxy = global_proxy if __name__ == "__main__": diff --git a/tests/metagpt/utils/test_mermaid.py b/tests/metagpt/utils/test_mermaid.py index 6345e9c51..367223332 100644 --- a/tests/metagpt/utils/test_mermaid.py +++ b/tests/metagpt/utils/test_mermaid.py @@ -8,7 +8,6 @@ import pytest -from metagpt.config import CONFIG from metagpt.context import CONTEXT from metagpt.utils.common import check_cmd_exists from metagpt.utils.mermaid import MMC1, mermaid_to_file @@ -22,9 +21,8 @@ async def test_mermaid(engine): # playwright prerequisites: playwright install --with-deps chromium assert check_cmd_exists("npm") == 0 - CONFIG.mermaid_engine = engine - save_to = CONTEXT.git_repo.workdir / f"{CONFIG.mermaid_engine}/1" - await mermaid_to_file(MMC1, save_to) + save_to = CONTEXT.git_repo.workdir / f"{engine}/1" + await mermaid_to_file(engine, MMC1, save_to) # ink does not support pdf if engine == "ink": From 0514ee565b0e8bec85beac898d57e391be1891e6 Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 20:36:28 +0800 Subject: [PATCH 45/61] fix bug --- metagpt/actions/write_prd.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/metagpt/actions/write_prd.py b/metagpt/actions/write_prd.py index 728ddfbf9..a838dea8e 100644 --- a/metagpt/actions/write_prd.py +++ b/metagpt/actions/write_prd.py @@ -164,7 +164,7 @@ class WritePRD(Action): pathname = self.git_repo.workdir / Path(COMPETITIVE_ANALYSIS_FILE_REPO) / Path(prd_doc.filename).with_suffix("") if not pathname.parent.exists(): pathname.parent.mkdir(parents=True, exist_ok=True) - await mermaid_to_file(quadrant_chart, pathname) + await mermaid_to_file(self.config.mermaid_engine, quadrant_chart, pathname) async def _save_pdf(self, prd_doc): await self.file_repo.save_as(doc=prd_doc, with_suffix=".md", relative_path=PRD_PDF_FILE_REPO) From cab6ee877d3660e9dcc54845e2e3f4e0bdfbe4ed Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 21:23:03 +0800 Subject: [PATCH 46/61] fix bugs --- metagpt/actions/rebuild_sequence_view.py | 2 ++ metagpt/config2.py | 4 ++-- metagpt/subscription.py | 2 +- tests/metagpt/actions/test_debug_error.py | 2 +- tests/metagpt/actions/test_prepare_documents.py | 2 +- tests/metagpt/actions/test_rebuild_class_view.py | 3 ++- .../metagpt/actions/test_rebuild_sequence_view.py | 3 ++- tests/metagpt/actions/test_run_code.py | 6 +++--- tests/metagpt/actions/test_summarize_code.py | 2 +- tests/metagpt/actions/test_talk_action.py | 9 ++++----- tests/metagpt/actions/test_write_code_review.py | 2 +- tests/metagpt/actions/test_write_prd.py | 4 ++-- tests/metagpt/actions/test_write_teaching_plan.py | 2 +- tests/metagpt/actions/test_write_test.py | 2 +- tests/metagpt/learn/test_text_to_image.py | 4 +++- .../serialize_deserialize/test_write_code.py | 2 +- .../test_write_code_review.py | 2 +- tests/metagpt/test_config.py | 6 +----- tests/metagpt/test_role.py | 14 +++++++------- 19 files changed, 37 insertions(+), 36 deletions(-) diff --git a/metagpt/actions/rebuild_sequence_view.py b/metagpt/actions/rebuild_sequence_view.py index 8785e6245..b701e66de 100644 --- a/metagpt/actions/rebuild_sequence_view.py +++ b/metagpt/actions/rebuild_sequence_view.py @@ -12,7 +12,9 @@ from pathlib import Path from typing import List from metagpt.actions import Action +from metagpt.config2 import config from metagpt.const import GRAPH_REPO_FILE_REPO +from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.utils.common import aread, list_files from metagpt.utils.di_graph_repository import DiGraphRepository diff --git a/metagpt/config2.py b/metagpt/config2.py index 6345c1b8c..c0991a6a0 100644 --- a/metagpt/config2.py +++ b/metagpt/config2.py @@ -75,8 +75,8 @@ class Config(CLIParams, YamlModel): puppeteer_config: str = "" pyppeteer_executable_path: str = "" IFLYTEK_APP_ID: str = "" - IFLYTEK_APP_SECRET: str = "" - IFLYTEK_APP_KEY: str = "" + IFLYTEK_API_SECRET: str = "" + IFLYTEK_API_KEY: str = "" AZURE_TTS_SUBSCRIPTION_KEY: str = "" AZURE_TTS_REGION: str = "" mermaid_engine: str = "nodejs" diff --git a/metagpt/subscription.py b/metagpt/subscription.py index e2b0916ac..d225a5d87 100644 --- a/metagpt/subscription.py +++ b/metagpt/subscription.py @@ -13,7 +13,7 @@ class SubscriptionRunner(BaseModel): Example: >>> import asyncio - >>> from metagpt.subscription import SubscriptionRunner + >>> from metagpt.address import SubscriptionRunner >>> from metagpt.roles import Searcher >>> from metagpt.schema import Message diff --git a/tests/metagpt/actions/test_debug_error.py b/tests/metagpt/actions/test_debug_error.py index 922aa8613..2e57a95c9 100644 --- a/tests/metagpt/actions/test_debug_error.py +++ b/tests/metagpt/actions/test_debug_error.py @@ -144,7 +144,7 @@ async def test_debug_error(): await repo.save_file( filename=ctx.output_filename, content=output_data.model_dump_json(), relative_path=TEST_OUTPUTS_FILE_REPO ) - debug_error = DebugError(context=ctx) + debug_error = DebugError(i_context=ctx) rsp = await debug_error.run() diff --git a/tests/metagpt/actions/test_prepare_documents.py b/tests/metagpt/actions/test_prepare_documents.py index fde971f3c..317683113 100644 --- a/tests/metagpt/actions/test_prepare_documents.py +++ b/tests/metagpt/actions/test_prepare_documents.py @@ -22,7 +22,7 @@ async def test_prepare_documents(): CONTEXT.git_repo.delete_repository() CONTEXT.git_repo = None - await PrepareDocuments(g_context=CONTEXT).run(with_messages=[msg]) + await PrepareDocuments(context=CONTEXT).run(with_messages=[msg]) assert CONTEXT.git_repo doc = await CONTEXT.file_repo.get_file(filename=REQUIREMENT_FILENAME, relative_path=DOCS_FILE_REPO) assert doc diff --git a/tests/metagpt/actions/test_rebuild_class_view.py b/tests/metagpt/actions/test_rebuild_class_view.py index cc23cc8dc..94295fd55 100644 --- a/tests/metagpt/actions/test_rebuild_class_view.py +++ b/tests/metagpt/actions/test_rebuild_class_view.py @@ -12,13 +12,14 @@ import pytest from metagpt.actions.rebuild_class_view import RebuildClassView from metagpt.const import GRAPH_REPO_FILE_REPO +from metagpt.context import CONTEXT from metagpt.llm import LLM @pytest.mark.asyncio async def test_rebuild(): action = RebuildClassView( - name="RedBean", context=str(Path(__file__).parent.parent.parent.parent / "metagpt"), llm=LLM() + name="RedBean", i_context=str(Path(__file__).parent.parent.parent.parent / "metagpt"), llm=LLM() ) await action.run() graph_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=GRAPH_REPO_FILE_REPO) diff --git a/tests/metagpt/actions/test_rebuild_sequence_view.py b/tests/metagpt/actions/test_rebuild_sequence_view.py index 62f64b666..8c515d976 100644 --- a/tests/metagpt/actions/test_rebuild_sequence_view.py +++ b/tests/metagpt/actions/test_rebuild_sequence_view.py @@ -11,6 +11,7 @@ import pytest from metagpt.actions.rebuild_sequence_view import RebuildSequenceView from metagpt.const import GRAPH_REPO_FILE_REPO +from metagpt.context import CONTEXT from metagpt.llm import LLM from metagpt.utils.common import aread from metagpt.utils.file_repository import FileRepository @@ -31,7 +32,7 @@ async def test_rebuild(): CONTEXT.git_repo.commit("commit1") action = RebuildSequenceView( - name="RedBean", context=str(Path(__file__).parent.parent.parent.parent / "metagpt"), llm=LLM() + name="RedBean", i_context=str(Path(__file__).parent.parent.parent.parent / "metagpt"), llm=LLM() ) await action.run() graph_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=GRAPH_REPO_FILE_REPO) diff --git a/tests/metagpt/actions/test_run_code.py b/tests/metagpt/actions/test_run_code.py index ad08b5738..76397734d 100644 --- a/tests/metagpt/actions/test_run_code.py +++ b/tests/metagpt/actions/test_run_code.py @@ -26,12 +26,12 @@ async def test_run_text(): @pytest.mark.asyncio async def test_run_script(): # Successful command - out, err = await RunCode.run_script(".", command=["echo", "Hello World"]) + out, err = await RunCode().run_script(".", command=["echo", "Hello World"]) assert out.strip() == "Hello World" assert err == "" # Unsuccessful command - out, err = await RunCode.run_script(".", command=["python", "-c", "print(1/0)"]) + out, err = await RunCode().run_script(".", command=["python", "-c", "print(1/0)"]) assert "ZeroDivisionError" in err @@ -61,5 +61,5 @@ async def test_run(): ), ] for ctx, result in inputs: - rsp = await RunCode(context=ctx).run() + rsp = await RunCode(i_context=ctx).run() assert result in rsp.summary diff --git a/tests/metagpt/actions/test_summarize_code.py b/tests/metagpt/actions/test_summarize_code.py index 081636a21..b617b59ae 100644 --- a/tests/metagpt/actions/test_summarize_code.py +++ b/tests/metagpt/actions/test_summarize_code.py @@ -188,7 +188,7 @@ async def test_summarize_code(): src_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=CONTEXT.src_workspace) all_files = src_file_repo.all_files ctx = CodeSummarizeContext(design_filename="1.json", task_filename="1.json", codes_filenames=all_files) - action = SummarizeCode(context=ctx) + action = SummarizeCode(i_context=ctx) rsp = await action.run() assert rsp logger.info(rsp) diff --git a/tests/metagpt/actions/test_talk_action.py b/tests/metagpt/actions/test_talk_action.py index 6d01dcc3f..b722d7c40 100644 --- a/tests/metagpt/actions/test_talk_action.py +++ b/tests/metagpt/actions/test_talk_action.py @@ -9,7 +9,7 @@ import pytest from metagpt.actions.talk_action import TalkAction -from metagpt.context import Context +from metagpt.context import CONTEXT from metagpt.schema import Message @@ -35,11 +35,10 @@ from metagpt.schema import Message ) async def test_prompt(agent_description, language, context, knowledge, history_summary): # Prerequisites - g_context = Context() - g_context.kwargs["agent_description"] = agent_description - g_context.kwargs["language"] = language + CONTEXT.kwargs.agent_description = agent_description + CONTEXT.kwargs.language = language - action = TalkAction(context=context, knowledge=knowledge, history_summary=history_summary) + action = TalkAction(i_context=context, knowledge=knowledge, history_summary=history_summary) assert "{" not in action.prompt assert "{" not in action.prompt_gpt4 diff --git a/tests/metagpt/actions/test_write_code_review.py b/tests/metagpt/actions/test_write_code_review.py index 3343b42b4..951929b76 100644 --- a/tests/metagpt/actions/test_write_code_review.py +++ b/tests/metagpt/actions/test_write_code_review.py @@ -21,7 +21,7 @@ def add(a, b): filename="math.py", design_doc=Document(content="编写一个从a加b的函数，返回a+b"), code_doc=Document(content=code) ) - context = await WriteCodeReview(context=context).run() + context = await WriteCodeReview(i_context=context).run() # 我们不能精确地预测生成的代码评审，但我们可以检查返回的是否为字符串 assert isinstance(context.code_doc.content, str) diff --git a/tests/metagpt/actions/test_write_prd.py b/tests/metagpt/actions/test_write_prd.py index faa5b77a4..1a897ac2e 100644 --- a/tests/metagpt/actions/test_write_prd.py +++ b/tests/metagpt/actions/test_write_prd.py @@ -16,14 +16,14 @@ from metagpt.roles.product_manager import ProductManager from metagpt.roles.role import RoleReactMode from metagpt.schema import Message from metagpt.utils.common import any_to_str -from metagpt.utils.file_repository import FileRepository @pytest.mark.asyncio async def test_write_prd(new_filename): product_manager = ProductManager() requirements = "开发一个基于大语言模型与私有知识库的搜索引擎，希望可以基于大语言模型进行搜索总结" - await FileRepository.save_file(filename=REQUIREMENT_FILENAME, content=requirements, relative_path=DOCS_FILE_REPO) + repo = CONTEXT.file_repo + await repo.save_file(filename=REQUIREMENT_FILENAME, content=requirements, relative_path=DOCS_FILE_REPO) product_manager.rc.react_mode = RoleReactMode.BY_ORDER prd = await product_manager.run(Message(content=requirements, cause_by=UserRequirement)) assert prd.cause_by == any_to_str(WritePRD) diff --git a/tests/metagpt/actions/test_write_teaching_plan.py b/tests/metagpt/actions/test_write_teaching_plan.py index 57a4f5eb0..3d556ab92 100644 --- a/tests/metagpt/actions/test_write_teaching_plan.py +++ b/tests/metagpt/actions/test_write_teaching_plan.py @@ -17,7 +17,7 @@ from metagpt.actions.write_teaching_plan import WriteTeachingPlanPart [("Title", "Lesson 1: Learn to draw an apple."), ("Teaching Content", "Lesson 1: Learn to draw an apple.")], ) async def test_write_teaching_plan_part(topic, context): - action = WriteTeachingPlanPart(topic=topic, context=context) + action = WriteTeachingPlanPart(topic=topic, i_context=context) rsp = await action.run() assert rsp diff --git a/tests/metagpt/actions/test_write_test.py b/tests/metagpt/actions/test_write_test.py index 9649b9abb..e09038414 100644 --- a/tests/metagpt/actions/test_write_test.py +++ b/tests/metagpt/actions/test_write_test.py @@ -26,7 +26,7 @@ async def test_write_test(): self.position = (random.randint(1, max_y - 1), random.randint(1, max_x - 1)) """ context = TestingContext(filename="food.py", code_doc=Document(filename="food.py", content=code)) - write_test = WriteTest(context=context) + write_test = WriteTest(i_context=context) context = await write_test.run() logger.info(context.model_dump_json()) diff --git a/tests/metagpt/learn/test_text_to_image.py b/tests/metagpt/learn/test_text_to_image.py index 2c43297c2..7c133149d 100644 --- a/tests/metagpt/learn/test_text_to_image.py +++ b/tests/metagpt/learn/test_text_to_image.py @@ -27,7 +27,9 @@ async def test_text_to_image(mocker): config = Config.default() assert config.METAGPT_TEXT_TO_IMAGE_MODEL_URL - data = await text_to_image("Panda emoji", size_type="512x512", model_url=config.METAGPT_TEXT_TO_IMAGE_MODEL_URL) + data = await text_to_image( + "Panda emoji", size_type="512x512", model_url=config.METAGPT_TEXT_TO_IMAGE_MODEL_URL, config=config + ) assert "base64" in data or "http" in data diff --git a/tests/metagpt/serialize_deserialize/test_write_code.py b/tests/metagpt/serialize_deserialize/test_write_code.py index 12dc49c3b..132f343bc 100644 --- a/tests/metagpt/serialize_deserialize/test_write_code.py +++ b/tests/metagpt/serialize_deserialize/test_write_code.py @@ -22,7 +22,7 @@ async def test_write_code_serdeser(): filename="test_code.py", design_doc=Document(content="write add function to calculate two numbers") ) doc = Document(content=context.model_dump_json()) - action = WriteCode(context=doc) + action = WriteCode(i_context=doc) serialized_data = action.model_dump() new_action = WriteCode(**serialized_data) diff --git a/tests/metagpt/serialize_deserialize/test_write_code_review.py b/tests/metagpt/serialize_deserialize/test_write_code_review.py index d1a9bff24..70a4f2077 100644 --- a/tests/metagpt/serialize_deserialize/test_write_code_review.py +++ b/tests/metagpt/serialize_deserialize/test_write_code_review.py @@ -20,7 +20,7 @@ def div(a: int, b: int = 0): code_doc=Document(content=code_content), ) - action = WriteCodeReview(context=context) + action = WriteCodeReview(i_context=context) serialized_data = action.model_dump() assert serialized_data["name"] == "WriteCodeReview" diff --git a/tests/metagpt/test_config.py b/tests/metagpt/test_config.py index cfde7a04c..c804702dd 100644 --- a/tests/metagpt/test_config.py +++ b/tests/metagpt/test_config.py @@ -7,7 +7,7 @@ """ from pydantic import BaseModel -from metagpt.config2 import Config, config +from metagpt.config2 import Config from metagpt.configs.llm_config import LLMType from metagpt.context import ContextMixin from tests.metagpt.provider.mock_llm_config import mock_llm_config @@ -20,10 +20,6 @@ def test_config_1(): assert llm.api_type == LLMType.OPENAI -def test_config_2(): - assert config == Config.default() - - def test_config_from_dict(): cfg = Config(llm={"default": mock_llm_config}) assert cfg diff --git a/tests/metagpt/test_role.py b/tests/metagpt/test_role.py index 351ba9051..20a366db8 100644 --- a/tests/metagpt/test_role.py +++ b/tests/metagpt/test_role.py @@ -38,11 +38,11 @@ class MockRole(Role): def test_basic(): mock_role = MockRole() - assert mock_role.subscription == {"tests.metagpt.test_role.MockRole"} + assert mock_role.addresses == ({"tests.metagpt.test_role.MockRole"}) assert mock_role.rc.watch == {"metagpt.actions.add_requirement.UserRequirement"} mock_role = MockRole(name="mock_role") - assert mock_role.subscription == {"tests.metagpt.test_role.MockRole", "mock_role"} + assert mock_role.addresses == {"tests.metagpt.test_role.MockRole", "mock_role"} @pytest.mark.asyncio @@ -53,7 +53,7 @@ async def test_react(): goal: str constraints: str desc: str - subscription: str + address: str inputs = [ { @@ -71,7 +71,7 @@ async def test_react(): role = MockRole( name=seed.name, profile=seed.profile, goal=seed.goal, constraints=seed.constraints, desc=seed.desc ) - role.subscribe({seed.subscription}) + role.set_addresses({seed.address}) assert role.rc.watch == {any_to_str(UserRequirement)} assert role.name == seed.name assert role.profile == seed.profile @@ -81,13 +81,13 @@ async def test_react(): assert role.is_idle env = Environment() env.add_role(role) - assert env.get_subscription(role) == {seed.subscription} - env.publish_message(Message(content="test", msg_to=seed.subscription)) + assert env.get_addresses(role) == {seed.address} + env.publish_message(Message(content="test", msg_to=seed.address)) assert not role.is_idle while not env.is_idle: await env.run() assert role.is_idle - env.publish_message(Message(content="test", cause_by=seed.subscription)) + env.publish_message(Message(content="test", cause_by=seed.address)) assert not role.is_idle while not env.is_idle: await env.run() From 60969b6aed1a868e6d9f8445c7ba7ecf04e07289 Mon Sep 17 00:00:00 2001 From: geekan Date: Wed, 10 Jan 2024 22:02:44 +0800 Subject: [PATCH 47/61] fix bugs --- examples/example.pkl | Bin 624 -> 624 bytes metagpt/actions/debug_error.py | 2 +- metagpt/actions/research.py | 2 +- metagpt/actions/talk_action.py | 6 +++--- metagpt/roles/product_manager.py | 2 +- metagpt/roles/qa_engineer.py | 5 ----- metagpt/tools/search_engine.py | 2 +- metagpt/tools/ut_writer.py | 3 ++- metagpt/tools/web_browser_engine.py | 2 +- tests/conftest.py | 3 ++- tests/data/rsp_cache.json | 14 +++++++++++++- .../actions/test_rebuild_sequence_view.py | 4 ++-- tests/metagpt/test_role.py | 8 ++++---- tests/metagpt/test_schema.py | 2 +- tests/metagpt/utils/test_redis.py | 2 +- 15 files changed, 33 insertions(+), 24 deletions(-) diff --git a/examples/example.pkl b/examples/example.pkl index f706fd803328b14547ee12efb4cf90f9fd2be99c..94e0fe63b7128ac56fa5d3ebd823c2f7d07dafa0 100644 GIT binary patch delta 88 zcmWN{%ME}a3;@uOFbdZuwv^v2o`kk*xPplbxPqHF3M0tno!<1*UwdG|F)Saj2@7zu n4!tK`AeJbVvD$lr3x%|ZQ3B~1ffegIl%bi`NUAE0?$13xtmqn% delta 88 zcmWN@O$~rB3 Message: msg, format_msgs, system_msgs = self.aask_args diff --git a/metagpt/roles/product_manager.py b/metagpt/roles/product_manager.py index ec80d7bb0..fbe139a99 100644 --- a/metagpt/roles/product_manager.py +++ b/metagpt/roles/product_manager.py @@ -43,7 +43,7 @@ class ProductManager(Role): self._set_state(1) else: self._set_state(0) - self.context.config.git_reinit = False + self.config.git_reinit = False self.todo_action = any_to_name(WritePRD) return bool(self.rc.todo) diff --git a/metagpt/roles/qa_engineer.py b/metagpt/roles/qa_engineer.py index 783fde9b6..cd043b551 100644 --- a/metagpt/roles/qa_engineer.py +++ b/metagpt/roles/qa_engineer.py @@ -17,7 +17,6 @@ from metagpt.actions import DebugError, RunCode, WriteTest from metagpt.actions.summarize_code import SummarizeCode -from metagpt.config2 import Config from metagpt.const import ( MESSAGE_ROUTE_TO_NONE, TEST_CODES_FILE_REPO, @@ -48,10 +47,6 @@ class QaEngineer(Role): self._watch([SummarizeCode, WriteTest, RunCode, DebugError]) self.test_round = 0 - @property - def config(self) -> Config: - return self.context.config - async def _write_test(self, message: Message) -> None: src_file_repo = self.context.git_repo.new_file_repository(self.context.src_workspace) changed_files = set(src_file_repo.changed_files.keys()) diff --git a/metagpt/tools/search_engine.py b/metagpt/tools/search_engine.py index fd237d537..4111dd106 100644 --- a/metagpt/tools/search_engine.py +++ b/metagpt/tools/search_engine.py @@ -42,7 +42,7 @@ class SearchEngine: def __init__( self, - engine: Optional[SearchEngineType] = None, + engine: Optional[SearchEngineType] = SearchEngineType.SERPER_GOOGLE, run_func: Callable[[str, int, bool], Coroutine[None, None, Union[str, list[str]]]] = None, ): if engine == SearchEngineType.SERPAPI_GOOGLE: diff --git a/metagpt/tools/ut_writer.py b/metagpt/tools/ut_writer.py index f2f2bf51c..a155c27ab 100644 --- a/metagpt/tools/ut_writer.py +++ b/metagpt/tools/ut_writer.py @@ -4,6 +4,7 @@ import json from pathlib import Path +from metagpt.config2 import config from metagpt.provider.openai_api import OpenAILLM as GPTAPI from metagpt.utils.common import awrite @@ -281,6 +282,6 @@ class UTGenerator: """Choose based on different calling methods""" result = "" if self.chatgpt_method == "API": - result = await GPTAPI().aask_code(messages=messages) + result = await GPTAPI(config.get_llm_config()).aask_code(messages=messages) return result diff --git a/metagpt/tools/web_browser_engine.py b/metagpt/tools/web_browser_engine.py index 3493a5398..ff1f46a36 100644 --- a/metagpt/tools/web_browser_engine.py +++ b/metagpt/tools/web_browser_engine.py @@ -15,7 +15,7 @@ from metagpt.utils.parse_html import WebPage class WebBrowserEngine: def __init__( self, - engine: WebBrowserEngineType | None = None, + engine: WebBrowserEngineType | None = WebBrowserEngineType.PLAYWRIGHT, run_func: Callable[..., Coroutine[Any, Any, WebPage | list[WebPage]]] | None = None, ): if engine is None: diff --git a/tests/conftest.py b/tests/conftest.py index faa2d92e9..9ad05e1a0 100644 --- a/tests/conftest.py +++ b/tests/conftest.py @@ -146,7 +146,8 @@ def setup_and_teardown_git_repo(request): # Destroy git repo at the end of the test session. def fin(): - CONTEXT.git_repo.delete_repository() + if CONTEXT.git_repo: + CONTEXT.git_repo.delete_repository() # Register the function for destroying the environment. request.addfinalizer(fin) diff --git a/tests/data/rsp_cache.json b/tests/data/rsp_cache.json index 0ed13593e..b173c789b 100644 --- a/tests/data/rsp_cache.json +++ b/tests/data/rsp_cache.json @@ -154,5 +154,17 @@ "Do not refer to the context of the previous conversation records, start the conversation anew.\n\nFormation: \"Capacity and role\" defines the role you are currently playing;\n\t\"[LESSON_BEGIN]\" and \"[LESSON_END]\" tags enclose the content of textbook;\n\t\"Statement\" defines the work detail you need to complete at this stage;\n\t\"Answer options\" defines the format requirements for your responses;\n\t\"Constraint\" defines the conditions that your responses must comply with.\n\nCapacity and role: You are a {teaching_language} Teacher, named Lily, your goal is writing a {language} teaching plan part by part. the constraint is writing in {language}. \nStatement: Write the \"Choice Questions\" part of teaching plan, WITHOUT ANY content unrelated to \"Choice Questions\"!!\nStatement: Based on the content of the textbook enclosed by \"[LESSON_BEGIN]\" and \"[LESSON_END]\", create choice questions. 10 questions.\nAnswer options: Enclose the teaching plan content with \"[TEACHING_PLAN_BEGIN]\" and \"[TEACHING_PLAN_END]\" tags.\nAnswer options: Using proper markdown format from second-level header format.\nConstraint: Writing in Chinese.\n[LESSON_BEGIN]\n\n UNIT 1 Making New Friends\n TOPIC 1 Welcome to China!\n Section A\n\n 1a Listen and number the following names.\n Jane Mari Kangkang Michael\n Look, listen and understand. Then practice the conversation.\n Work in groups. Introduce yourself using\n I ’m ... Then practice 1a\n with your own hometown or the following places.\n\n 1b Listen and number the following names\n Jane Michael Maria Kangkang\n 1c Work in groups. Introduce yourself using I ’m ... Then practice 1a with your own hometown or the following places.\n China the USA the UK Hong Kong Beijing\n\n 2a Look, listen and understand. Then practice the conversation\n Hello! \n Hello! \n Hello! \n Hello! Are you Maria? \n No, I’m not. I’m Jane.\n Oh, nice to meet you, Jane\n Nice to meet you, too.\n Hi, Maria!\n Hi, Kangkang!\n Welcome to China!\n Thanks.\n\n 2b Work in groups. Make up a conversation with your own name and the\n following structures.\n A: Hello! / Good morning! / Hi! I’m ... Are you ... ?\n B: ...\n\n 3a Listen, say and trace\n Aa Bb Cc Dd Ee Ff Gg\n\n 3b Listen and number the following letters. Then circle the letters with the same sound as Bb.\n Aa Bb Cc Dd Ee Ff Gg\n\n 3c Match the big letters with the small ones. Then write them on the lines.\n \n[LESSON_END]": "[TEACHING_PLAN_BEGIN]\n\n## 选择题\n\n1. 在1a部分，听到的名字按顺序应该是？\n - A. Jane B. Mari C. Kangkang D. Michael\n\n2. 在1b部分，听到的名字按顺序应该是？\n - A. Jane B. Michael C. Maria D. Kangkang\n\n3. 在2a部分，对话中提到了哪些地方？\n - A. 中国 B. 美国 C. 英国 D. 香港\n\n4. 在3b部分，与Bb发音相同的字母是？\n - A. Aa B. Cc C. Dd D. Gg\n\n5. 在3c部分，大写字母和小写字母的正确匹配是？\n - A. Aa - a B. Bb - b C. Cc - c D. Dd - d\n\n6. 在1a部分，听到的名字按顺序应该是？\n - A. Jane B. Mari C. Kangkang D. Michael\n\n7. 在1b部分，听到的名字按顺序应该是？\n - A. Jane B. Michael C. Maria D. Kangkang\n\n8. 在2a部分，对话中提到了哪些地方？\n - A. 中国 B. 美国 C. 英国 D. 香港\n\n9. 在3b部分，与Bb发音相同的字母是？\n - A. Aa B. Cc C. Dd D. Gg\n\n10. 在3c部分，大写字母和小写字母的正确匹配是？\n - A. Aa - a B. Bb - b C. Cc - c D. Dd - d\n\n[TEACHING_PLAN_END]", "Do not refer to the context of the previous conversation records, start the conversation anew.\n\nFormation: \"Capacity and role\" defines the role you are currently playing;\n\t\"[LESSON_BEGIN]\" and \"[LESSON_END]\" tags enclose the content of textbook;\n\t\"Statement\" defines the work detail you need to complete at this stage;\n\t\"Answer options\" defines the format requirements for your responses;\n\t\"Constraint\" defines the conditions that your responses must comply with.\n\nCapacity and role: You are a {teaching_language} Teacher, named Lily, your goal is writing a {language} teaching plan part by part. the constraint is writing in {language}. \nStatement: Write the \"Grammar Questions\" part of teaching plan, WITHOUT ANY content unrelated to \"Grammar Questions\"!!\nStatement: Based on the content of the textbook enclosed by \"[LESSON_BEGIN]\" and \"[LESSON_END]\", create grammar questions. 10 questions.\nAnswer options: Enclose the teaching plan content with \"[TEACHING_PLAN_BEGIN]\" and \"[TEACHING_PLAN_END]\" tags.\nAnswer options: Using proper markdown format from second-level header format.\nConstraint: Writing in Chinese.\n[LESSON_BEGIN]\n\n UNIT 1 Making New Friends\n TOPIC 1 Welcome to China!\n Section A\n\n 1a Listen and number the following names.\n Jane Mari Kangkang Michael\n Look, listen and understand. Then practice the conversation.\n Work in groups. Introduce yourself using\n I ’m ... Then practice 1a\n with your own hometown or the following places.\n\n 1b Listen and number the following names\n Jane Michael Maria Kangkang\n 1c Work in groups. Introduce yourself using I ’m ... Then practice 1a with your own hometown or the following places.\n China the USA the UK Hong Kong Beijing\n\n 2a Look, listen and understand. Then practice the conversation\n Hello! \n Hello! \n Hello! \n Hello! Are you Maria? \n No, I’m not. I’m Jane.\n Oh, nice to meet you, Jane\n Nice to meet you, too.\n Hi, Maria!\n Hi, Kangkang!\n Welcome to China!\n Thanks.\n\n 2b Work in groups. Make up a conversation with your own name and the\n following structures.\n A: Hello! / Good morning! / Hi! I’m ... Are you ... ?\n B: ...\n\n 3a Listen, say and trace\n Aa Bb Cc Dd Ee Ff Gg\n\n 3b Listen and number the following letters. Then circle the letters with the same sound as Bb.\n Aa Bb Cc Dd Ee Ff Gg\n\n 3c Match the big letters with the small ones. Then write them on the lines.\n \n[LESSON_END]": "[TEACHING_PLAN_BEGIN]\n\n## Grammar Questions\n\n1. 请问在1a中，学生需要做什么？\n2. 请问在1b中，学生需要做什么？\n3. 请问在2a中，学生需要做什么？\n4. 请问在2b中，学生需要做什么？\n5. 请问在3a中，学生需要做什么？\n6. 请问在3b中，学生需要做什么？\n7. 请问在3c中，学生需要做什么？\n8. 请问在1a中，学生需要听什么？\n9. 请问在2a中，学生需要看什么？\n10. 请问在3a中，学生需要说什么？\n\n[TEACHING_PLAN_END]", "Do not refer to the context of the previous conversation records, start the conversation anew.\n\nFormation: \"Capacity and role\" defines the role you are currently playing;\n\t\"[LESSON_BEGIN]\" and \"[LESSON_END]\" tags enclose the content of textbook;\n\t\"Statement\" defines the work detail you need to complete at this stage;\n\t\"Answer options\" defines the format requirements for your responses;\n\t\"Constraint\" defines the conditions that your responses must comply with.\n\nCapacity and role: You are a {teaching_language} Teacher, named Lily, your goal is writing a {language} teaching plan part by part. the constraint is writing in {language}. \nStatement: Write the \"Translation Questions\" part of teaching plan, WITHOUT ANY content unrelated to \"Translation Questions\"!!\nStatement: Based on the content of the textbook enclosed by \"[LESSON_BEGIN]\" and \"[LESSON_END]\", create translation questions. The translation should include 10 {language} questions with {teaching_language} answers, and it should also include 10 {teaching_language} questions with {language} answers.\nAnswer options: Enclose the teaching plan content with \"[TEACHING_PLAN_BEGIN]\" and \"[TEACHING_PLAN_END]\" tags.\nAnswer options: Using proper markdown format from second-level header format.\nConstraint: Writing in Chinese.\n[LESSON_BEGIN]\n\n UNIT 1 Making New Friends\n TOPIC 1 Welcome to China!\n Section A\n\n 1a Listen and number the following names.\n Jane Mari Kangkang Michael\n Look, listen and understand. Then practice the conversation.\n Work in groups. Introduce yourself using\n I ’m ... Then practice 1a\n with your own hometown or the following places.\n\n 1b Listen and number the following names\n Jane Michael Maria Kangkang\n 1c Work in groups. Introduce yourself using I ’m ... Then practice 1a with your own hometown or the following places.\n China the USA the UK Hong Kong Beijing\n\n 2a Look, listen and understand. Then practice the conversation\n Hello! \n Hello! \n Hello! \n Hello! Are you Maria? \n No, I’m not. I’m Jane.\n Oh, nice to meet you, Jane\n Nice to meet you, too.\n Hi, Maria!\n Hi, Kangkang!\n Welcome to China!\n Thanks.\n\n 2b Work in groups. Make up a conversation with your own name and the\n following structures.\n A: Hello! / Good morning! / Hi! I’m ... Are you ... ?\n B: ...\n\n 3a Listen, say and trace\n Aa Bb Cc Dd Ee Ff Gg\n\n 3b Listen and number the following letters. Then circle the letters with the same sound as Bb.\n Aa Bb Cc Dd Ee Ff Gg\n\n 3c Match the big letters with the small ones. Then write them on the lines.\n \n[LESSON_END]": "[TEACHING_PLAN_BEGIN]\n\n## Translation Questions\n\n### {language} Questions with {teaching_language} Answers\n1. 你能听懂这些名字吗？ (Can you understand these names?)\n - 能，我能听懂。 (Yes, I can understand.)\n2. 请用“我是...”介绍一下你自己。 (Please introduce yourself using \"I am...\")\n - 我是... (I am...)\n3. 你能用这些结构编一个对话吗？ (Can you make up a conversation with these structures?)\n - 能，我能编一个对话。 (Yes, I can make up a conversation.)\n4. 你能说出这些字母的名字吗？ (Can you say the names of these letters?)\n - 能，我能说出来。 (Yes, I can say them.)\n5. 你能把大写字母和小写字母配对吗？ (Can you match the uppercase letters with the lowercase letters?)\n - 能，我能配对。 (Yes, I can match them.)\n\n### {teaching_language} Questions with {language} Answers\n1. Can you understand these names?\n - Yes, I can understand.\n2. Please introduce yourself using \"I am...\"\n - I am...\n3. Can you make up a conversation with these structures?\n - Yes, I can make up a conversation.\n4. Can you say the names of these letters?\n - Yes, I can say them.\n5. Can you match the uppercase letters with the lowercase letters?\n - Yes, I can match them.\n\n[TEACHING_PLAN_END]", - "The given text repeatedly describes Lily as a girl. It emphasizes that Lily is a girl multiple times. The content consistently refers to Lily as a girl.\nTranslate the above summary into a English title of less than 5 words.": "\"Emphasizing Lily's Gender\"" + "The given text repeatedly describes Lily as a girl. It emphasizes that Lily is a girl multiple times. The content consistently refers to Lily as a girl.\nTranslate the above summary into a English title of less than 5 words.": "\"Emphasizing Lily's Gender\"", + "\n## context\n\n### Project Name\n20240110212347\n\n### Original Requirements\n['需要一个基于LLM做总结的搜索引擎']\n\n### Search Information\n-\n\n\n-----\n\n## format example\n[CONTENT]\n{\n \"Language\": \"en_us\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"Create a 2048 game\",\n \"Product Goals\": [\n \"Create an engaging user experience\",\n \"Improve accessibility, be responsive\",\n \"More beautiful UI\"\n ],\n \"User Stories\": [\n \"As a player, I want to be able to choose difficulty levels\",\n \"As a player, I want to see my score after each game\",\n \"As a player, I want to get restart button when I lose\",\n \"As a player, I want to see beautiful UI that make me feel good\",\n \"As a player, I want to play game via mobile phone\"\n ],\n \"Competitive Analysis\": [\n \"2048 Game A: Simple interface, lacks responsive features\",\n \"play2048.co: Beautiful and responsive UI with my best score shown\",\n \"2048game.com: Responsive UI with my best score shown, but many ads\"\n ],\n \"Competitive Quadrant Chart\": \"quadrantChart\\n title \\\"Reach and engagement of campaigns\\\"\\n x-axis \\\"Low Reach\\\" --> \\\"High Reach\\\"\\n y-axis \\\"Low Engagement\\\" --> \\\"High Engagement\\\"\\n quadrant-1 \\\"We should expand\\\"\\n quadrant-2 \\\"Need to promote\\\"\\n quadrant-3 \\\"Re-evaluate\\\"\\n quadrant-4 \\\"May be improved\\\"\\n \\\"Campaign A\\\": [0.3, 0.6]\\n \\\"Campaign B\\\": [0.45, 0.23]\\n \\\"Campaign C\\\": [0.57, 0.69]\\n \\\"Campaign D\\\": [0.78, 0.34]\\n \\\"Campaign E\\\": [0.40, 0.34]\\n \\\"Campaign F\\\": [0.35, 0.78]\\n \\\"Our Target Product\\\": [0.5, 0.6]\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [\n [\n \"P0\",\n \"The main code ...\"\n ],\n [\n \"P0\",\n \"The game algorithm ...\"\n ]\n ],\n \"UI Design draft\": \"Basic function description with a simple style and layout.\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]\n\n## nodes: \": # \"\n- Language: # Provide the language used in the project, typically matching the user's requirement language.\n- Programming Language: # Python/JavaScript or other mainstream programming language.\n- Original Requirements: # Place the original user's requirements here.\n- Product Goals: typing.List[str] # Provide up to three clear, orthogonal product goals.\n- User Stories: typing.List[str] # Provide up to 3 to 5 scenario-based user stories.\n- Competitive Analysis: typing.List[str] # Provide 5 to 7 competitive products.\n- Competitive Quadrant Chart: # Use mermaid quadrantChart syntax. Distribute scores evenly between 0 and 1\n- Requirement Analysis: # Provide a detailed analysis of the requirements.\n- Requirement Pool: typing.List[typing.List[str]] # List down the top-5 requirements with their priority (P0, P1, P2).\n- UI Design draft: # Provide a simple description of UI elements, functions, style, and layout.\n- Anything UNCLEAR: # Mention any aspects of the project that are unclear and try to clarify them.\n\n\n## constraint\nLanguage: Please use the same language as Human INPUT.\nFormat: output wrapped inside [CONTENT][/CONTENT] like format example, nothing else.\n\n## action\nFollow instructions of nodes, generate output and make sure it follows the format example.\n": "[CONTENT]\n{\n \"Language\": \"zh_cn\",\n \"Programming Language\": \"LLM\",\n \"Original Requirements\": \"需要一个基于LLM做总结的搜索引擎\",\n \"Product Goals\": [],\n \"User Stories\": [],\n \"Competitive Analysis\": [],\n \"Competitive Quadrant Chart\": \"\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [],\n \"UI Design draft\": \"\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]", + "\n## context\n\n### Project Name\n20240101\n\n### Original Requirements\n['Make a cli snake game']\n\n### Search Information\n-\n\n\n-----\n\n## format example\n[CONTENT]\n{\n \"Language\": \"en_us\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"Create a 2048 game\",\n \"Product Goals\": [\n \"Create an engaging user experience\",\n \"Improve accessibility, be responsive\",\n \"More beautiful UI\"\n ],\n \"User Stories\": [\n \"As a player, I want to be able to choose difficulty levels\",\n \"As a player, I want to see my score after each game\",\n \"As a player, I want to get restart button when I lose\",\n \"As a player, I want to see beautiful UI that make me feel good\",\n \"As a player, I want to play game via mobile phone\"\n ],\n \"Competitive Analysis\": [\n \"2048 Game A: Simple interface, lacks responsive features\",\n \"play2048.co: Beautiful and responsive UI with my best score shown\",\n \"2048game.com: Responsive UI with my best score shown, but many ads\"\n ],\n \"Competitive Quadrant Chart\": \"quadrantChart\\n title \\\"Reach and engagement of campaigns\\\"\\n x-axis \\\"Low Reach\\\" --> \\\"High Reach\\\"\\n y-axis \\\"Low Engagement\\\" --> \\\"High Engagement\\\"\\n quadrant-1 \\\"We should expand\\\"\\n quadrant-2 \\\"Need to promote\\\"\\n quadrant-3 \\\"Re-evaluate\\\"\\n quadrant-4 \\\"May be improved\\\"\\n \\\"Campaign A\\\": [0.3, 0.6]\\n \\\"Campaign B\\\": [0.45, 0.23]\\n \\\"Campaign C\\\": [0.57, 0.69]\\n \\\"Campaign D\\\": [0.78, 0.34]\\n \\\"Campaign E\\\": [0.40, 0.34]\\n \\\"Campaign F\\\": [0.35, 0.78]\\n \\\"Our Target Product\\\": [0.5, 0.6]\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [\n [\n \"P0\",\n \"The main code ...\"\n ],\n [\n \"P0\",\n \"The game algorithm ...\"\n ]\n ],\n \"UI Design draft\": \"Basic function description with a simple style and layout.\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]\n\n## nodes: \": # \"\n- Language: # Provide the language used in the project, typically matching the user's requirement language.\n- Programming Language: # Python/JavaScript or other mainstream programming language.\n- Original Requirements: # Place the original user's requirements here.\n- Product Goals: typing.List[str] # Provide up to three clear, orthogonal product goals.\n- User Stories: typing.List[str] # Provide up to 3 to 5 scenario-based user stories.\n- Competitive Analysis: typing.List[str] # Provide 5 to 7 competitive products.\n- Competitive Quadrant Chart: # Use mermaid quadrantChart syntax. Distribute scores evenly between 0 and 1\n- Requirement Analysis: # Provide a detailed analysis of the requirements.\n- Requirement Pool: typing.List[typing.List[str]] # List down the top-5 requirements with their priority (P0, P1, P2).\n- UI Design draft: # Provide a simple description of UI elements, functions, style, and layout.\n- Anything UNCLEAR: # Mention any aspects of the project that are unclear and try to clarify them.\n\n\n## constraint\nLanguage: Please use the same language as Human INPUT.\nFormat: output wrapped inside [CONTENT][/CONTENT] like format example, nothing else.\n\n## action\nFollow instructions of nodes, generate output and make sure it follows the format example.\n": "[CONTENT]\n{\n \"Language\": \"en_us\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"Make a cli snake game\",\n \"Product Goals\": [],\n \"User Stories\": [],\n \"Competitive Analysis\": [],\n \"Competitive Quadrant Chart\": \"\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [],\n \"UI Design draft\": \"\",\n \"Anything UNCLEAR\": \"Please provide more details on the product goals and user stories.\"\n}\n[/CONTENT]", + "\n## context\n{\"Language\":\"en_us\",\"Programming Language\":\"Python\",\"Original Requirements\":\"Make a cli snake game\",\"Product Goals\":[],\"User Stories\":[],\"Competitive Analysis\":[],\"Competitive Quadrant Chart\":\"\",\"Requirement Analysis\":\"\",\"Requirement Pool\":[],\"UI Design draft\":\"\",\"Anything UNCLEAR\":\"Please provide more details on the product goals and user stories.\"}\n\n-----\n\n## format example\n[CONTENT]\n{\n \"Implementation approach\": \"We will ...\",\n \"File list\": [\n \"main.py\",\n \"game.py\"\n ],\n \"Data structures and interfaces\": \"\\nclassDiagram\\n class Main {\\n -SearchEngine search_engine\\n +main() str\\n }\\n class SearchEngine {\\n -Index index\\n -Ranking ranking\\n -Summary summary\\n +search(query: str) str\\n }\\n class Index {\\n -KnowledgeBase knowledge_base\\n +create_index(data: dict)\\n +query_index(query: str) list\\n }\\n class Ranking {\\n +rank_results(results: list) list\\n }\\n class Summary {\\n +summarize_results(results: list) str\\n }\\n class KnowledgeBase {\\n +update(data: dict)\\n +fetch_data(query: str) dict\\n }\\n Main --> SearchEngine\\n SearchEngine --> Index\\n SearchEngine --> Ranking\\n SearchEngine --> Summary\\n Index --> KnowledgeBase\\n\",\n \"Program call flow\": \"\\nsequenceDiagram\\n participant M as Main\\n participant SE as SearchEngine\\n participant I as Index\\n participant R as Ranking\\n participant S as Summary\\n participant KB as KnowledgeBase\\n M->>SE: search(query)\\n SE->>I: query_index(query)\\n I->>KB: fetch_data(query)\\n KB-->>I: return data\\n I-->>SE: return results\\n SE->>R: rank_results(results)\\n R-->>SE: return ranked_results\\n SE->>S: summarize_results(ranked_results)\\n S-->>SE: return summary\\n SE-->>M: return summary\\n\",\n \"Anything UNCLEAR\": \"Clarification needed on third-party API integration, ...\"\n}\n[/CONTENT]\n\n## nodes: \": # \"\n- Implementation approach: # Analyze the difficult points of the requirements, select the appropriate open-source framework\n- File list: typing.List[str] # Only need relative paths. ALWAYS write a main.py or app.py here\n- Data structures and interfaces: # Use mermaid classDiagram code syntax, including classes, method(__init__ etc.) and functions with type annotations, CLEARLY MARK the RELATIONSHIPS between classes, and comply with PEP8 standards. The data structures SHOULD BE VERY DETAILED and the API should be comprehensive with a complete design.\n- Program call flow: # Use sequenceDiagram code syntax, COMPLETE and VERY DETAILED, using CLASSES AND API DEFINED ABOVE accurately, covering the CRUD AND INIT of each object, SYNTAX MUST BE CORRECT.\n- Anything UNCLEAR: # Mention unclear project aspects, then try to clarify it.\n\n\n## constraint\nLanguage: Please use the same language as Human INPUT.\nFormat: output wrapped inside [CONTENT][/CONTENT] like format example, nothing else.\n\n## action\nFollow instructions of nodes, generate output and make sure it follows the format example.\n": "[CONTENT]\n{\n \"Product Goals\": [\n \"Create a command-line interface (CLI) snake game\",\n \"Implement game logic for movement, collision, and scoring\",\n \"Provide a user-friendly and interactive gaming experience\"\n ],\n \"User Stories\": [\n \"As a player, I want to be able to control the snake's movement using arrow keys\",\n \"As a player, I want the game to end when the snake collides with the walls or itself\",\n \"As a player, I want to see my score displayed on the screen during and after the game\"\n ],\n \"Anything UNCLEAR\": \"Please provide more details on the specific features and functionalities expected in the snake game.\"\n}\n[/CONTENT]", + "\n## context\n{\"Implementation approach\":\"We will use Python and the curses library to create the snake game. The game logic will be implemented in a separate module, and the main.py file will handle the user interface and game loop.\",\"File list\":[\"main.py\",\"game.py\"],\"Data structures and interfaces\":\"\\nclassDiagram\\n class Game {\\n -Snake snake\\n -Food food\\n -Score score\\n +__init__(width: int, height: int)\\n +start_game()\\n +move_snake(direction: str)\\n +generate_food()\\n +update_score(points: int)\\n }\\n class Snake {\\n -body list\\n -direction str\\n +__init__(x: int, y: int)\\n +move(direction: str)\\n +grow()\\n +collides_with_self() bool\\n }\\n class Food {\\n -position tuple\\n +__init__(x: int, y: int)\\n +get_position() tuple\\n }\\n class Score {\\n -points int\\n +__init__()\\n +increase(points: int)\\n }\\n Game --> Snake\\n Game --> Food\\n Game --> Score\\n\",\"Program call flow\":\"\\nsequenceDiagram\\n participant M as Main\\n participant G as Game\\n M->>G: start_game()\\n M->>G: move_snake(direction)\\n G->>G: generate_food()\\n G->>G: update_score(points)\\n\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n-----\n\n## format example\n[CONTENT]\n{\n \"Required Python packages\": [\n \"flask==1.1.2\",\n \"bcrypt==3.2.0\"\n ],\n \"Required Other language third-party packages\": [\n \"No third-party dependencies required\"\n ],\n \"Logic Analysis\": [\n [\n \"game.py\",\n \"Contains Game class and ... functions\"\n ],\n [\n \"main.py\",\n \"Contains main function, from game import Game\"\n ]\n ],\n \"Task list\": [\n \"game.py\",\n \"main.py\"\n ],\n \"Full API spec\": \"openapi: 3.0.0 ...\",\n \"Shared Knowledge\": \"'game.py' contains functions shared across the project.\",\n \"Anything UNCLEAR\": \"Clarification needed on how to start and initialize third-party libraries.\"\n}\n[/CONTENT]\n\n## nodes: \": # \"\n- Required Python packages: typing.List[str] # Provide required Python packages in requirements.txt format.\n- Required Other language third-party packages: typing.List[str] # List down the required packages for languages other than Python.\n- Logic Analysis: typing.List[typing.List[str]] # Provide a list of files with the classes/methods/functions to be implemented, including dependency analysis and imports.\n- Task list: typing.List[str] # Break down the tasks into a list of filenames, prioritized by dependency order.\n- Full API spec: # Describe all APIs using OpenAPI 3.0 spec that may be used by both frontend and backend. If front-end and back-end communication is not required, leave it blank.\n- Shared Knowledge: # Detail any shared knowledge, like common utility functions or configuration variables.\n- Anything UNCLEAR: # Mention any unclear aspects in the project management context and try to clarify them.\n\n\n## constraint\nLanguage: Please use the same language as Human INPUT.\nFormat: output wrapped inside [CONTENT][/CONTENT] like format example, nothing else.\n\n## action\nFollow instructions of nodes, generate output and make sure it follows the format example.\n": "[CONTENT]\n{\n \"Required Python packages\": [\n \"curses==2.2.0\"\n ],\n \"Required Other language third-party packages\": [\n \"No third-party dependencies required\"\n ],\n \"Logic Analysis\": [\n [\n \"game.py\",\n \"Contains Game class and ... functions\"\n ],\n [\n \"main.py\",\n \"Contains main function, from game import Game\"\n ]\n ],\n \"Task list\": [\n \"game.py\",\n \"main.py\"\n ],\n \"Full API spec\": \"\",\n \"Shared Knowledge\": \"'game.py' contains functions shared across the project.\",\n \"Anything UNCLEAR\": \"Please provide more details on the game mechanics and user interactions.\"\n}\n[/CONTENT]", + "\nNOTICE\nRole: You are a professional engineer; the main goal is to write google-style, elegant, modular, easy to read and maintain code\nLanguage: Please use the same language as the user requirement, but the title and code should be still in English. For example, if the user speaks Chinese, the specific text of your answer should also be in Chinese.\nATTENTION: Use '##' to SPLIT SECTIONS, not '#'. Output format carefully referenced \"Format example\".\n\n# Context\n## Design\n{\"Implementation approach\":\"We will use Python and the curses library to create the snake game. The game logic will be implemented in a separate module, and the main.py file will handle the user interface and game loop.\",\"File list\":[\"main.py\",\"game.py\"],\"Data structures and interfaces\":\"\\nclassDiagram\\n class Game {\\n -Snake snake\\n -Food food\\n -Score score\\n +__init__(width: int, height: int)\\n +start_game()\\n +move_snake(direction: str)\\n +generate_food()\\n +update_score(points: int)\\n }\\n class Snake {\\n -body list\\n -direction str\\n +__init__(x: int, y: int)\\n +move(direction: str)\\n +grow()\\n +collides_with_self() bool\\n }\\n class Food {\\n -position tuple\\n +__init__(x: int, y: int)\\n +get_position() tuple\\n }\\n class Score {\\n -points int\\n +__init__()\\n +increase(points: int)\\n }\\n Game --> Snake\\n Game --> Food\\n Game --> Score\\n\",\"Program call flow\":\"\\nsequenceDiagram\\n participant M as Main\\n participant G as Game\\n M->>G: start_game()\\n M->>G: move_snake(direction)\\n G->>G: generate_food()\\n G->>G: update_score(points)\\n\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n## Tasks\n{\"Required Python packages\":[\"curses==2.2.0\"],\"Required Other language third-party packages\":[\"No third-party dependencies required\"],\"Logic Analysis\":[[\"game.py\",\"Contains Game class and ... functions\"],[\"main.py\",\"Contains main function, from game import Game\"]],\"Task list\":[\"game.py\",\"main.py\"],\"Full API spec\":\"\",\"Shared Knowledge\":\"'game.py' contains functions shared across the project.\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n## Legacy Code\n```Code\n\n```\n\n## Debug logs\n```text\n\n\n\n```\n\n## Bug Feedback logs\n```text\n\n```\n\n# Format example\n## Code: game.py\n```python\n## game.py\n...\n```\n\n# Instruction: Based on the context, follow \"Format example\", write code.\n\n## Code: game.py. Write code with triple quoto, based on the following attentions and context.\n1. Only One file: do your best to implement THIS ONLY ONE FILE.\n2. COMPLETE CODE: Your code will be part of the entire project, so please implement complete, reliable, reusable code snippets.\n3. Set default value: If there is any setting, ALWAYS SET A DEFAULT VALUE, ALWAYS USE STRONG TYPE AND EXPLICIT VARIABLE. AVOID circular import.\n4. Follow design: YOU MUST FOLLOW \"Data structures and interfaces\". DONT CHANGE ANY DESIGN. Do not use public member functions that do not exist in your design.\n5. CAREFULLY CHECK THAT YOU DONT MISS ANY NECESSARY CLASS/FUNCTION IN THIS FILE.\n6. Before using a external variable/module, make sure you import it first.\n7. Write out EVERY CODE DETAIL, DON'T LEAVE TODO.\n\n": "```python\n## game.py\n\nclass Snake:\n def __init__(self, x: int, y: int):\n self.body = [(x, y)]\n self.direction = 'right'\n\n def move(self, direction: str):\n if direction == 'up' and self.direction != 'down':\n self.direction = 'up'\n elif direction == 'down' and self.direction != 'up':\n self.direction = 'down'\n elif direction == 'left' and self.direction != 'right':\n self.direction = 'left'\n elif direction == 'right' and self.direction != 'left':\n self.direction = 'right'\n\n head = self.body[0]\n x, y = head\n if self.direction == 'up':\n new_head = (x, y - 1)\n elif self.direction == 'down':\n new_head = (x, y + 1)\n elif self.direction == 'left':\n new_head = (x - 1, y)\n elif self.direction == 'right':\n new_head = (x + 1, y)\n self.body.insert(0, new_head)\n\n def grow(self):\n tail = self.body[-1]\n x, y = tail\n if self.direction == 'up':\n new_tail = (x, y + 1)\n elif self.direction == 'down':\n new_tail = (x, y - 1)\n elif self.direction == 'left':\n new_tail = (x + 1, y)\n elif self.direction == 'right':\n new_tail = (x - 1, y)\n self.body.append(new_tail)\n\n def collides_with_self(self) -> bool:\n return len(self.body) != len(set(self.body))\n\nclass Food:\n def __init__(self, x: int, y: int):\n self.position = (x, y)\n\n def get_position(self) -> tuple:\n return self.position\n\nclass Score:\n def __init__(self):\n self.points = 0\n\n def increase(self, points: int):\n self.points += points\n\nclass Game:\n def __init__(self, width: int, height: int):\n self.snake = Snake(width // 2, height // 2)\n self.food = None\n self.score = Score()\n self.width = width\n self.height = height\n\n def start_game(self):\n self.generate_food()\n\n def move_snake(self, direction: str):\n self.snake.move(direction)\n if self.check_collision():\n return False\n self.check_eat()\n return True\n\n def generate_food(self):\n import random\n x = random.randint(0, self.width - 1)\n y = random.randint(0, self.height - 1)\n self.food = Food(x, y)\n\n def update_score(self, points: int):\n self.score.increase(points)\n\n def check_collision(self) -> bool:\n head = self.snake.body[0]\n if head[0] < 0 or head[0] >= self.width or head[1] < 0 or head[1] >= self.height:\n return True\n if self.snake.collides_with_self():\n return True\n return False\n\n def check_eat(self):\n if self.snake.body[0] == self.food.get_position():\n self.snake.grow()\n self.generate_food()\n self.update_score(10)\n```", + "\n# System\nRole: You are a professional software engineer, and your main task is to review and revise the code. You need to ensure that the code conforms to the google-style standards, is elegantly designed and modularized, easy to read and maintain.\nLanguage: Please use the same language as the user requirement, but the title and code should be still in English. For example, if the user speaks Chinese, the specific text of your answer should also be in Chinese.\nATTENTION: Use '##' to SPLIT SECTIONS, not '#'. Output format carefully referenced \"Format example\".\n\n# Context\n## System Design\n{\"Implementation approach\":\"We will use Python and the curses library to create the snake game. The game logic will be implemented in a separate module, and the main.py file will handle the user interface and game loop.\",\"File list\":[\"main.py\",\"game.py\"],\"Data structures and interfaces\":\"\\nclassDiagram\\n class Game {\\n -Snake snake\\n -Food food\\n -Score score\\n +__init__(width: int, height: int)\\n +start_game()\\n +move_snake(direction: str)\\n +generate_food()\\n +update_score(points: int)\\n }\\n class Snake {\\n -body list\\n -direction str\\n +__init__(x: int, y: int)\\n +move(direction: str)\\n +grow()\\n +collides_with_self() bool\\n }\\n class Food {\\n -position tuple\\n +__init__(x: int, y: int)\\n +get_position() tuple\\n }\\n class Score {\\n -points int\\n +__init__()\\n +increase(points: int)\\n }\\n Game --> Snake\\n Game --> Food\\n Game --> Score\\n\",\"Program call flow\":\"\\nsequenceDiagram\\n participant M as Main\\n participant G as Game\\n M->>G: start_game()\\n M->>G: move_snake(direction)\\n G->>G: generate_food()\\n G->>G: update_score(points)\\n\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n## Tasks\n{\"Required Python packages\":[\"curses==2.2.0\"],\"Required Other language third-party packages\":[\"No third-party dependencies required\"],\"Logic Analysis\":[[\"game.py\",\"Contains Game class and ... functions\"],[\"main.py\",\"Contains main function, from game import Game\"]],\"Task list\":[\"game.py\",\"main.py\"],\"Full API spec\":\"\",\"Shared Knowledge\":\"'game.py' contains functions shared across the project.\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n## Code Files\n\n\n\n## Code to be Reviewed: game.py\n```Code\n## game.py\n\nclass Snake:\n def __init__(self, x: int, y: int):\n self.body = [(x, y)]\n self.direction = 'right'\n\n def move(self, direction: str):\n if direction == 'up' and self.direction != 'down':\n self.direction = 'up'\n elif direction == 'down' and self.direction != 'up':\n self.direction = 'down'\n elif direction == 'left' and self.direction != 'right':\n self.direction = 'left'\n elif direction == 'right' and self.direction != 'left':\n self.direction = 'right'\n\n head = self.body[0]\n x, y = head\n if self.direction == 'up':\n new_head = (x, y - 1)\n elif self.direction == 'down':\n new_head = (x, y + 1)\n elif self.direction == 'left':\n new_head = (x - 1, y)\n elif self.direction == 'right':\n new_head = (x + 1, y)\n self.body.insert(0, new_head)\n\n def grow(self):\n tail = self.body[-1]\n x, y = tail\n if self.direction == 'up':\n new_tail = (x, y + 1)\n elif self.direction == 'down':\n new_tail = (x, y - 1)\n elif self.direction == 'left':\n new_tail = (x + 1, y)\n elif self.direction == 'right':\n new_tail = (x - 1, y)\n self.body.append(new_tail)\n\n def collides_with_self(self) -> bool:\n return len(self.body) != len(set(self.body))\n\nclass Food:\n def __init__(self, x: int, y: int):\n self.position = (x, y)\n\n def get_position(self) -> tuple:\n return self.position\n\nclass Score:\n def __init__(self):\n self.points = 0\n\n def increase(self, points: int):\n self.points += points\n\nclass Game:\n def __init__(self, width: int, height: int):\n self.snake = Snake(width // 2, height // 2)\n self.food = None\n self.score = Score()\n self.width = width\n self.height = height\n\n def start_game(self):\n self.generate_food()\n\n def move_snake(self, direction: str):\n self.snake.move(direction)\n if self.check_collision():\n return False\n self.check_eat()\n return True\n\n def generate_food(self):\n import random\n x = random.randint(0, self.width - 1)\n y = random.randint(0, self.height - 1)\n self.food = Food(x, y)\n\n def update_score(self, points: int):\n self.score.increase(points)\n\n def check_collision(self) -> bool:\n head = self.snake.body[0]\n if head[0] < 0 or head[0] >= self.width or head[1] < 0 or head[1] >= self.height:\n return True\n if self.snake.collides_with_self():\n return True\n return False\n\n def check_eat(self):\n if self.snake.body[0] == self.food.get_position():\n self.snake.grow()\n self.generate_food()\n self.update_score(10)\n\n```\n\n\n\n# Format example 1\n## Code Review: game.py\n1. No, we should fix the logic of class A due to ...\n2. ...\n3. ...\n4. No, function B is not implemented, ...\n5. ...\n6. ...\n\n## Actions\n1. Fix the `handle_events` method to update the game state only if a move is successful.\n ```python\n def handle_events(self):\n for event in pygame.event.get():\n if event.type == pygame.QUIT:\n return False\n if event.type == pygame.KEYDOWN:\n moved = False\n if event.key == pygame.K_UP:\n moved = self.game.move('UP')\n elif event.key == pygame.K_DOWN:\n moved = self.game.move('DOWN')\n elif event.key == pygame.K_LEFT:\n moved = self.game.move('LEFT')\n elif event.key == pygame.K_RIGHT:\n moved = self.game.move('RIGHT')\n if moved:\n # Update the game state only if a move was successful\n self.render()\n return True\n ```\n2. Implement function B\n\n## Code Review Result\nLBTM\n\n# Format example 2\n## Code Review: game.py\n1. Yes.\n2. Yes.\n3. Yes.\n4. Yes.\n5. Yes.\n6. Yes.\n\n## Actions\npass\n\n## Code Review Result\nLGTM\n\n\n\n# Instruction: Based on the actual code situation, follow one of the \"Format example\". Return only 1 file under review.\n\n## Code Review: Ordered List. Based on the \"Code to be Reviewed\", provide key, clear, concise, and specific answer. If any answer is no, explain how to fix it step by step.\n1. Is the code implemented as per the requirements? If not, how to achieve it? Analyse it step by step.\n2. Is the code logic completely correct? If there are errors, please indicate how to correct them.\n3. Does the existing code follow the \"Data structures and interfaces\"?\n4. Are all functions implemented? If there is no implementation, please indicate how to achieve it step by step.\n5. Have all necessary pre-dependencies been imported? If not, indicate which ones need to be imported\n6. Are methods from other files being reused correctly?\n\n## Actions: Ordered List. Things that should be done after CR, such as implementing class A and function B\n\n## Code Review Result: str. If the code doesn't have bugs, we don't need to rewrite it, so answer LGTM and stop. ONLY ANSWER LGTM/LBTM.\nLGTM/LBTM\n\n": "## Code Review: game.py\n1. Yes, the code is implemented as per the requirements. The Snake, Food, and Score classes are correctly implemented, and the Game class handles the game logic as specified.\n2. Yes, the code logic is correct. The movement, growth, collision detection, and scoring mechanisms are implemented accurately.\n3. Yes, the existing code follows the \"Data structures and interfaces\" as specified in the class diagram.\n4. Yes, all functions are implemented as required.\n5. No, the necessary pre-dependencies have not been imported. The `curses` package needs to be imported at the beginning of the file using `import curses`.\n6. Yes, methods from other files are being reused correctly.\n\n## Actions\n1. Import the necessary pre-dependency `curses` at the beginning of the file using `import curses`.\n\n## Code Review Result\nLBTM", + "\n# System\nRole: You are a professional software engineer, and your main task is to review and revise the code. You need to ensure that the code conforms to the google-style standards, is elegantly designed and modularized, easy to read and maintain.\nLanguage: Please use the same language as the user requirement, but the title and code should be still in English. For example, if the user speaks Chinese, the specific text of your answer should also be in Chinese.\nATTENTION: Use '##' to SPLIT SECTIONS, not '#'. Output format carefully referenced \"Format example\".\n\n# Context\n## System Design\n{\"Implementation approach\":\"We will use Python and the curses library to create the snake game. The game logic will be implemented in a separate module, and the main.py file will handle the user interface and game loop.\",\"File list\":[\"main.py\",\"game.py\"],\"Data structures and interfaces\":\"\\nclassDiagram\\n class Game {\\n -Snake snake\\n -Food food\\n -Score score\\n +__init__(width: int, height: int)\\n +start_game()\\n +move_snake(direction: str)\\n +generate_food()\\n +update_score(points: int)\\n }\\n class Snake {\\n -body list\\n -direction str\\n +__init__(x: int, y: int)\\n +move(direction: str)\\n +grow()\\n +collides_with_self() bool\\n }\\n class Food {\\n -position tuple\\n +__init__(x: int, y: int)\\n +get_position() tuple\\n }\\n class Score {\\n -points int\\n +__init__()\\n +increase(points: int)\\n }\\n Game --> Snake\\n Game --> Food\\n Game --> Score\\n\",\"Program call flow\":\"\\nsequenceDiagram\\n participant M as Main\\n participant G as Game\\n M->>G: start_game()\\n M->>G: move_snake(direction)\\n G->>G: generate_food()\\n G->>G: update_score(points)\\n\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n## Tasks\n{\"Required Python packages\":[\"curses==2.2.0\"],\"Required Other language third-party packages\":[\"No third-party dependencies required\"],\"Logic Analysis\":[[\"game.py\",\"Contains Game class and ... functions\"],[\"main.py\",\"Contains main function, from game import Game\"]],\"Task list\":[\"game.py\",\"main.py\"],\"Full API spec\":\"\",\"Shared Knowledge\":\"'game.py' contains functions shared across the project.\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n## Code Files\n\n\n\n## Code to be Reviewed: game.py\n```Code\n## game.py\n\nclass Snake:\n def __init__(self, x: int, y: int):\n self.body = [(x, y)]\n self.direction = 'right'\n\n def move(self, direction: str):\n if direction == 'up' and self.direction != 'down':\n self.direction = 'up'\n elif direction == 'down' and self.direction != 'up':\n self.direction = 'down'\n elif direction == 'left' and self.direction != 'right':\n self.direction = 'left'\n elif direction == 'right' and self.direction != 'left':\n self.direction = 'right'\n\n head = self.body[0]\n x, y = head\n if self.direction == 'up':\n new_head = (x, y - 1)\n elif self.direction == 'down':\n new_head = (x, y + 1)\n elif self.direction == 'left':\n new_head = (x - 1, y)\n elif self.direction == 'right':\n new_head = (x + 1, y)\n self.body.insert(0, new_head)\n\n def grow(self):\n tail = self.body[-1]\n x, y = tail\n if self.direction == 'up':\n new_tail = (x, y + 1)\n elif self.direction == 'down':\n new_tail = (x, y - 1)\n elif self.direction == 'left':\n new_tail = (x + 1, y)\n elif self.direction == 'right':\n new_tail = (x - 1, y)\n self.body.append(new_tail)\n\n def collides_with_self(self) -> bool:\n return len(self.body) != len(set(self.body))\n\nclass Food:\n def __init__(self, x: int, y: int):\n self.position = (x, y)\n\n def get_position(self) -> tuple:\n return self.position\n\nclass Score:\n def __init__(self):\n self.points = 0\n\n def increase(self, points: int):\n self.points += points\n\nclass Game:\n def __init__(self, width: int, height: int):\n self.snake = Snake(width // 2, height // 2)\n self.food = None\n self.score = Score()\n self.width = width\n self.height = height\n\n def start_game(self):\n self.generate_food()\n\n def move_snake(self, direction: str):\n self.snake.move(direction)\n if self.check_collision():\n return False\n self.check_eat()\n return True\n\n def generate_food(self):\n import random\n x = random.randint(0, self.width - 1)\n y = random.randint(0, self.height - 1)\n self.food = Food(x, y)\n\n def update_score(self, points: int):\n self.score.increase(points)\n\n def check_collision(self) -> bool:\n head = self.snake.body[0]\n if head[0] < 0 or head[0] >= self.width or head[1] < 0 or head[1] >= self.height:\n return True\n if self.snake.collides_with_self():\n return True\n return False\n\n def check_eat(self):\n if self.snake.body[0] == self.food.get_position():\n self.snake.grow()\n self.generate_food()\n self.update_score(10)\n\n```\n\n## Code Review: game.py\n1. Yes, the code is implemented as per the requirements. The Snake, Food, and Score classes are correctly implemented, and the Game class handles the game logic as specified.\n2. Yes, the code logic is correct. The movement, growth, collision detection, and scoring mechanisms are implemented accurately.\n3. Yes, the existing code follows the \"Data structures and interfaces\" as specified in the class diagram.\n4. Yes, all functions are implemented as required.\n5. No, the necessary pre-dependencies have not been imported. The `curses` package needs to be imported at the beginning of the file using `import curses`.\n6. Yes, methods from other files are being reused correctly.\n\n## Actions\n1. Import the necessary pre-dependency `curses` at the beginning of the file using `import curses`.\n\n## Code Review Result\nLBTM\n\n# Instruction: rewrite code based on the Code Review and Actions\n## Rewrite Code: CodeBlock. If it still has some bugs, rewrite game.py with triple quotes. Do your utmost to optimize THIS SINGLE FILE. Return all completed codes and prohibit the return of unfinished codes.\n```Code\n## game.py\n...\n```\n": "```Code\n## game.py\n\nimport curses\n\nclass Snake:\n def __init__(self, x: int, y: int):\n self.body = [(x, y)]\n self.direction = 'right'\n\n def move(self, direction: str):\n if direction == 'up' and self.direction != 'down':\n self.direction = 'up'\n elif direction == 'down' and self.direction != 'up':\n self.direction = 'down'\n elif direction == 'left' and self.direction != 'right':\n self.direction = 'left'\n elif direction == 'right' and self.direction != 'left':\n self.direction = 'right'\n\n head = self.body[0]\n x, y = head\n if self.direction == 'up':\n new_head = (x, y - 1)\n elif self.direction == 'down':\n new_head = (x, y + 1)\n elif self.direction == 'left':\n new_head = (x - 1, y)\n elif self.direction == 'right':\n new_head = (x + 1, y)\n self.body.insert(0, new_head)\n\n def grow(self):\n tail = self.body[-1]\n x, y = tail\n if self.direction == 'up':\n new_tail = (x, y + 1)\n elif self.direction == 'down':\n new_tail = (x, y - 1)\n elif self.direction == 'left':\n new_tail = (x + 1, y)\n elif self.direction == 'right':\n new_tail = (x - 1, y)\n self.body.append(new_tail)\n\n def collides_with_self(self) -> bool:\n return len(self.body) != len(set(self.body))\n\nclass Food:\n def __init__(self, x: int, y: int):\n self.position = (x, y)\n\n def get_position(self) -> tuple:\n return self.position\n\nclass Score:\n def __init__(self):\n self.points = 0\n\n def increase(self, points: int):\n self.points += points\n\nclass Game:\n def __init__(self, width: int, height: int):\n self.snake = Snake(width // 2, height // 2)\n self.food = None\n self.score = Score()\n self.width = width\n self.height = height\n\n def start_game(self):\n self.generate_food()\n\n def move_snake(self, direction: str):\n self.snake.move(direction)\n if self.check_collision():\n return False\n self.check_eat()\n return True\n\n def generate_food(self):\n import random\n x = random.randint(0, self.width - 1)\n y = random.randint(0, self.height - 1)\n self.food = Food(x, y)\n\n def update_score(self, points: int):\n self.score.increase(points)\n\n def check_collision(self) -> bool:\n head = self.snake.body[0]\n if head[0] < 0 or head[0] >= self.width or head[1] < 0 or head[1] >= self.height:\n return True\n if self.snake.collides_with_self():\n return True\n return False\n\n def check_eat(self):\n if self.snake.body[0] == self.food.get_position():\n self.snake.grow()\n self.generate_food()\n self.update_score(10)\n\n```", + "\n# System\nRole: You are a professional software engineer, and your main task is to review and revise the code. You need to ensure that the code conforms to the google-style standards, is elegantly designed and modularized, easy to read and maintain.\nLanguage: Please use the same language as the user requirement, but the title and code should be still in English. For example, if the user speaks Chinese, the specific text of your answer should also be in Chinese.\nATTENTION: Use '##' to SPLIT SECTIONS, not '#'. Output format carefully referenced \"Format example\".\n\n# Context\n## System Design\n{\"Implementation approach\":\"We will use Python and the curses library to create the snake game. The game logic will be implemented in a separate module, and the main.py file will handle the user interface and game loop.\",\"File list\":[\"main.py\",\"game.py\"],\"Data structures and interfaces\":\"\\nclassDiagram\\n class Game {\\n -Snake snake\\n -Food food\\n -Score score\\n +__init__(width: int, height: int)\\n +start_game()\\n +move_snake(direction: str)\\n +generate_food()\\n +update_score(points: int)\\n }\\n class Snake {\\n -body list\\n -direction str\\n +__init__(x: int, y: int)\\n +move(direction: str)\\n +grow()\\n +collides_with_self() bool\\n }\\n class Food {\\n -position tuple\\n +__init__(x: int, y: int)\\n +get_position() tuple\\n }\\n class Score {\\n -points int\\n +__init__()\\n +increase(points: int)\\n }\\n Game --> Snake\\n Game --> Food\\n Game --> Score\\n\",\"Program call flow\":\"\\nsequenceDiagram\\n participant M as Main\\n participant G as Game\\n M->>G: start_game()\\n M->>G: move_snake(direction)\\n G->>G: generate_food()\\n G->>G: update_score(points)\\n\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n## Tasks\n{\"Required Python packages\":[\"curses==2.2.0\"],\"Required Other language third-party packages\":[\"No third-party dependencies required\"],\"Logic Analysis\":[[\"game.py\",\"Contains Game class and ... functions\"],[\"main.py\",\"Contains main function, from game import Game\"]],\"Task list\":[\"game.py\",\"main.py\"],\"Full API spec\":\"\",\"Shared Knowledge\":\"'game.py' contains functions shared across the project.\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n## Code Files\n\n\n\n## Code to be Reviewed: game.py\n```Code\n## game.py\n\nimport curses\n\nclass Snake:\n def __init__(self, x: int, y: int):\n self.body = [(x, y)]\n self.direction = 'right'\n\n def move(self, direction: str):\n if direction == 'up' and self.direction != 'down':\n self.direction = 'up'\n elif direction == 'down' and self.direction != 'up':\n self.direction = 'down'\n elif direction == 'left' and self.direction != 'right':\n self.direction = 'left'\n elif direction == 'right' and self.direction != 'left':\n self.direction = 'right'\n\n head = self.body[0]\n x, y = head\n if self.direction == 'up':\n new_head = (x, y - 1)\n elif self.direction == 'down':\n new_head = (x, y + 1)\n elif self.direction == 'left':\n new_head = (x - 1, y)\n elif self.direction == 'right':\n new_head = (x + 1, y)\n self.body.insert(0, new_head)\n\n def grow(self):\n tail = self.body[-1]\n x, y = tail\n if self.direction == 'up':\n new_tail = (x, y + 1)\n elif self.direction == 'down':\n new_tail = (x, y - 1)\n elif self.direction == 'left':\n new_tail = (x + 1, y)\n elif self.direction == 'right':\n new_tail = (x - 1, y)\n self.body.append(new_tail)\n\n def collides_with_self(self) -> bool:\n return len(self.body) != len(set(self.body))\n\nclass Food:\n def __init__(self, x: int, y: int):\n self.position = (x, y)\n\n def get_position(self) -> tuple:\n return self.position\n\nclass Score:\n def __init__(self):\n self.points = 0\n\n def increase(self, points: int):\n self.points += points\n\nclass Game:\n def __init__(self, width: int, height: int):\n self.snake = Snake(width // 2, height // 2)\n self.food = None\n self.score = Score()\n self.width = width\n self.height = height\n\n def start_game(self):\n self.generate_food()\n\n def move_snake(self, direction: str):\n self.snake.move(direction)\n if self.check_collision():\n return False\n self.check_eat()\n return True\n\n def generate_food(self):\n import random\n x = random.randint(0, self.width - 1)\n y = random.randint(0, self.height - 1)\n self.food = Food(x, y)\n\n def update_score(self, points: int):\n self.score.increase(points)\n\n def check_collision(self) -> bool:\n head = self.snake.body[0]\n if head[0] < 0 or head[0] >= self.width or head[1] < 0 or head[1] >= self.height:\n return True\n if self.snake.collides_with_self():\n return True\n return False\n\n def check_eat(self):\n if self.snake.body[0] == self.food.get_position():\n self.snake.grow()\n self.generate_food()\n self.update_score(10)\n\n\n```\n\n\n\n# Format example 1\n## Code Review: game.py\n1. No, we should fix the logic of class A due to ...\n2. ...\n3. ...\n4. No, function B is not implemented, ...\n5. ...\n6. ...\n\n## Actions\n1. Fix the `handle_events` method to update the game state only if a move is successful.\n ```python\n def handle_events(self):\n for event in pygame.event.get():\n if event.type == pygame.QUIT:\n return False\n if event.type == pygame.KEYDOWN:\n moved = False\n if event.key == pygame.K_UP:\n moved = self.game.move('UP')\n elif event.key == pygame.K_DOWN:\n moved = self.game.move('DOWN')\n elif event.key == pygame.K_LEFT:\n moved = self.game.move('LEFT')\n elif event.key == pygame.K_RIGHT:\n moved = self.game.move('RIGHT')\n if moved:\n # Update the game state only if a move was successful\n self.render()\n return True\n ```\n2. Implement function B\n\n## Code Review Result\nLBTM\n\n# Format example 2\n## Code Review: game.py\n1. Yes.\n2. Yes.\n3. Yes.\n4. Yes.\n5. Yes.\n6. Yes.\n\n## Actions\npass\n\n## Code Review Result\nLGTM\n\n\n\n# Instruction: Based on the actual code situation, follow one of the \"Format example\". Return only 1 file under review.\n\n## Code Review: Ordered List. Based on the \"Code to be Reviewed\", provide key, clear, concise, and specific answer. If any answer is no, explain how to fix it step by step.\n1. Is the code implemented as per the requirements? If not, how to achieve it? Analyse it step by step.\n2. Is the code logic completely correct? If there are errors, please indicate how to correct them.\n3. Does the existing code follow the \"Data structures and interfaces\"?\n4. Are all functions implemented? If there is no implementation, please indicate how to achieve it step by step.\n5. Have all necessary pre-dependencies been imported? If not, indicate which ones need to be imported\n6. Are methods from other files being reused correctly?\n\n## Actions: Ordered List. Things that should be done after CR, such as implementing class A and function B\n\n## Code Review Result: str. If the code doesn't have bugs, we don't need to rewrite it, so answer LGTM and stop. ONLY ANSWER LGTM/LBTM.\nLGTM/LBTM\n\n": "## Code Review: game.py\n1. Yes, the code is implemented as per the requirements.\n2. Yes, the code logic is completely correct.\n3. Yes, the existing code follows the \"Data structures and interfaces\".\n4. Yes, all functions are implemented.\n5. Yes, all necessary pre-dependencies have been imported.\n6. Yes, methods from other files are being reused correctly.\n\n## Code Review Result\nLGTM", + "\nNOTICE\nRole: You are a professional engineer; the main goal is to write google-style, elegant, modular, easy to read and maintain code\nLanguage: Please use the same language as the user requirement, but the title and code should be still in English. For example, if the user speaks Chinese, the specific text of your answer should also be in Chinese.\nATTENTION: Use '##' to SPLIT SECTIONS, not '#'. Output format carefully referenced \"Format example\".\n\n# Context\n## Design\n{\"Implementation approach\":\"We will use Python and the curses library to create the snake game. The game logic will be implemented in a separate module, and the main.py file will handle the user interface and game loop.\",\"File list\":[\"main.py\",\"game.py\"],\"Data structures and interfaces\":\"\\nclassDiagram\\n class Game {\\n -Snake snake\\n -Food food\\n -Score score\\n +__init__(width: int, height: int)\\n +start_game()\\n +move_snake(direction: str)\\n +generate_food()\\n +update_score(points: int)\\n }\\n class Snake {\\n -body list\\n -direction str\\n +__init__(x: int, y: int)\\n +move(direction: str)\\n +grow()\\n +collides_with_self() bool\\n }\\n class Food {\\n -position tuple\\n +__init__(x: int, y: int)\\n +get_position() tuple\\n }\\n class Score {\\n -points int\\n +__init__()\\n +increase(points: int)\\n }\\n Game --> Snake\\n Game --> Food\\n Game --> Score\\n\",\"Program call flow\":\"\\nsequenceDiagram\\n participant M as Main\\n participant G as Game\\n M->>G: start_game()\\n M->>G: move_snake(direction)\\n G->>G: generate_food()\\n G->>G: update_score(points)\\n\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n## Tasks\n{\"Required Python packages\":[\"curses==2.2.0\"],\"Required Other language third-party packages\":[\"No third-party dependencies required\"],\"Logic Analysis\":[[\"game.py\",\"Contains Game class and ... functions\"],[\"main.py\",\"Contains main function, from game import Game\"]],\"Task list\":[\"game.py\",\"main.py\"],\"Full API spec\":\"\",\"Shared Knowledge\":\"'game.py' contains functions shared across the project.\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n## Legacy Code\n```Code\n----- game.py\n## game.py\n\nimport curses\n\nclass Snake:\n def __init__(self, x: int, y: int):\n self.body = [(x, y)]\n self.direction = 'right'\n\n def move(self, direction: str):\n if direction == 'up' and self.direction != 'down':\n self.direction = 'up'\n elif direction == 'down' and self.direction != 'up':\n self.direction = 'down'\n elif direction == 'left' and self.direction != 'right':\n self.direction = 'left'\n elif direction == 'right' and self.direction != 'left':\n self.direction = 'right'\n\n head = self.body[0]\n x, y = head\n if self.direction == 'up':\n new_head = (x, y - 1)\n elif self.direction == 'down':\n new_head = (x, y + 1)\n elif self.direction == 'left':\n new_head = (x - 1, y)\n elif self.direction == 'right':\n new_head = (x + 1, y)\n self.body.insert(0, new_head)\n\n def grow(self):\n tail = self.body[-1]\n x, y = tail\n if self.direction == 'up':\n new_tail = (x, y + 1)\n elif self.direction == 'down':\n new_tail = (x, y - 1)\n elif self.direction == 'left':\n new_tail = (x + 1, y)\n elif self.direction == 'right':\n new_tail = (x - 1, y)\n self.body.append(new_tail)\n\n def collides_with_self(self) -> bool:\n return len(self.body) != len(set(self.body))\n\nclass Food:\n def __init__(self, x: int, y: int):\n self.position = (x, y)\n\n def get_position(self) -> tuple:\n return self.position\n\nclass Score:\n def __init__(self):\n self.points = 0\n\n def increase(self, points: int):\n self.points += points\n\nclass Game:\n def __init__(self, width: int, height: int):\n self.snake = Snake(width // 2, height // 2)\n self.food = None\n self.score = Score()\n self.width = width\n self.height = height\n\n def start_game(self):\n self.generate_food()\n\n def move_snake(self, direction: str):\n self.snake.move(direction)\n if self.check_collision():\n return False\n self.check_eat()\n return True\n\n def generate_food(self):\n import random\n x = random.randint(0, self.width - 1)\n y = random.randint(0, self.height - 1)\n self.food = Food(x, y)\n\n def update_score(self, points: int):\n self.score.increase(points)\n\n def check_collision(self) -> bool:\n head = self.snake.body[0]\n if head[0] < 0 or head[0] >= self.width or head[1] < 0 or head[1] >= self.height:\n return True\n if self.snake.collides_with_self():\n return True\n return False\n\n def check_eat(self):\n if self.snake.body[0] == self.food.get_position():\n self.snake.grow()\n self.generate_food()\n self.update_score(10)\n\n\n```\n\n## Debug logs\n```text\n\n\n\n```\n\n## Bug Feedback logs\n```text\n\n```\n\n# Format example\n## Code: main.py\n```python\n## main.py\n...\n```\n\n# Instruction: Based on the context, follow \"Format example\", write code.\n\n## Code: main.py. Write code with triple quoto, based on the following attentions and context.\n1. Only One file: do your best to implement THIS ONLY ONE FILE.\n2. COMPLETE CODE: Your code will be part of the entire project, so please implement complete, reliable, reusable code snippets.\n3. Set default value: If there is any setting, ALWAYS SET A DEFAULT VALUE, ALWAYS USE STRONG TYPE AND EXPLICIT VARIABLE. AVOID circular import.\n4. Follow design: YOU MUST FOLLOW \"Data structures and interfaces\". DONT CHANGE ANY DESIGN. Do not use public member functions that do not exist in your design.\n5. CAREFULLY CHECK THAT YOU DONT MISS ANY NECESSARY CLASS/FUNCTION IN THIS FILE.\n6. Before using a external variable/module, make sure you import it first.\n7. Write out EVERY CODE DETAIL, DON'T LEAVE TODO.\n\n": "```python\n## main.py\n\nfrom game import Game\n\ndef main():\n width = 20 # Set default width\n height = 20 # Set default height\n game = Game(width, height)\n game.start_game()\n\n while True:\n # Get user input for direction\n direction = input(\"Enter direction (up/down/left/right): \")\n if direction in ['up', 'down', 'left', 'right']:\n if not game.move_snake(direction):\n print(\"Game over!\")\n break\n else:\n print(\"Invalid direction!\")\n\nif __name__ == \"__main__\":\n main()\n```", + "\n# System\nRole: You are a professional software engineer, and your main task is to review and revise the code. You need to ensure that the code conforms to the google-style standards, is elegantly designed and modularized, easy to read and maintain.\nLanguage: Please use the same language as the user requirement, but the title and code should be still in English. For example, if the user speaks Chinese, the specific text of your answer should also be in Chinese.\nATTENTION: Use '##' to SPLIT SECTIONS, not '#'. Output format carefully referenced \"Format example\".\n\n# Context\n## System Design\n{\"Implementation approach\":\"We will use Python and the curses library to create the snake game. The game logic will be implemented in a separate module, and the main.py file will handle the user interface and game loop.\",\"File list\":[\"main.py\",\"game.py\"],\"Data structures and interfaces\":\"\\nclassDiagram\\n class Game {\\n -Snake snake\\n -Food food\\n -Score score\\n +__init__(width: int, height: int)\\n +start_game()\\n +move_snake(direction: str)\\n +generate_food()\\n +update_score(points: int)\\n }\\n class Snake {\\n -body list\\n -direction str\\n +__init__(x: int, y: int)\\n +move(direction: str)\\n +grow()\\n +collides_with_self() bool\\n }\\n class Food {\\n -position tuple\\n +__init__(x: int, y: int)\\n +get_position() tuple\\n }\\n class Score {\\n -points int\\n +__init__()\\n +increase(points: int)\\n }\\n Game --> Snake\\n Game --> Food\\n Game --> Score\\n\",\"Program call flow\":\"\\nsequenceDiagram\\n participant M as Main\\n participant G as Game\\n M->>G: start_game()\\n M->>G: move_snake(direction)\\n G->>G: generate_food()\\n G->>G: update_score(points)\\n\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n## Tasks\n{\"Required Python packages\":[\"curses==2.2.0\"],\"Required Other language third-party packages\":[\"No third-party dependencies required\"],\"Logic Analysis\":[[\"game.py\",\"Contains Game class and ... functions\"],[\"main.py\",\"Contains main function, from game import Game\"]],\"Task list\":[\"game.py\",\"main.py\"],\"Full API spec\":\"\",\"Shared Knowledge\":\"'game.py' contains functions shared across the project.\",\"Anything UNCLEAR\":\"Please provide more details on the game mechanics and user interactions.\"}\n\n## Code Files\n----- game.py\n## game.py\n\nimport curses\n\nclass Snake:\n def __init__(self, x: int, y: int):\n self.body = [(x, y)]\n self.direction = 'right'\n\n def move(self, direction: str):\n if direction == 'up' and self.direction != 'down':\n self.direction = 'up'\n elif direction == 'down' and self.direction != 'up':\n self.direction = 'down'\n elif direction == 'left' and self.direction != 'right':\n self.direction = 'left'\n elif direction == 'right' and self.direction != 'left':\n self.direction = 'right'\n\n head = self.body[0]\n x, y = head\n if self.direction == 'up':\n new_head = (x, y - 1)\n elif self.direction == 'down':\n new_head = (x, y + 1)\n elif self.direction == 'left':\n new_head = (x - 1, y)\n elif self.direction == 'right':\n new_head = (x + 1, y)\n self.body.insert(0, new_head)\n\n def grow(self):\n tail = self.body[-1]\n x, y = tail\n if self.direction == 'up':\n new_tail = (x, y + 1)\n elif self.direction == 'down':\n new_tail = (x, y - 1)\n elif self.direction == 'left':\n new_tail = (x + 1, y)\n elif self.direction == 'right':\n new_tail = (x - 1, y)\n self.body.append(new_tail)\n\n def collides_with_self(self) -> bool:\n return len(self.body) != len(set(self.body))\n\nclass Food:\n def __init__(self, x: int, y: int):\n self.position = (x, y)\n\n def get_position(self) -> tuple:\n return self.position\n\nclass Score:\n def __init__(self):\n self.points = 0\n\n def increase(self, points: int):\n self.points += points\n\nclass Game:\n def __init__(self, width: int, height: int):\n self.snake = Snake(width // 2, height // 2)\n self.food = None\n self.score = Score()\n self.width = width\n self.height = height\n\n def start_game(self):\n self.generate_food()\n\n def move_snake(self, direction: str):\n self.snake.move(direction)\n if self.check_collision():\n return False\n self.check_eat()\n return True\n\n def generate_food(self):\n import random\n x = random.randint(0, self.width - 1)\n y = random.randint(0, self.height - 1)\n self.food = Food(x, y)\n\n def update_score(self, points: int):\n self.score.increase(points)\n\n def check_collision(self) -> bool:\n head = self.snake.body[0]\n if head[0] < 0 or head[0] >= self.width or head[1] < 0 or head[1] >= self.height:\n return True\n if self.snake.collides_with_self():\n return True\n return False\n\n def check_eat(self):\n if self.snake.body[0] == self.food.get_position():\n self.snake.grow()\n self.generate_food()\n self.update_score(10)\n\n\n\n\n## Code to be Reviewed: main.py\n```Code\n## main.py\n\nfrom game import Game\n\ndef main():\n width = 20 # Set default width\n height = 20 # Set default height\n game = Game(width, height)\n game.start_game()\n\n while True:\n # Get user input for direction\n direction = input(\"Enter direction (up/down/left/right): \")\n if direction in ['up', 'down', 'left', 'right']:\n if not game.move_snake(direction):\n print(\"Game over!\")\n break\n else:\n print(\"Invalid direction!\")\n\nif __name__ == \"__main__\":\n main()\n\n```\n\n\n\n# Format example 1\n## Code Review: main.py\n1. No, we should fix the logic of class A due to ...\n2. ...\n3. ...\n4. No, function B is not implemented, ...\n5. ...\n6. ...\n\n## Actions\n1. Fix the `handle_events` method to update the game state only if a move is successful.\n ```python\n def handle_events(self):\n for event in pygame.event.get():\n if event.type == pygame.QUIT:\n return False\n if event.type == pygame.KEYDOWN:\n moved = False\n if event.key == pygame.K_UP:\n moved = self.game.move('UP')\n elif event.key == pygame.K_DOWN:\n moved = self.game.move('DOWN')\n elif event.key == pygame.K_LEFT:\n moved = self.game.move('LEFT')\n elif event.key == pygame.K_RIGHT:\n moved = self.game.move('RIGHT')\n if moved:\n # Update the game state only if a move was successful\n self.render()\n return True\n ```\n2. Implement function B\n\n## Code Review Result\nLBTM\n\n# Format example 2\n## Code Review: main.py\n1. Yes.\n2. Yes.\n3. Yes.\n4. Yes.\n5. Yes.\n6. Yes.\n\n## Actions\npass\n\n## Code Review Result\nLGTM\n\n\n\n# Instruction: Based on the actual code situation, follow one of the \"Format example\". Return only 1 file under review.\n\n## Code Review: Ordered List. Based on the \"Code to be Reviewed\", provide key, clear, concise, and specific answer. If any answer is no, explain how to fix it step by step.\n1. Is the code implemented as per the requirements? If not, how to achieve it? Analyse it step by step.\n2. Is the code logic completely correct? If there are errors, please indicate how to correct them.\n3. Does the existing code follow the \"Data structures and interfaces\"?\n4. Are all functions implemented? If there is no implementation, please indicate how to achieve it step by step.\n5. Have all necessary pre-dependencies been imported? If not, indicate which ones need to be imported\n6. Are methods from other files being reused correctly?\n\n## Actions: Ordered List. Things that should be done after CR, such as implementing class A and function B\n\n## Code Review Result: str. If the code doesn't have bugs, we don't need to rewrite it, so answer LGTM and stop. ONLY ANSWER LGTM/LBTM.\nLGTM/LBTM\n\n": "## Code Review: main.py\n1. The code is implemented as per the requirements. The main function initializes the game and handles user input for the snake's direction.\n2. The code logic is correct. It correctly handles user input and updates the game state based on the snake's movement.\n3. The existing code follows the \"Data structures and interfaces\" as defined in the class diagram.\n4. All necessary functions are implemented in the code.\n5. The necessary pre-dependencies have been imported. The required Python package \"curses==2.2.0\" has been imported.\n6. The methods from the \"game.py\" file are being reused correctly.\n\n## Actions\npass\n\n## Code Review Result\nLGTM", + "\n## context\n\n### Project Name\n20240110212717\n\n### Original Requirements\n['开发一个基于大语言模型与私有知识库的搜索引擎，希望可以基于大语言模型进行搜索总结']\n\n### Search Information\n-\n\n\n-----\n\n## format example\n[CONTENT]\n{\n \"Language\": \"en_us\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"Create a 2048 game\",\n \"Product Goals\": [\n \"Create an engaging user experience\",\n \"Improve accessibility, be responsive\",\n \"More beautiful UI\"\n ],\n \"User Stories\": [\n \"As a player, I want to be able to choose difficulty levels\",\n \"As a player, I want to see my score after each game\",\n \"As a player, I want to get restart button when I lose\",\n \"As a player, I want to see beautiful UI that make me feel good\",\n \"As a player, I want to play game via mobile phone\"\n ],\n \"Competitive Analysis\": [\n \"2048 Game A: Simple interface, lacks responsive features\",\n \"play2048.co: Beautiful and responsive UI with my best score shown\",\n \"2048game.com: Responsive UI with my best score shown, but many ads\"\n ],\n \"Competitive Quadrant Chart\": \"quadrantChart\\n title \\\"Reach and engagement of campaigns\\\"\\n x-axis \\\"Low Reach\\\" --> \\\"High Reach\\\"\\n y-axis \\\"Low Engagement\\\" --> \\\"High Engagement\\\"\\n quadrant-1 \\\"We should expand\\\"\\n quadrant-2 \\\"Need to promote\\\"\\n quadrant-3 \\\"Re-evaluate\\\"\\n quadrant-4 \\\"May be improved\\\"\\n \\\"Campaign A\\\": [0.3, 0.6]\\n \\\"Campaign B\\\": [0.45, 0.23]\\n \\\"Campaign C\\\": [0.57, 0.69]\\n \\\"Campaign D\\\": [0.78, 0.34]\\n \\\"Campaign E\\\": [0.40, 0.34]\\n \\\"Campaign F\\\": [0.35, 0.78]\\n \\\"Our Target Product\\\": [0.5, 0.6]\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [\n [\n \"P0\",\n \"The main code ...\"\n ],\n [\n \"P0\",\n \"The game algorithm ...\"\n ]\n ],\n \"UI Design draft\": \"Basic function description with a simple style and layout.\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]\n\n## nodes: \": # \"\n- Language: # Provide the language used in the project, typically matching the user's requirement language.\n- Programming Language: # Python/JavaScript or other mainstream programming language.\n- Original Requirements: # Place the original user's requirements here.\n- Product Goals: typing.List[str] # Provide up to three clear, orthogonal product goals.\n- User Stories: typing.List[str] # Provide up to 3 to 5 scenario-based user stories.\n- Competitive Analysis: typing.List[str] # Provide 5 to 7 competitive products.\n- Competitive Quadrant Chart: # Use mermaid quadrantChart syntax. Distribute scores evenly between 0 and 1\n- Requirement Analysis: # Provide a detailed analysis of the requirements.\n- Requirement Pool: typing.List[typing.List[str]] # List down the top-5 requirements with their priority (P0, P1, P2).\n- UI Design draft: # Provide a simple description of UI elements, functions, style, and layout.\n- Anything UNCLEAR: # Mention any aspects of the project that are unclear and try to clarify them.\n\n\n## constraint\nLanguage: Please use the same language as Human INPUT.\nFormat: output wrapped inside [CONTENT][/CONTENT] like format example, nothing else.\n\n## action\nFollow instructions of nodes, generate output and make sure it follows the format example.\n": "[CONTENT]\n{\n \"Language\": \"zh_cn\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"开发一个基于大语言模型与私有知识库的搜索引擎，希望可以基于大语言模型进行搜索总结\",\n \"Product Goals\": [],\n \"User Stories\": [],\n \"Competitive Analysis\": [],\n \"Competitive Quadrant Chart\": \"\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [],\n \"UI Design draft\": \"\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]", + "\n## context\n\n### Project Name\n20240110212717\n\n### Original Requirements\n['']\n\n### Search Information\n-\n\n\n-----\n\n## format example\n[CONTENT]\n{\n \"Language\": \"en_us\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"Create a 2048 game\",\n \"Product Goals\": [\n \"Create an engaging user experience\",\n \"Improve accessibility, be responsive\",\n \"More beautiful UI\"\n ],\n \"User Stories\": [\n \"As a player, I want to be able to choose difficulty levels\",\n \"As a player, I want to see my score after each game\",\n \"As a player, I want to get restart button when I lose\",\n \"As a player, I want to see beautiful UI that make me feel good\",\n \"As a player, I want to play game via mobile phone\"\n ],\n \"Competitive Analysis\": [\n \"2048 Game A: Simple interface, lacks responsive features\",\n \"play2048.co: Beautiful and responsive UI with my best score shown\",\n \"2048game.com: Responsive UI with my best score shown, but many ads\"\n ],\n \"Competitive Quadrant Chart\": \"quadrantChart\\n title \\\"Reach and engagement of campaigns\\\"\\n x-axis \\\"Low Reach\\\" --> \\\"High Reach\\\"\\n y-axis \\\"Low Engagement\\\" --> \\\"High Engagement\\\"\\n quadrant-1 \\\"We should expand\\\"\\n quadrant-2 \\\"Need to promote\\\"\\n quadrant-3 \\\"Re-evaluate\\\"\\n quadrant-4 \\\"May be improved\\\"\\n \\\"Campaign A\\\": [0.3, 0.6]\\n \\\"Campaign B\\\": [0.45, 0.23]\\n \\\"Campaign C\\\": [0.57, 0.69]\\n \\\"Campaign D\\\": [0.78, 0.34]\\n \\\"Campaign E\\\": [0.40, 0.34]\\n \\\"Campaign F\\\": [0.35, 0.78]\\n \\\"Our Target Product\\\": [0.5, 0.6]\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [\n [\n \"P0\",\n \"The main code ...\"\n ],\n [\n \"P0\",\n \"The game algorithm ...\"\n ]\n ],\n \"UI Design draft\": \"Basic function description with a simple style and layout.\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]\n\n## nodes: \": # \"\n- Language: # Provide the language used in the project, typically matching the user's requirement language.\n- Programming Language: # Python/JavaScript or other mainstream programming language.\n- Original Requirements: # Place the original user's requirements here.\n- Product Goals: typing.List[str] # Provide up to three clear, orthogonal product goals.\n- User Stories: typing.List[str] # Provide up to 3 to 5 scenario-based user stories.\n- Competitive Analysis: typing.List[str] # Provide 5 to 7 competitive products.\n- Competitive Quadrant Chart: # Use mermaid quadrantChart syntax. Distribute scores evenly between 0 and 1\n- Requirement Analysis: # Provide a detailed analysis of the requirements.\n- Requirement Pool: typing.List[typing.List[str]] # List down the top-5 requirements with their priority (P0, P1, P2).\n- UI Design draft: # Provide a simple description of UI elements, functions, style, and layout.\n- Anything UNCLEAR: # Mention any aspects of the project that are unclear and try to clarify them.\n\n\n## constraint\nLanguage: Please use the same language as Human INPUT.\nFormat: output wrapped inside [CONTENT][/CONTENT] like format example, nothing else.\n\n## action\nFollow instructions of nodes, generate output and make sure it follows the format example.\n": "[CONTENT]\n{\n \"Language\": \"en_us\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"\",\n \"Product Goals\": [],\n \"User Stories\": [],\n \"Competitive Analysis\": [],\n \"Competitive Quadrant Chart\": \"\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [],\n \"UI Design draft\": \"\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]" } \ No newline at end of file diff --git a/tests/metagpt/actions/test_rebuild_sequence_view.py b/tests/metagpt/actions/test_rebuild_sequence_view.py index 8c515d976..0511f0308 100644 --- a/tests/metagpt/actions/test_rebuild_sequence_view.py +++ b/tests/metagpt/actions/test_rebuild_sequence_view.py @@ -14,7 +14,6 @@ from metagpt.const import GRAPH_REPO_FILE_REPO from metagpt.context import CONTEXT from metagpt.llm import LLM from metagpt.utils.common import aread -from metagpt.utils.file_repository import FileRepository from metagpt.utils.git_repository import ChangeType @@ -23,7 +22,8 @@ async def test_rebuild(): # Mock data = await aread(filename=Path(__file__).parent / "../../data/graph_db/networkx.json") graph_db_filename = Path(CONTEXT.git_repo.workdir.name).with_suffix(".json") - await FileRepository.save_file( + repo = CONTEXT.file_repo + await repo.save_file( filename=str(graph_db_filename), relative_path=GRAPH_REPO_FILE_REPO, content=data, diff --git a/tests/metagpt/test_role.py b/tests/metagpt/test_role.py index 20a366db8..1b843795c 100644 --- a/tests/metagpt/test_role.py +++ b/tests/metagpt/test_role.py @@ -62,7 +62,7 @@ async def test_react(): "goal": "Test", "constraints": "constraints", "desc": "desc", - "subscription": "start", + "address": "start", } ] @@ -93,8 +93,8 @@ async def test_react(): await env.run() assert role.is_idle tag = uuid.uuid4().hex - role.subscribe({tag}) - assert env.get_subscription(role) == {tag} + role.set_addresses({tag}) + assert env.get_addresses(role) == {tag} @pytest.mark.asyncio @@ -131,7 +131,7 @@ async def test_recover(): role.recovered = True role.latest_observed_msg = Message(content="recover_test") role.rc.state = 0 - assert role.todo == any_to_name(MockAction) + assert role.first_action == any_to_name(MockAction) rsp = await role.run() assert rsp.cause_by == any_to_str(MockAction) diff --git a/tests/metagpt/test_schema.py b/tests/metagpt/test_schema.py index c4f071d85..0929e6c4a 100644 --- a/tests/metagpt/test_schema.py +++ b/tests/metagpt/test_schema.py @@ -102,7 +102,7 @@ def test_message_serdeser(): new_message = Message.model_validate(message_dict) assert new_message.content == message.content assert new_message.instruct_content.model_dump() == message.instruct_content.model_dump() - assert new_message.instruct_content != message.instruct_content # TODO + assert new_message.instruct_content == message.instruct_content # TODO assert new_message.cause_by == message.cause_by assert new_message.instruct_content.field3 == out_data["field3"] diff --git a/tests/metagpt/utils/test_redis.py b/tests/metagpt/utils/test_redis.py index 95eff4f61..8e9cf710a 100644 --- a/tests/metagpt/utils/test_redis.py +++ b/tests/metagpt/utils/test_redis.py @@ -22,7 +22,7 @@ async def async_mock_from_url(*args, **kwargs): @pytest.mark.asyncio @mock.patch("aioredis.from_url", return_value=async_mock_from_url()) -async def test_redis(): +async def test_redis(i): redis = Config.default().redis conn = Redis(redis) From bf6fc25f572d9b874b505af8dbef21961c316c89 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=8E=98=E6=9D=83=20=E9=A9=AC?= Date: Thu, 11 Jan 2024 11:25:00 +0800 Subject: [PATCH 48/61] feat: ProjectRepo + srcs feat: ProjectRepo + git_repo feat: Replace FileRepository with ProjectRepo --- metagpt/actions/action.py | 14 +---- metagpt/actions/debug_error.py | 13 ++--- metagpt/actions/design_api.py | 45 +++++---------- metagpt/actions/prepare_documents.py | 8 +-- metagpt/actions/project_management.py | 49 ++++++---------- metagpt/actions/summarize_code.py | 8 +-- metagpt/actions/write_code.py | 28 +++------ metagpt/actions/write_code_review.py | 3 +- metagpt/actions/write_prd.py | 58 +++++++------------ metagpt/roles/engineer.py | 82 ++++++++++----------------- metagpt/roles/qa_engineer.py | 33 ++++------- metagpt/roles/role.py | 8 ++- metagpt/utils/file_repository.py | 16 +++++- metagpt/utils/git_repository.py | 7 +++ metagpt/utils/project_repo.py | 44 +++++++++++--- 15 files changed, 178 insertions(+), 238 deletions(-) diff --git a/metagpt/actions/action.py b/metagpt/actions/action.py index a3f7163c3..f6e2868e9 100644 --- a/metagpt/actions/action.py +++ b/metagpt/actions/action.py @@ -21,7 +21,7 @@ from metagpt.schema import ( SerializationMixin, TestingContext, ) -from metagpt.utils.file_repository import FileRepository +from metagpt.utils.project_repo import ProjectRepo class Action(SerializationMixin, ContextMixin, BaseModel): @@ -34,16 +34,8 @@ class Action(SerializationMixin, ContextMixin, BaseModel): node: ActionNode = Field(default=None, exclude=True) @property - def git_repo(self): - return self.context.git_repo - - @property - def file_repo(self): - return FileRepository(self.context.git_repo) - - @property - def src_workspace(self): - return self.context.src_workspace + def project_repo(self): + return ProjectRepo(git_repo=self.context.git_repo) @property def prompt_schema(self): diff --git a/metagpt/actions/debug_error.py b/metagpt/actions/debug_error.py index 983214662..f491fdd55 100644 --- a/metagpt/actions/debug_error.py +++ b/metagpt/actions/debug_error.py @@ -13,7 +13,6 @@ import re from pydantic import Field from metagpt.actions.action import Action -from metagpt.const import TEST_CODES_FILE_REPO, TEST_OUTPUTS_FILE_REPO from metagpt.logs import logger from metagpt.schema import RunCodeContext, RunCodeResult from metagpt.utils.common import CodeParser @@ -50,9 +49,7 @@ class DebugError(Action): i_context: RunCodeContext = Field(default_factory=RunCodeContext) async def run(self, *args, **kwargs) -> str: - output_doc = await self.file_repo.get_file( - filename=self.i_context.output_filename, relative_path=TEST_OUTPUTS_FILE_REPO - ) + output_doc = await self.project_repo.test_outputs.get(filename=self.i_context.output_filename) if not output_doc: return "" output_detail = RunCodeResult.loads(output_doc.content) @@ -62,14 +59,12 @@ class DebugError(Action): return "" logger.info(f"Debug and rewrite {self.i_context.test_filename}") - code_doc = await self.file_repo.get_file( - filename=self.i_context.code_filename, relative_path=self.context.src_workspace + code_doc = await self.project_repo.with_src_path(self.context.src_workspace).srcs.get( + filename=self.i_context.code_filename ) if not code_doc: return "" - test_doc = await self.file_repo.get_file( - filename=self.i_context.test_filename, relative_path=TEST_CODES_FILE_REPO - ) + test_doc = await self.project_repo.tests.get(filename=self.i_context.test_filename) if not test_doc: return "" prompt = PROMPT_TEMPLATE.format(code=code_doc.content, test_code=test_doc.content, logs=output_detail.stderr) diff --git a/metagpt/actions/design_api.py b/metagpt/actions/design_api.py index 5f973bb60..04c580226 100644 --- a/metagpt/actions/design_api.py +++ b/metagpt/actions/design_api.py @@ -15,13 +15,7 @@ from typing import Optional from metagpt.actions import Action, ActionOutput from metagpt.actions.design_api_an import DESIGN_API_NODE -from metagpt.const import ( - DATA_API_DESIGN_FILE_REPO, - PRDS_FILE_REPO, - SEQ_FLOW_FILE_REPO, - SYSTEM_DESIGN_FILE_REPO, - SYSTEM_DESIGN_PDF_FILE_REPO, -) +from metagpt.const import DATA_API_DESIGN_FILE_REPO, SEQ_FLOW_FILE_REPO from metagpt.logs import logger from metagpt.schema import Document, Documents, Message from metagpt.utils.mermaid import mermaid_to_file @@ -46,27 +40,21 @@ class WriteDesign(Action): async def run(self, with_messages: Message, schema: str = None): # Use `git status` to identify which PRD documents have been modified in the `docs/prds` directory. - prds_file_repo = self.git_repo.new_file_repository(PRDS_FILE_REPO) - changed_prds = prds_file_repo.changed_files + changed_prds = self.project_repo.docs.prd.changed_files # Use `git status` to identify which design documents in the `docs/system_designs` directory have undergone # changes. - system_design_file_repo = self.git_repo.new_file_repository(SYSTEM_DESIGN_FILE_REPO) - changed_system_designs = system_design_file_repo.changed_files + changed_system_designs = self.project_repo.docs.system_design.changed_files # For those PRDs and design documents that have undergone changes, regenerate the design content. changed_files = Documents() for filename in changed_prds.keys(): - doc = await self._update_system_design( - filename=filename, prds_file_repo=prds_file_repo, system_design_file_repo=system_design_file_repo - ) + doc = await self._update_system_design(filename=filename) changed_files.docs[filename] = doc for filename in changed_system_designs.keys(): if filename in changed_files.docs: continue - doc = await self._update_system_design( - filename=filename, prds_file_repo=prds_file_repo, system_design_file_repo=system_design_file_repo - ) + doc = await self._update_system_design(filename=filename) changed_files.docs[filename] = doc if not changed_files.docs: logger.info("Nothing has changed.") @@ -84,24 +72,22 @@ class WriteDesign(Action): system_design_doc.content = node.instruct_content.model_dump_json() return system_design_doc - async def _update_system_design(self, filename, prds_file_repo, system_design_file_repo) -> Document: - prd = await prds_file_repo.get(filename) - old_system_design_doc = await system_design_file_repo.get(filename) + async def _update_system_design(self, filename) -> Document: + prd = await self.project_repo.docs.prd.get(filename) + old_system_design_doc = await self.project_repo.docs.system_design.get(filename) if not old_system_design_doc: system_design = await self._new_system_design(context=prd.content) - doc = Document( - root_path=SYSTEM_DESIGN_FILE_REPO, + doc = await self.project_repo.docs.system_design.save( filename=filename, content=system_design.instruct_content.model_dump_json(), + dependencies={prd.root_relative_path}, ) else: doc = await self._merge(prd_doc=prd, system_design_doc=old_system_design_doc) - await system_design_file_repo.save( - filename=filename, content=doc.content, dependencies={prd.root_relative_path} - ) + await self.project_repo.docs.system_design.save_doc(doc=doc, dependencies={prd.root_relative_path}) await self._save_data_api_design(doc) await self._save_seq_flow(doc) - await self._save_pdf(doc) + await self.project_repo.resources.system_design.save_pdf(doc=doc) return doc async def _save_data_api_design(self, design_doc): @@ -109,7 +95,7 @@ class WriteDesign(Action): data_api_design = m.get("Data structures and interfaces") if not data_api_design: return - pathname = self.git_repo.workdir / DATA_API_DESIGN_FILE_REPO / Path(design_doc.filename).with_suffix("") + pathname = self.project_repo.workdir / DATA_API_DESIGN_FILE_REPO / Path(design_doc.filename).with_suffix("") await self._save_mermaid_file(data_api_design, pathname) logger.info(f"Save class view to {str(pathname)}") @@ -118,13 +104,10 @@ class WriteDesign(Action): seq_flow = m.get("Program call flow") if not seq_flow: return - pathname = self.git_repo.workdir / Path(SEQ_FLOW_FILE_REPO) / Path(design_doc.filename).with_suffix("") + pathname = self.project_repo.workdir / Path(SEQ_FLOW_FILE_REPO) / Path(design_doc.filename).with_suffix("") await self._save_mermaid_file(seq_flow, pathname) logger.info(f"Saving sequence flow to {str(pathname)}") - async def _save_pdf(self, design_doc): - await self.file_repo.save_as(doc=design_doc, with_suffix=".md", relative_path=SYSTEM_DESIGN_PDF_FILE_REPO) - async def _save_mermaid_file(self, data: str, pathname: Path): pathname.parent.mkdir(parents=True, exist_ok=True) await mermaid_to_file(self.config.mermaid_engine, data, pathname) diff --git a/metagpt/actions/prepare_documents.py b/metagpt/actions/prepare_documents.py index 8a9e78b2a..56c587cb3 100644 --- a/metagpt/actions/prepare_documents.py +++ b/metagpt/actions/prepare_documents.py @@ -12,8 +12,7 @@ from pathlib import Path from typing import Optional from metagpt.actions import Action, ActionOutput -from metagpt.const import DOCS_FILE_REPO, REQUIREMENT_FILENAME -from metagpt.schema import Document +from metagpt.const import REQUIREMENT_FILENAME from metagpt.utils.file_repository import FileRepository from metagpt.utils.git_repository import GitRepository @@ -38,7 +37,6 @@ class PrepareDocuments(Action): if path.exists() and not self.config.inc: shutil.rmtree(path) self.config.project_path = path - self.config.project_name = path.name self.context.git_repo = GitRepository(local_path=path, auto_init=True) async def run(self, with_messages, **kwargs): @@ -46,9 +44,7 @@ class PrepareDocuments(Action): self._init_repo() # Write the newly added requirements from the main parameter idea to `docs/requirement.txt`. - doc = Document(root_path=DOCS_FILE_REPO, filename=REQUIREMENT_FILENAME, content=with_messages[0].content) - await self.file_repo.save_file(filename=REQUIREMENT_FILENAME, content=doc.content, relative_path=DOCS_FILE_REPO) - + doc = await self.project_repo.docs.save(filename=REQUIREMENT_FILENAME, content=with_messages[0].content) # Send a Message notification to the WritePRD action, instructing it to process requirements using # `docs/requirement.txt` and `docs/prds/`. return ActionOutput(content=doc.content, instruct_content=doc) diff --git a/metagpt/actions/project_management.py b/metagpt/actions/project_management.py index bb8141a74..9ada629be 100644 --- a/metagpt/actions/project_management.py +++ b/metagpt/actions/project_management.py @@ -16,12 +16,7 @@ from typing import Optional from metagpt.actions import ActionOutput from metagpt.actions.action import Action from metagpt.actions.project_management_an import PM_NODE -from metagpt.const import ( - PACKAGE_REQUIREMENTS_FILENAME, - SYSTEM_DESIGN_FILE_REPO, - TASK_FILE_REPO, - TASK_PDF_FILE_REPO, -) +from metagpt.const import PACKAGE_REQUIREMENTS_FILENAME from metagpt.logs import logger from metagpt.schema import Document, Documents @@ -39,27 +34,20 @@ class WriteTasks(Action): i_context: Optional[str] = None async def run(self, with_messages): - system_design_file_repo = self.git_repo.new_file_repository(SYSTEM_DESIGN_FILE_REPO) - changed_system_designs = system_design_file_repo.changed_files - - tasks_file_repo = self.git_repo.new_file_repository(TASK_FILE_REPO) - changed_tasks = tasks_file_repo.changed_files + changed_system_designs = self.project_repo.docs.system_design.changed_files + changed_tasks = self.project_repo.docs.task.changed_files change_files = Documents() # Rewrite the system designs that have undergone changes based on the git head diff under # `docs/system_designs/`. for filename in changed_system_designs: - task_doc = await self._update_tasks( - filename=filename, system_design_file_repo=system_design_file_repo, tasks_file_repo=tasks_file_repo - ) + task_doc = await self._update_tasks(filename=filename) change_files.docs[filename] = task_doc # Rewrite the task files that have undergone changes based on the git head diff under `docs/tasks/`. for filename in changed_tasks: if filename in change_files.docs: continue - task_doc = await self._update_tasks( - filename=filename, system_design_file_repo=system_design_file_repo, tasks_file_repo=tasks_file_repo - ) + task_doc = await self._update_tasks(filename=filename) change_files.docs[filename] = task_doc if not change_files.docs: @@ -68,21 +56,22 @@ class WriteTasks(Action): # global optimization in subsequent steps. return ActionOutput(content=change_files.model_dump_json(), instruct_content=change_files) - async def _update_tasks(self, filename, system_design_file_repo, tasks_file_repo): - system_design_doc = await system_design_file_repo.get(filename) - task_doc = await tasks_file_repo.get(filename) + async def _update_tasks(self, filename): + system_design_doc = await self.project_repo.docs.system_design.get(filename) + task_doc = await self.project_repo.docs.task.get(filename) if task_doc: task_doc = await self._merge(system_design_doc=system_design_doc, task_doc=task_doc) + await self.project_repo.docs.task.save_doc( + doc=task_doc, dependencies={system_design_doc.root_relative_path} + ) else: rsp = await self._run_new_tasks(context=system_design_doc.content) - task_doc = Document( - root_path=TASK_FILE_REPO, filename=filename, content=rsp.instruct_content.model_dump_json() + task_doc = await self.project_repo.docs.task.save( + filename=filename, + content=rsp.instruct_content.model_dump_json(), + dependencies={system_design_doc.root_relative_path}, ) - await tasks_file_repo.save( - filename=filename, content=task_doc.content, dependencies={system_design_doc.root_relative_path} - ) await self._update_requirements(task_doc) - await self._save_pdf(task_doc=task_doc) return task_doc async def _run_new_tasks(self, context): @@ -98,8 +87,7 @@ class WriteTasks(Action): async def _update_requirements(self, doc): m = json.loads(doc.content) packages = set(m.get("Required Python third-party packages", set())) - file_repo = self.git_repo.new_file_repository() - requirement_doc = await file_repo.get(filename=PACKAGE_REQUIREMENTS_FILENAME) + requirement_doc = await self.project_repo.get(filename=PACKAGE_REQUIREMENTS_FILENAME) if not requirement_doc: requirement_doc = Document(filename=PACKAGE_REQUIREMENTS_FILENAME, root_path=".", content="") lines = requirement_doc.content.splitlines() @@ -107,7 +95,4 @@ class WriteTasks(Action): if pkg == "": continue packages.add(pkg) - await file_repo.save(PACKAGE_REQUIREMENTS_FILENAME, content="\n".join(packages)) - - async def _save_pdf(self, task_doc): - await self.file_repo.save_as(doc=task_doc, with_suffix=".md", relative_path=TASK_PDF_FILE_REPO) + await self.project_repo.save(filename=PACKAGE_REQUIREMENTS_FILENAME, content="\n".join(packages)) diff --git a/metagpt/actions/summarize_code.py b/metagpt/actions/summarize_code.py index dde41d3c6..182561d59 100644 --- a/metagpt/actions/summarize_code.py +++ b/metagpt/actions/summarize_code.py @@ -11,7 +11,6 @@ from pydantic import Field from tenacity import retry, stop_after_attempt, wait_random_exponential from metagpt.actions.action import Action -from metagpt.const import SYSTEM_DESIGN_FILE_REPO, TASK_FILE_REPO from metagpt.logs import logger from metagpt.schema import CodeSummarizeContext @@ -99,11 +98,10 @@ class SummarizeCode(Action): async def run(self): design_pathname = Path(self.i_context.design_filename) - repo = self.file_repo - design_doc = await repo.get_file(filename=design_pathname.name, relative_path=SYSTEM_DESIGN_FILE_REPO) + design_doc = await self.project_repo.docs.system_design.get(filename=design_pathname.name) task_pathname = Path(self.i_context.task_filename) - task_doc = await repo.get_file(filename=task_pathname.name, relative_path=TASK_FILE_REPO) - src_file_repo = self.git_repo.new_file_repository(relative_path=self.context.src_workspace) + task_doc = await self.project_repo.docs.task.get(filename=task_pathname.name) + src_file_repo = self.project_repo.with_src_path(self.context.src_workspace).srcs code_blocks = [] for filename in self.i_context.codes_filenames: code_doc = await src_file_repo.get(filename) diff --git a/metagpt/actions/write_code.py b/metagpt/actions/write_code.py index 1b3dcf5f0..c0f1b1a93 100644 --- a/metagpt/actions/write_code.py +++ b/metagpt/actions/write_code.py @@ -21,13 +21,7 @@ from pydantic import Field from tenacity import retry, stop_after_attempt, wait_random_exponential from metagpt.actions.action import Action -from metagpt.const import ( - BUGFIX_FILENAME, - CODE_SUMMARIES_FILE_REPO, - DOCS_FILE_REPO, - TASK_FILE_REPO, - TEST_OUTPUTS_FILE_REPO, -) +from metagpt.const import BUGFIX_FILENAME from metagpt.logs import logger from metagpt.schema import CodingContext, Document, RunCodeResult from metagpt.utils.common import CodeParser @@ -94,16 +88,12 @@ class WriteCode(Action): return code async def run(self, *args, **kwargs) -> CodingContext: - bug_feedback = await self.file_repo.get_file(filename=BUGFIX_FILENAME, relative_path=DOCS_FILE_REPO) + bug_feedback = await self.project_repo.docs.get(filename=BUGFIX_FILENAME) coding_context = CodingContext.loads(self.i_context.content) - test_doc = await self.file_repo.get_file( - filename="test_" + coding_context.filename + ".json", relative_path=TEST_OUTPUTS_FILE_REPO - ) + test_doc = await self.project_repo.test_outputs.get(filename="test_" + coding_context.filename + ".json") summary_doc = None if coding_context.design_doc and coding_context.design_doc.filename: - summary_doc = await self.file_repo.get_file( - filename=coding_context.design_doc.filename, relative_path=CODE_SUMMARIES_FILE_REPO - ) + summary_doc = await self.project_repo.docs.code_summary.get(filename=coding_context.design_doc.filename) logs = "" if test_doc: test_detail = RunCodeResult.loads(test_doc.content) @@ -115,8 +105,7 @@ class WriteCode(Action): code_context = await self.get_codes( coding_context.task_doc, exclude=self.i_context.filename, - git_repo=self.git_repo, - src_workspace=self.context.src_workspace, + project_repo=self.project_repo.with_src_path(self.context.src_workspace), ) prompt = PROMPT_TEMPLATE.format( @@ -138,16 +127,15 @@ class WriteCode(Action): return coding_context @staticmethod - async def get_codes(task_doc, exclude, git_repo, src_workspace) -> str: + async def get_codes(task_doc, exclude, project_repo) -> str: if not task_doc: return "" if not task_doc.content: - file_repo = git_repo.new_file_repository() - task_doc.content = file_repo.get_file(filename=task_doc.filename, relative_path=TASK_FILE_REPO) + task_doc = project_repo.docs.task.get(filename=task_doc.filename) m = json.loads(task_doc.content) code_filenames = m.get("Task list", []) codes = [] - src_file_repo = git_repo.new_file_repository(relative_path=src_workspace) + src_file_repo = project_repo.srcs for filename in code_filenames: if filename == exclude: continue diff --git a/metagpt/actions/write_code_review.py b/metagpt/actions/write_code_review.py index b25f1ab69..21281dde1 100644 --- a/metagpt/actions/write_code_review.py +++ b/metagpt/actions/write_code_review.py @@ -143,8 +143,7 @@ class WriteCodeReview(Action): code_context = await WriteCode.get_codes( self.i_context.task_doc, exclude=self.i_context.filename, - git_repo=self.context.git_repo, - src_workspace=self.src_workspace, + project_repo=self.project_repo.with_src_path(self.context.src_workspace), ) context = "\n".join( [ diff --git a/metagpt/actions/write_prd.py b/metagpt/actions/write_prd.py index a838dea8e..38ac62536 100644 --- a/metagpt/actions/write_prd.py +++ b/metagpt/actions/write_prd.py @@ -29,9 +29,6 @@ from metagpt.actions.write_prd_an import ( from metagpt.const import ( BUGFIX_FILENAME, COMPETITIVE_ANALYSIS_FILE_REPO, - DOCS_FILE_REPO, - PRD_PDF_FILE_REPO, - PRDS_FILE_REPO, REQUIREMENT_FILENAME, ) from metagpt.logs import logger @@ -67,11 +64,10 @@ class WritePRD(Action): async def run(self, with_messages, *args, **kwargs) -> ActionOutput | Message: # Determine which requirement documents need to be rewritten: Use LLM to assess whether new requirements are # related to the PRD. If they are related, rewrite the PRD. - docs_file_repo = self.git_repo.new_file_repository(relative_path=DOCS_FILE_REPO) - requirement_doc = await docs_file_repo.get(filename=REQUIREMENT_FILENAME) + requirement_doc = await self.project_repo.docs.get(filename=REQUIREMENT_FILENAME) if requirement_doc and await self._is_bugfix(requirement_doc.content): - await docs_file_repo.save(filename=BUGFIX_FILENAME, content=requirement_doc.content) - await docs_file_repo.save(filename=REQUIREMENT_FILENAME, content="") + await self.project_repo.docs.save(filename=BUGFIX_FILENAME, content=requirement_doc.content) + await self.project_repo.docs.save(filename=REQUIREMENT_FILENAME, content="") bug_fix = BugFixContext(filename=BUGFIX_FILENAME) return Message( content=bug_fix.model_dump_json(), @@ -82,24 +78,19 @@ class WritePRD(Action): send_to="Alex", # the name of Engineer ) else: - await docs_file_repo.delete(filename=BUGFIX_FILENAME) + await self.project_repo.docs.delete(filename=BUGFIX_FILENAME) - prds_file_repo = self.git_repo.new_file_repository(PRDS_FILE_REPO) - prd_docs = await prds_file_repo.get_all() + prd_docs = await self.project_repo.docs.prd.get_all() change_files = Documents() for prd_doc in prd_docs: - prd_doc = await self._update_prd( - requirement_doc=requirement_doc, prd_doc=prd_doc, prds_file_repo=prds_file_repo, *args, **kwargs - ) + prd_doc = await self._update_prd(requirement_doc=requirement_doc, prd_doc=prd_doc, *args, **kwargs) if not prd_doc: continue change_files.docs[prd_doc.filename] = prd_doc logger.info(f"rewrite prd: {prd_doc.filename}") # If there is no existing PRD, generate one using 'docs/requirement.txt'. if not change_files.docs: - prd_doc = await self._update_prd( - requirement_doc=requirement_doc, prd_doc=None, prds_file_repo=prds_file_repo, *args, **kwargs - ) + prd_doc = await self._update_prd(requirement_doc=requirement_doc, *args, **kwargs) if prd_doc: change_files.docs[prd_doc.filename] = prd_doc logger.debug(f"new prd: {prd_doc.filename}") @@ -109,13 +100,6 @@ class WritePRD(Action): return ActionOutput(content=change_files.model_dump_json(), instruct_content=change_files) async def _run_new_requirement(self, requirements) -> ActionOutput: - # sas = SearchAndSummarize() - # # rsp = await sas.run(context=requirements, system_text=SEARCH_AND_SUMMARIZE_SYSTEM_EN_US) - # rsp = "" - # info = f"### Search Results\n{sas.result}\n\n### Search Summary\n{rsp}" - # if sas.result: - # logger.info(sas.result) - # logger.info(rsp) project_name = self.project_name context = CONTEXT_TEMPLATE.format(requirements=requirements, project_name=project_name) exclude = [PROJECT_NAME.key] if project_name else [] @@ -137,23 +121,21 @@ class WritePRD(Action): await self._rename_workspace(node) return prd_doc - async def _update_prd(self, requirement_doc, prd_doc, prds_file_repo, *args, **kwargs) -> Document | None: + async def _update_prd(self, requirement_doc, prd_doc=None, *args, **kwargs) -> Document | None: if not prd_doc: prd = await self._run_new_requirement( requirements=[requirement_doc.content if requirement_doc else ""], *args, **kwargs ) - new_prd_doc = Document( - root_path=PRDS_FILE_REPO, - filename=FileRepository.new_filename() + ".json", - content=prd.instruct_content.model_dump_json(), + new_prd_doc = await self.project_repo.docs.prd.save( + filename=FileRepository.new_filename() + ".json", content=prd.instruct_content.model_dump_json() ) elif await self._is_relative(requirement_doc, prd_doc): new_prd_doc = await self._merge(requirement_doc, prd_doc) + self.project_repo.docs.prd.save_doc(doc=new_prd_doc) else: return None - await prds_file_repo.save(filename=new_prd_doc.filename, content=new_prd_doc.content) await self._save_competitive_analysis(new_prd_doc) - await self._save_pdf(new_prd_doc) + await self.project_repo.resources.prd.save_pdf(doc=new_prd_doc) return new_prd_doc async def _save_competitive_analysis(self, prd_doc): @@ -161,14 +143,13 @@ class WritePRD(Action): quadrant_chart = m.get("Competitive Quadrant Chart") if not quadrant_chart: return - pathname = self.git_repo.workdir / Path(COMPETITIVE_ANALYSIS_FILE_REPO) / Path(prd_doc.filename).with_suffix("") + pathname = ( + self.project_repo.workdir / Path(COMPETITIVE_ANALYSIS_FILE_REPO) / Path(prd_doc.filename).with_suffix("") + ) if not pathname.parent.exists(): pathname.parent.mkdir(parents=True, exist_ok=True) await mermaid_to_file(self.config.mermaid_engine, quadrant_chart, pathname) - async def _save_pdf(self, prd_doc): - await self.file_repo.save_as(doc=prd_doc, with_suffix=".md", relative_path=PRD_PDF_FILE_REPO) - async def _rename_workspace(self, prd): if not self.project_name: if isinstance(prd, (ActionOutput, ActionNode)): @@ -177,11 +158,14 @@ class WritePRD(Action): ws_name = CodeParser.parse_str(block="Project Name", text=prd) if ws_name: self.project_name = ws_name - self.git_repo.rename_root(self.project_name) + self.project_repo.git_repo.rename_root(self.project_name) async def _is_bugfix(self, context) -> bool: - src_workspace_path = self.git_repo.workdir / self.git_repo.workdir.name - code_files = self.git_repo.get_files(relative_path=src_workspace_path) + git_workdir = self.project_repo.git_repo.workdir + src_workdir = git_workdir / git_workdir.name + if not src_workdir.exists(): + return False + code_files = self.project_repo.with_src_path(path=git_workdir / git_workdir.name).srcs.all_files if not code_files: return False node = await WP_ISSUE_TYPE_NODE.fill(context, self.llm) diff --git a/metagpt/roles/engineer.py b/metagpt/roles/engineer.py index bc56ca813..20dcce181 100644 --- a/metagpt/roles/engineer.py +++ b/metagpt/roles/engineer.py @@ -27,12 +27,7 @@ from typing import Set from metagpt.actions import Action, WriteCode, WriteCodeReview, WriteTasks from metagpt.actions.fix_bug import FixBug from metagpt.actions.summarize_code import SummarizeCode -from metagpt.const import ( - CODE_SUMMARIES_FILE_REPO, - CODE_SUMMARIES_PDF_FILE_REPO, - SYSTEM_DESIGN_FILE_REPO, - TASK_FILE_REPO, -) +from metagpt.const import SYSTEM_DESIGN_FILE_REPO, TASK_FILE_REPO from metagpt.logs import logger from metagpt.roles import Role from metagpt.schema import ( @@ -97,7 +92,6 @@ class Engineer(Role): async def _act_sp_with_cr(self, review=False) -> Set[str]: changed_files = set() - src_file_repo = self.git_repo.new_file_repository(self.src_workspace) for todo in self.code_todos: """ # Select essential information from the historical data to reduce the length of the prompt (summarized from human experience): @@ -112,8 +106,8 @@ class Engineer(Role): action = WriteCodeReview(i_context=coding_context, context=self.context, llm=self.llm) self._init_action_system_message(action) coding_context = await action.run() - await src_file_repo.save( - coding_context.filename, + await self.project_repo.srcs.save( + filename=coding_context.filename, dependencies={coding_context.design_doc.root_relative_path, coding_context.task_doc.root_relative_path}, content=coding_context.code_doc.content, ) @@ -153,31 +147,28 @@ class Engineer(Role): ) async def _act_summarize(self): - code_summaries_file_repo = self.git_repo.new_file_repository(CODE_SUMMARIES_FILE_REPO) - code_summaries_pdf_file_repo = self.git_repo.new_file_repository(CODE_SUMMARIES_PDF_FILE_REPO) tasks = [] - src_relative_path = self.src_workspace.relative_to(self.git_repo.workdir) for todo in self.summarize_todos: summary = await todo.run() summary_filename = Path(todo.i_context.design_filename).with_suffix(".md").name dependencies = {todo.i_context.design_filename, todo.i_context.task_filename} for filename in todo.i_context.codes_filenames: - rpath = src_relative_path / filename + rpath = self.project_repo.src_relative_path / filename dependencies.add(str(rpath)) - await code_summaries_pdf_file_repo.save( + await self.project_repo.resources.code_summary.save( filename=summary_filename, content=summary, dependencies=dependencies ) is_pass, reason = await self._is_pass(summary) if not is_pass: todo.i_context.reason = reason tasks.append(todo.i_context.dict()) - await code_summaries_file_repo.save( + await self.project_repo.docs.code_summary.save( filename=Path(todo.i_context.design_filename).name, content=todo.i_context.model_dump_json(), dependencies=dependencies, ) else: - await code_summaries_file_repo.delete(filename=Path(todo.i_context.design_filename).name) + await self.project_repo.docs.code_summary.delete(filename=Path(todo.i_context.design_filename).name) logger.info(f"--max-auto-summarize-code={self.config.max_auto_summarize_code}") if not tasks or self.config.max_auto_summarize_code == 0: @@ -220,60 +211,54 @@ class Engineer(Role): return self.rc.todo return None - @staticmethod - async def _new_coding_context( - filename, src_file_repo, task_file_repo, design_file_repo, dependency - ) -> CodingContext: - old_code_doc = await src_file_repo.get(filename) + async def _new_coding_context(self, filename, dependency) -> CodingContext: + old_code_doc = await self.project_repo.srcs.get(filename) if not old_code_doc: - old_code_doc = Document(root_path=str(src_file_repo.root_path), filename=filename, content="") + old_code_doc = Document(root_path=str(self.project_repo.src_relative_path), filename=filename, content="") dependencies = {Path(i) for i in await dependency.get(old_code_doc.root_relative_path)} task_doc = None design_doc = None for i in dependencies: if str(i.parent) == TASK_FILE_REPO: - task_doc = await task_file_repo.get(i.name) + task_doc = await self.project_repo.docs.task.get(i.name) elif str(i.parent) == SYSTEM_DESIGN_FILE_REPO: - design_doc = await design_file_repo.get(i.name) + design_doc = await self.project_repo.docs.system_design.get(i.name) if not task_doc or not design_doc: logger.error(f'Detected source code "{filename}" from an unknown origin.') raise ValueError(f'Detected source code "{filename}" from an unknown origin.') context = CodingContext(filename=filename, design_doc=design_doc, task_doc=task_doc, code_doc=old_code_doc) return context - @staticmethod - async def _new_coding_doc(filename, src_file_repo, task_file_repo, design_file_repo, dependency): - context = await Engineer._new_coding_context( - filename, src_file_repo, task_file_repo, design_file_repo, dependency - ) + async def _new_coding_doc(self, filename, dependency): + context = await self._new_coding_context(filename, dependency) coding_doc = Document( - root_path=str(src_file_repo.root_path), filename=filename, content=context.model_dump_json() + root_path=str(self.project_repo.src_relative_path), filename=filename, content=context.model_dump_json() ) return coding_doc async def _new_code_actions(self, bug_fix=False): # Prepare file repos - src_file_repo = self.git_repo.new_file_repository(self.src_workspace) - changed_src_files = src_file_repo.all_files if bug_fix else src_file_repo.changed_files - task_file_repo = self.git_repo.new_file_repository(TASK_FILE_REPO) - changed_task_files = task_file_repo.changed_files - design_file_repo = self.git_repo.new_file_repository(SYSTEM_DESIGN_FILE_REPO) - + changed_src_files = self.project_repo.srcs.all_files if bug_fix else self.project_repo.srcs.changed_files + changed_task_files = self.project_repo.docs.task.changed_files changed_files = Documents() # Recode caused by upstream changes. for filename in changed_task_files: - design_doc = await design_file_repo.get(filename) - task_doc = await task_file_repo.get(filename) + design_doc = await self.project_repo.docs.system_design.get(filename) + task_doc = await self.project_repo.docs.task.get(filename) task_list = self._parse_tasks(task_doc) for task_filename in task_list: - old_code_doc = await src_file_repo.get(task_filename) + old_code_doc = await self.project_repo.srcs.get(task_filename) if not old_code_doc: - old_code_doc = Document(root_path=str(src_file_repo.root_path), filename=task_filename, content="") + old_code_doc = Document( + root_path=str(self.project_repo.src_relative_path), filename=task_filename, content="" + ) context = CodingContext( filename=task_filename, design_doc=design_doc, task_doc=task_doc, code_doc=old_code_doc ) coding_doc = Document( - root_path=str(src_file_repo.root_path), filename=task_filename, content=context.model_dump_json() + root_path=str(self.project_repo.src_relative_path), + filename=task_filename, + content=context.model_dump_json(), ) if task_filename in changed_files.docs: logger.warning( @@ -289,13 +274,7 @@ class Engineer(Role): for filename in changed_src_files: if filename in changed_files.docs: continue - coding_doc = await self._new_coding_doc( - filename=filename, - src_file_repo=src_file_repo, - task_file_repo=task_file_repo, - design_file_repo=design_file_repo, - dependency=dependency, - ) + coding_doc = await self._new_coding_doc(filename=filename, dependency=dependency) changed_files.docs[filename] = coding_doc self.code_todos.append(WriteCode(i_context=coding_doc, context=self.context, llm=self.llm)) @@ -303,13 +282,12 @@ class Engineer(Role): self.set_todo(self.code_todos[0]) async def _new_summarize_actions(self): - src_file_repo = self.git_repo.new_file_repository(self.src_workspace) - src_files = src_file_repo.all_files + src_files = self.project_repo.srcs.all_files # Generate a SummarizeCode action for each pair of (system_design_doc, task_doc). summarizations = defaultdict(list) for filename in src_files: - dependencies = await src_file_repo.get_dependency(filename=filename) - ctx = CodeSummarizeContext.loads(filenames=dependencies) + dependencies = await self.project_repo.srcs.get_dependency(filename=filename) + ctx = CodeSummarizeContext.loads(filenames=list(dependencies)) summarizations[ctx].append(filename) for ctx, filenames in summarizations.items(): ctx.codes_filenames = filenames diff --git a/metagpt/roles/qa_engineer.py b/metagpt/roles/qa_engineer.py index cd043b551..949085fe9 100644 --- a/metagpt/roles/qa_engineer.py +++ b/metagpt/roles/qa_engineer.py @@ -17,11 +17,7 @@ from metagpt.actions import DebugError, RunCode, WriteTest from metagpt.actions.summarize_code import SummarizeCode -from metagpt.const import ( - MESSAGE_ROUTE_TO_NONE, - TEST_CODES_FILE_REPO, - TEST_OUTPUTS_FILE_REPO, -) +from metagpt.const import MESSAGE_ROUTE_TO_NONE, TEST_CODES_FILE_REPO from metagpt.logs import logger from metagpt.roles import Role from metagpt.schema import Document, Message, RunCodeContext, TestingContext @@ -48,37 +44,32 @@ class QaEngineer(Role): self.test_round = 0 async def _write_test(self, message: Message) -> None: - src_file_repo = self.context.git_repo.new_file_repository(self.context.src_workspace) + src_file_repo = self.project_repo.with_src_path(self.context.src_workspace).srcs changed_files = set(src_file_repo.changed_files.keys()) # Unit tests only. if self.config.reqa_file and self.config.reqa_file not in changed_files: changed_files.add(self.config.reqa_file) - tests_file_repo = self.context.git_repo.new_file_repository(TEST_CODES_FILE_REPO) for filename in changed_files: # write tests if not filename or "test" in filename: continue code_doc = await src_file_repo.get(filename) - test_doc = await tests_file_repo.get("test_" + code_doc.filename) + test_doc = await self.project_repo.tests.get("test_" + code_doc.filename) if not test_doc: test_doc = Document( - root_path=str(tests_file_repo.root_path), filename="test_" + code_doc.filename, content="" + root_path=str(self.project_repo.tests.root_path), filename="test_" + code_doc.filename, content="" ) logger.info(f"Writing {test_doc.filename}..") context = TestingContext(filename=test_doc.filename, test_doc=test_doc, code_doc=code_doc) context = await WriteTest(i_context=context, context=self.context, llm=self.llm).run() - await tests_file_repo.save( - filename=context.test_doc.filename, - content=context.test_doc.content, - dependencies={context.code_doc.root_relative_path}, - ) + await self.project_repo.tests.save_doc(doc=test_doc, dependencies={context.code_doc.root_relative_path}) # prepare context for run tests in next round run_code_context = RunCodeContext( command=["python", context.test_doc.root_relative_path], code_filename=context.code_doc.filename, test_filename=context.test_doc.filename, - working_directory=str(self.context.git_repo.workdir), + working_directory=str(self.project_repo.workdir), additional_python_paths=[str(self.context.src_workspace)], ) self.publish_message( @@ -91,25 +82,23 @@ class QaEngineer(Role): ) ) - logger.info(f"Done {str(tests_file_repo.workdir)} generating.") + logger.info(f"Done {str(self.project_repo.tests.workdir)} generating.") async def _run_code(self, msg): run_code_context = RunCodeContext.loads(msg.content) - src_doc = await self.context.git_repo.new_file_repository(self.context.src_workspace).get( + src_doc = await self.project_repo.with_src_path(self.context.src_workspace).srcs.get( run_code_context.code_filename ) if not src_doc: return - test_doc = await self.context.git_repo.new_file_repository(TEST_CODES_FILE_REPO).get( - run_code_context.test_filename - ) + test_doc = await self.project_repo.tests.get(run_code_context.test_filename) if not test_doc: return run_code_context.code = src_doc.content run_code_context.test_code = test_doc.content result = await RunCode(i_context=run_code_context, context=self.context, llm=self.llm).run() run_code_context.output_filename = run_code_context.test_filename + ".json" - await self.context.git_repo.new_file_repository(TEST_OUTPUTS_FILE_REPO).save( + await self.project_repo.test_outputs.save( filename=run_code_context.output_filename, content=result.model_dump_json(), dependencies={src_doc.root_relative_path, test_doc.root_relative_path}, @@ -132,7 +121,7 @@ class QaEngineer(Role): async def _debug_error(self, msg): run_code_context = RunCodeContext.loads(msg.content) code = await DebugError(i_context=run_code_context, context=self.context, llm=self.llm).run() - await self.context.file_repo.save_file( + await self.project_repo.tests.save( filename=run_code_context.test_filename, content=code, relative_path=TEST_CODES_FILE_REPO ) run_code_context.output = None diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py index e467ef83e..0ca353398 100644 --- a/metagpt/roles/role.py +++ b/metagpt/roles/role.py @@ -36,6 +36,7 @@ from metagpt.memory import Memory from metagpt.provider import HumanProvider from metagpt.schema import Message, MessageQueue, SerializationMixin from metagpt.utils.common import any_to_name, any_to_str, role_raise_decorator +from metagpt.utils.project_repo import ProjectRepo from metagpt.utils.repair_llm_raw_output import extract_state_value_from_output PREFIX_TEMPLATE = """You are a {profile}, named {name}, your goal is {goal}. """ @@ -188,6 +189,11 @@ class Role(SerializationMixin, ContextMixin, BaseModel): def src_workspace(self, value): self.context.src_workspace = value + @property + def project_repo(self) -> ProjectRepo: + project_repo = ProjectRepo(git_repo=self.context.git_repo) + return project_repo.with_src_path(self.context.src_workspace) if self.context.src_workspace else project_repo + @property def prompt_schema(self): """Prompt schema: json/markdown""" @@ -427,7 +433,7 @@ class Role(SerializationMixin, ContextMixin, BaseModel): break # act logger.debug(f"{self._setting}: {self.rc.state=}, will do {self.rc.todo}") - rsp = await self._act() # 这个rsp是否需要publish_message？ + rsp = await self._act() actions_taken += 1 return rsp # return output from the last action diff --git a/metagpt/utils/file_repository.py b/metagpt/utils/file_repository.py index 1cb347a19..85e7dc8a4 100644 --- a/metagpt/utils/file_repository.py +++ b/metagpt/utils/file_repository.py @@ -183,10 +183,20 @@ class FileRepository: """ current_time = datetime.now().strftime("%Y%m%d%H%M%S") return current_time - # guid_suffix = str(uuid.uuid4())[:8] - # return f"{current_time}x{guid_suffix}" - async def save_doc(self, doc: Document, with_suffix: str = None, dependencies: List[str] = None): + async def save_doc(self, doc: Document, dependencies: List[str] = None): + """Save content to a file and update its dependencies. + + :param doc: The Document instance to be saved. + :type doc: Document + :param dependencies: A list of dependencies for the saved file. + :type dependencies: List[str], optional + """ + + await self.save(filename=doc.filename, content=doc.content, dependencies=dependencies) + logger.debug(f"File Saved: {str(doc.filename)}") + + async def save_pdf(self, doc: Document, with_suffix: str = ".md", dependencies: List[str] = None): """Save a Document instance as a PDF file. This method converts the content of the Document instance to Markdown, diff --git a/metagpt/utils/git_repository.py b/metagpt/utils/git_repository.py index e9855df05..4feed89d5 100644 --- a/metagpt/utils/git_repository.py +++ b/metagpt/utils/git_repository.py @@ -199,10 +199,17 @@ class GitRepository: if new_path.exists(): logger.info(f"Delete directory {str(new_path)}") shutil.rmtree(new_path) + if new_path.exists(): # Recheck for windows os + logger.warning(f"Failed to delete directory {str(new_path)}") + return try: shutil.move(src=str(self.workdir), dst=str(new_path)) except Exception as e: logger.warning(f"Move {str(self.workdir)} to {str(new_path)} error: {e}") + finally: + if not new_path.exists(): # Recheck for windows os + logger.warning(f"Failed to move {str(self.workdir)} to {str(new_path)}") + return logger.info(f"Rename directory {str(self.workdir)} to {str(new_path)}") self._repository = Repo(new_path) self._gitignore_rules = parse_gitignore(full_path=str(new_path / ".gitignore")) diff --git a/metagpt/utils/project_repo.py b/metagpt/utils/project_repo.py index deedd6c03..71cb9d55d 100644 --- a/metagpt/utils/project_repo.py +++ b/metagpt/utils/project_repo.py @@ -17,9 +17,11 @@ from metagpt.const import ( CODE_SUMMARIES_PDF_FILE_REPO, COMPETITIVE_ANALYSIS_FILE_REPO, DATA_API_DESIGN_FILE_REPO, + DOCS_FILE_REPO, GRAPH_REPO_FILE_REPO, PRD_PDF_FILE_REPO, PRDS_FILE_REPO, + RESOURCES_FILE_REPO, SD_OUTPUT_FILE_REPO, SEQ_FLOW_FILE_REPO, SYSTEM_DESIGN_FILE_REPO, @@ -33,7 +35,7 @@ from metagpt.utils.file_repository import FileRepository from metagpt.utils.git_repository import GitRepository -class DocFileRepositories: +class DocFileRepositories(FileRepository): prd: FileRepository system_design: FileRepository task: FileRepository @@ -42,6 +44,8 @@ class DocFileRepositories: class_view: FileRepository def __init__(self, git_repo): + super().__init__(git_repo=git_repo, relative_path=DOCS_FILE_REPO) + self.prd = git_repo.new_file_repository(relative_path=PRDS_FILE_REPO) self.system_design = git_repo.new_file_repository(relative_path=SYSTEM_DESIGN_FILE_REPO) self.task = git_repo.new_file_repository(relative_path=TASK_FILE_REPO) @@ -50,7 +54,7 @@ class DocFileRepositories: self.class_view = git_repo.new_file_repository(relative_path=CLASS_VIEW_FILE_REPO) -class ResourceFileRepositories: +class ResourceFileRepositories(FileRepository): competitive_analysis: FileRepository data_api_design: FileRepository seq_flow: FileRepository @@ -61,6 +65,8 @@ class ResourceFileRepositories: sd_output: FileRepository def __init__(self, git_repo): + super().__init__(git_repo=git_repo, relative_path=RESOURCES_FILE_REPO) + self.competitive_analysis = git_repo.new_file_repository(relative_path=COMPETITIVE_ANALYSIS_FILE_REPO) self.data_api_design = git_repo.new_file_repository(relative_path=DATA_API_DESIGN_FILE_REPO) self.seq_flow = git_repo.new_file_repository(relative_path=SEQ_FLOW_FILE_REPO) @@ -72,16 +78,40 @@ class ResourceFileRepositories: class ProjectRepo(FileRepository): - def __init__(self, root: str | Path): - git_repo = GitRepository(local_path=Path(root)) - super().__init__(git_repo=git_repo, relative_path=Path(".")) + def __init__(self, root: str | Path = None, git_repo: GitRepository = None): + if not root and not git_repo: + raise ValueError("Invalid root and git_repo") + git_repo_ = git_repo or GitRepository(local_path=Path(root)) + super().__init__(git_repo=git_repo_, relative_path=Path(".")) - self._git_repo = git_repo + self._git_repo = git_repo_ self.docs = DocFileRepositories(self._git_repo) self.resources = ResourceFileRepositories(self._git_repo) self.tests = self._git_repo.new_file_repository(relative_path=TEST_CODES_FILE_REPO) self.test_outputs = self._git_repo.new_file_repository(relative_path=TEST_OUTPUTS_FILE_REPO) + self._srcs_path = None @property - def git_repo(self): + def git_repo(self) -> GitRepository: return self._git_repo + + @property + def workdir(self) -> Path: + return Path(self.git_repo.workdir) + + @property + def srcs(self) -> FileRepository: + if not self._srcs_path: + raise ValueError("Call with_srcs first.") + return self._git_repo.new_file_repository(self._srcs_path) + + def with_src_path(self, path: str | Path) -> ProjectRepo: + try: + self._srcs_path = Path(path).relative_to(self.workdir) + except ValueError: + self._srcs_path = Path(path) + return self + + @property + def src_relative_path(self) -> Path | None: + return self._srcs_path From b8902bd4719a7308f7337c934b4273f0b431a01a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=8E=98=E6=9D=83=20=E9=A9=AC?= Date: Thu, 11 Jan 2024 18:10:06 +0800 Subject: [PATCH 49/61] feat: +unit test --- tests/metagpt/utils/test_project_repo.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tests/metagpt/utils/test_project_repo.py b/tests/metagpt/utils/test_project_repo.py index 6f80fbc14..667927a1d 100644 --- a/tests/metagpt/utils/test_project_repo.py +++ b/tests/metagpt/utils/test_project_repo.py @@ -24,6 +24,7 @@ async def test_project_repo(): pr = ProjectRepo(root=str(root)) assert pr.git_repo.workdir == root + assert pr.workdir == pr.git_repo.workdir await pr.save(filename=REQUIREMENT_FILENAME, content=REQUIREMENT_FILENAME) doc = await pr.get(filename=REQUIREMENT_FILENAME) @@ -51,6 +52,11 @@ async def test_project_repo(): assert pr.docs.prd.changed_files assert not pr.tests.changed_files + with pytest.raises(ValueError): + pr.srcs + assert pr.with_src_path("test_src").srcs.root_path == Path("test_src") + assert pr.src_relative_path == Path("test_src") + pr.git_repo.delete_repository() From 251352e802e93e46e5bc510b6942d40dbbc70008 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=8E=98=E6=9D=83=20=E9=A9=AC?= Date: Thu, 11 Jan 2024 19:11:32 +0800 Subject: [PATCH 50/61] fixbug: args error --- metagpt/roles/qa_engineer.py | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/metagpt/roles/qa_engineer.py b/metagpt/roles/qa_engineer.py index e042c1512..0666a63db 100644 --- a/metagpt/roles/qa_engineer.py +++ b/metagpt/roles/qa_engineer.py @@ -17,7 +17,7 @@ from metagpt.actions import DebugError, RunCode, WriteTest from metagpt.actions.summarize_code import SummarizeCode -from metagpt.const import MESSAGE_ROUTE_TO_NONE, TEST_CODES_FILE_REPO +from metagpt.const import MESSAGE_ROUTE_TO_NONE from metagpt.logs import logger from metagpt.roles import Role from metagpt.schema import Document, Message, RunCodeContext, TestingContext @@ -123,9 +123,7 @@ class QaEngineer(Role): async def _debug_error(self, msg): run_code_context = RunCodeContext.loads(msg.content) code = await DebugError(i_context=run_code_context, context=self.context, llm=self.llm).run() - await self.project_repo.tests.save( - filename=run_code_context.test_filename, content=code, relative_path=TEST_CODES_FILE_REPO - ) + await self.project_repo.tests.save(filename=run_code_context.test_filename, content=code) run_code_context.output = None self.publish_message( Message( From 1523a0df81049635cb4817a59eec98252c93e9bc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=8E=98=E6=9D=83=20=E9=A9=AC?= Date: Thu, 11 Jan 2024 23:15:18 +0800 Subject: [PATCH 51/61] fixbug: unit test --- metagpt/actions/action.py | 2 +- metagpt/context.py | 4 -- metagpt/learn/text_to_image.py | 4 +- metagpt/roles/role.py | 2 +- metagpt/utils/project_repo.py | 12 +++--- tests/data/openai/embedding.json | 1 + tests/metagpt/actions/test_debug_error.py | 12 +++--- tests/metagpt/actions/test_design_api.py | 6 +-- .../metagpt/actions/test_prepare_documents.py | 5 ++- .../actions/test_project_management.py | 7 ++-- .../actions/test_rebuild_sequence_view.py | 12 ++---- tests/metagpt/actions/test_summarize_code.py | 23 +++++++---- tests/metagpt/actions/test_write_code.py | 41 ++++++++----------- tests/metagpt/actions/test_write_prd.py | 9 ++-- tests/metagpt/learn/test_text_to_embedding.py | 15 ++++++- tests/metagpt/learn/test_text_to_image.py | 22 +++++++++- tests/metagpt/tools/test_azure_tts.py | 16 ++++++-- .../tools/test_openai_text_to_embedding.py | 15 ++++++- .../tools/test_openai_text_to_image.py | 26 +++++++++++- 19 files changed, 152 insertions(+), 82 deletions(-) create mode 100644 tests/data/openai/embedding.json diff --git a/metagpt/actions/action.py b/metagpt/actions/action.py index 34033e354..ec45690c0 100644 --- a/metagpt/actions/action.py +++ b/metagpt/actions/action.py @@ -35,7 +35,7 @@ class Action(SerializationMixin, ContextMixin, BaseModel): @property def project_repo(self): - return ProjectRepo(git_repo=self.context.git_repo) + return ProjectRepo(self.context.git_repo) @property def prompt_schema(self): diff --git a/metagpt/context.py b/metagpt/context.py index a5ff610eb..0ce2f4b40 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -55,10 +55,6 @@ class Context(BaseModel): _llm: Optional[BaseLLM] = None - @property - def file_repo(self): - return self.git_repo.new_file_repository() - @property def options(self): """Return all key-values""" diff --git a/metagpt/learn/text_to_image.py b/metagpt/learn/text_to_image.py index 1af66d6fb..8b2cb4473 100644 --- a/metagpt/learn/text_to_image.py +++ b/metagpt/learn/text_to_image.py @@ -30,8 +30,8 @@ async def text_to_image(text, size_type: str = "512x512", model_url="", config: if model_url: binary_data = await oas3_metagpt_text_to_image(text, size_type, model_url) - elif oai_llm := config.get_openai_llm(): - binary_data = await oas3_openai_text_to_image(text, size_type, LLM(oai_llm)) + elif config.get_openai_llm(): + binary_data = await oas3_openai_text_to_image(text, size_type, LLM()) else: raise ValueError("Missing necessary parameters.") base64_data = base64.b64encode(binary_data).decode("utf-8") diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py index f0b941085..edd7a5b99 100644 --- a/metagpt/roles/role.py +++ b/metagpt/roles/role.py @@ -191,7 +191,7 @@ class Role(SerializationMixin, ContextMixin, BaseModel): @property def project_repo(self) -> ProjectRepo: - project_repo = ProjectRepo(git_repo=self.context.git_repo) + project_repo = ProjectRepo(self.context.git_repo) return project_repo.with_src_path(self.context.src_workspace) if self.context.src_workspace else project_repo @property diff --git a/metagpt/utils/project_repo.py b/metagpt/utils/project_repo.py index 71cb9d55d..dd54cb56b 100644 --- a/metagpt/utils/project_repo.py +++ b/metagpt/utils/project_repo.py @@ -78,12 +78,14 @@ class ResourceFileRepositories(FileRepository): class ProjectRepo(FileRepository): - def __init__(self, root: str | Path = None, git_repo: GitRepository = None): - if not root and not git_repo: - raise ValueError("Invalid root and git_repo") - git_repo_ = git_repo or GitRepository(local_path=Path(root)) + def __init__(self, root: str | Path | GitRepository): + if isinstance(root, str) or isinstance(root, Path): + git_repo_ = GitRepository(local_path=Path(root)) + elif isinstance(root, GitRepository): + git_repo_ = root + else: + raise ValueError("Invalid root") super().__init__(git_repo=git_repo_, relative_path=Path(".")) - self._git_repo = git_repo_ self.docs = DocFileRepositories(self._git_repo) self.resources = ResourceFileRepositories(self._git_repo) diff --git a/tests/data/openai/embedding.json b/tests/data/openai/embedding.json new file mode 100644 index 000000000..249c78ecf --- /dev/null +++ b/tests/data/openai/embedding.json @@ -0,0 +1 @@ +{"object": "list", "data": [{"object": "embedding", "index": 0, "embedding": [-0.01999368, -0.02016083, 0.013037679, -0.011751912, -0.02810687, 0.0056188027, -0.011726197, -0.01088402, 0.01021542, -0.010967594, 0.0113276085, -0.0106332945, -0.012806241, -0.021626605, -0.00513664, 0.0023031305, 0.021343736, -0.0029026193, 0.009951838, -0.013114825, -0.0057730945, 0.0065799137, -0.016084947, -0.027309695, -0.011906204, 0.0066474164, 0.02921263, -0.013436267, -0.009096803, -0.00037287248, 0.033378515, -0.022912372, -0.036027197, -0.0077338894, -0.02307952, -0.011784056, -0.018527905, -0.0094182445, 0.02557391, -0.011276178, 0.017820733, 0.023670973, 0.0017293568, -0.0031501297, -0.0016192631, 0.01044043, 0.009071087, -0.014670604, -0.017820733, 0.010646152, 0.018656481, -0.010691154, -0.022410922, -0.017692156, -0.024391003, 0.010993309, -0.01088402, 0.0073545882, -0.000542433, -0.0028238662, 0.008569638, 0.0073481593, -0.027438272, 0.0018209678, -0.001176477, 0.00038673467, 0.010376141, 0.02259093, 0.03656722, 0.0010904913, 0.012581232, -0.0006497142, 0.010929021, 0.0024638514, 0.0135777015, 0.01380914, 0.009270381, 0.008486063, 0.01402772, -0.0069495714, 0.012414082, -0.032658488, 0.018785058, 0.013217687, 0.020842286, 0.016753547, -0.026743958, 0.021446597, -0.021112297, -0.008666071, 0.011591191, 0.025149606, 0.00043796445, 0.015699217, -0.0024863523, 0.020996578, 0.010954737, 0.022063766, 0.010948308, -0.024223853, -0.011944777, 0.0033365658, -0.010061128, -0.000753781, -0.019389369, -0.013616274, 0.004429468, -0.004220531, 0.0024043845, 0.016059233, -0.020276548, 0.024609584, 0.0053873644, -0.050222065, -0.0033654957, 0.0017872164, 0.009836119, -0.014567742, -0.0073545882, -0.0033719244, 0.009006799, 0.014850611, 0.033327084, -0.019157931, 0.026846819, 0.0026358226, -0.009758973, -0.023979558, -0.013783424, -0.00845392, 0.039473053, 0.007766034, 0.01595637, 0.0010205777, -0.022346634, 0.03584719, -0.018373612, 0.0006288205, -0.0005010474, -0.0043651797, 0.010871162, 0.035075728, -0.015673501, 0.004352322, -0.0023240242, 0.01530063, -0.0027097543, 0.00085583876, 0.015506352, -0.0063581187, 0.022655217, -0.004063024, 0.013886286, -0.0037640834, -0.010350426, 0.0055705863, 0.00433625, 0.014169155, 0.011700481, -0.011218319, 0.00019658175, 0.008691786, -0.0035390742, -0.028312594, 0.0018241822, 0.043330353, 0.022410922, 0.03155273, -0.0077403183, -0.025381044, -0.028724039, 0.021755181, -0.024995314, 0.008903937, -0.017036416, -0.009411816, -0.001938294, 0.0108904485, -0.017962167, -0.002576356, -0.024185281, 0.0028126156, 0.020726567, 0.010479002, -0.010118987, -0.018836489, 0.019350797, -0.028415455, 0.007746747, 0.006814566, 0.008762503, 0.032504193, 0.014207727, -0.01402772, -0.67847365, -0.033507094, -0.00029090483, -0.008595354, -0.0021568744, 0.0083382, -0.014002005, 0.0021022293, -0.014837753, 0.0018707912, -0.010787587, 0.004738052, -0.012041209, 0.0019800814, 0.019299366, -0.016252097, 0.020456556, -0.0022050908, -0.0056959484, 0.0107168695, -0.009379672, 0.012439798, 0.01794931, 0.0020475842, 0.008357487, -0.008209623, 0.02529104, 0.007328873, -0.012960534, 0.04567045, -0.04353608, 0.017242137, 0.015570641, -0.021999476, 0.05909386, 0.00601739, -0.019183647, 0.028364023, 0.016714973, 0.038341578, -0.035410028, -0.0023593828, 0.00016162495, 0.0012110319, -0.0011740661, -0.008209623, 0.011366182, -0.00021054437, 0.0005291735, -0.020199403, 0.0016039945, 0.015596356, 0.022449495, 0.0065574124, 0.00563166, -0.006898141, 0.0336871, 0.005004849, 0.010041841, 0.01855362, 0.0098489765, -0.0027499346, -0.0060334625, -0.01933794, 0.0019045427, 0.025805347, -0.012086212, 0.008003901, 0.01971081, -0.018913636, 0.009681826, -0.00043836626, -0.009816833, 0.01838647, -0.007361017, 0.021716608, 0.01756358, -0.0052555734, -0.01821932, 0.0291612, -0.0086339265, -0.0009860228, 0.000753781, -0.008762503, 0.033224225, -0.013796282, -0.016097805, 0.016599255, 0.010839017, 0.0010358462, 1.2945566e-05, 0.0053809355, 0.0031726304, -0.010922592, 0.0065349117, 0.0069174273, -0.019350797, -0.01044043, 0.016097805, -0.015197768, -0.008183908, -0.0035551463, 0.00601739, -0.004018022, -0.0124526555, 0.011160459, -0.012311221, 0.01065901, 0.043047484, -0.0035647894, -0.0030810195, -0.008588925, -0.0006641791, -0.0033654957, 0.029109769, -0.032761347, 0.01170691, 0.008048902, 0.010138274, 0.0050562792, 0.027952578, -0.015827794, 0.016059233, -0.007361017, 0.0027354697, 0.0075474535, -0.0108004445, -0.008434633, -0.01143047, 0.0044198246, 0.007881753, 0.0012696951, -0.007129579, -0.0007541828, -0.002476709, -0.0018836489, 0.02214091, -0.017357856, 0.006145967, -0.011803343, -0.014387735, -0.0062809726, 0.005397008, -0.015082049, 0.011494759, -0.012111926, -0.009733258, -0.004146599, -0.0012745167, 0.0041048117, -0.002721005, -0.026319655, -0.01115403, 0.03600148, 0.010080415, -0.0119319195, -0.013744852, -0.003100306, -0.018527905, -0.010138274, -0.0057120207, 0.0032208469, 0.0034651426, -0.0043716086, -0.011764769, -0.027515417, -0.017717872, 0.02016083, 0.0027226121, -0.015660644, -0.016072089, -0.017422145, 0.012066925, -0.0007702549, -0.0059016715, 0.0012351401, -0.01247837, -0.03695295, -0.0040790965, -0.016663542, 0.014349162, -0.0026968967, 0.007200296, 0.0045869746, 0.023709547, -0.00392159, -0.015390634, 0.032889925, -0.01766644, -0.020340838, -0.009533964, 0.010376141, 0.007258156, 0.0049502035, 0.012999106, -0.008762503, -0.016444962, 0.022372348, 0.044487543, 0.005975603, -0.016573539, 0.0058245254, 0.01722928, -0.009823261, 0.022449495, -0.022552356, 0.0006256061, -0.019260792, 0.00878179, 0.01650925, 0.0128833875, 0.004670549, -0.036104344, 0.004284819, -0.008685357, 0.024661014, 0.003854087, 0.022192342, 0.002960479, -0.0014167547, -0.0043491074, -0.00043515183, 0.0028029724, 0.0015139908, 0.00999684, -0.0006637773, 0.004946989, 0.042198878, -0.012999106, -0.014310589, -0.013108396, -0.0018482903, -0.0017052487, -0.0036708652, 0.00083173066, 0.0026952894, 0.035075728, -0.018013598, 0.023298101, 0.0064770523, -0.027155403, -0.0037351537, 0.049013443, -0.009636825, 0.019286508, 0.035384312, 0.02766971, -0.002584392, 0.0052748597, 0.0011652265, -0.025689628, -0.0066795605, -0.039138753, 0.02032798, 0.0145806, -0.0039280187, 0.0020250834, 0.0035808615, 0.031989887, 0.009701113, 0.02800401, 0.0016988199, 0.010350426, 0.01563493, 0.024159566, -0.007958899, -0.012330507, -0.01982653, -0.0025136748, 0.022295203, -0.0044133957, 0.0011660301, -0.0061041797, 0.002116694, 0.01595637, 0.0051848562, 0.009173949, 0.010067557, -0.0036547931, 0.013371979, -0.0017181064, -0.019453658, 0.019787956, 0.01049186, -0.0046287617, -0.015917799, -0.028801184, -0.0035197877, -0.012864101, 0.015583498, 0.0028174373, 0.028904047, 0.005593087, -0.007946041, -0.019196505, -0.0043651797, 0.012414082, -0.0017438218, 0.0126262335, 0.01590494, 0.009302526, 0.013783424, -0.01016399, -0.011623335, 0.011057598, 0.00336871, 0.005290932, -0.016252097, -0.0001511781, 0.009861834, -0.007598884, -0.0291612, -0.019260792, 0.0017952524, -0.012966962, 0.0030954846, -0.019839387, -0.019325081, 0.039627343, 0.0039698062, -0.006820995, -0.01496633, -0.027695425, -0.001907757, 0.048782006, 0.012941247, 0.0066152723, -0.010794016, 0.0019865104, -0.0013034465, -0.013963431, -0.031938456, 0.002452601, -0.01960795, -0.026203936, -0.0030617332, 0.007798178, -0.0039248043, 0.023156667, 0.00045443833, -0.00050546724, 0.0014416665, 0.0066024144, -0.004538758, 0.0023931342, -0.00081405137, 0.010427572, 0.009270381, 0.0062166844, -0.005538442, 0.026242508, 0.02689825, -0.003815514, -0.027926862, -0.01121189, 0.02738684, 0.0055480856, -0.009778259, -0.024558153, 0.012182644, -0.0078046066, 0.00070235034, 0.014207727, -0.0007156098, 0.04127313, 0.046261903, 0.009964695, -0.027052542, 0.000965129, 0.018695055, -0.0133205475, 0.012182644, -0.014194869, 0.0061170375, 0.034741428, -0.009746116, -0.025998212, -0.00040782927, 0.018245036, 0.016496394, -0.027078256, -0.012992677, -0.013011964, -0.052716453, -0.0011025454, -0.0029829799, -0.010530434, -0.011970492, 0.003944091, -0.020109398, 0.003384782, -0.0041176695, -0.02043084, -0.005049851, -0.0053166472, -0.022539498, -0.023902413, 0.0006392674, -0.0011202247, 0.018026456, -0.0049502035, -0.013204829, -0.0028110086, 0.041118834, 0.0005388168, -0.0005552907, -0.0032787062, -0.028595462, -0.021678034, -0.0025570695, -0.004953418, -0.008216052, -0.002645466, -0.0017213208, 0.032812778, 0.00955325, 0.006030248, 0.007444592, 0.00091932353, 0.0029942302, -0.0022822367, 0.023735262, -0.032118466, 0.013114825, 0.020070825, -0.024429576, -0.0045869746, -0.00455483, 0.013616274, -0.004345893, 0.017987883, 0.031064136, -0.05251073, 0.0071810097, 0.006435265, -0.012523373, 0.009411816, -0.0057313074, 0.0128833875, 0.003860516, -0.009386101, 0.010626866, -0.010755442, -0.029392637, 0.013384837, -0.030421251, 0.0063581187, 0.031321287, 0.01888792, 0.021163728, -0.01474775, -0.010376141, 0.004130527, -0.019170789, -0.00850535, 0.010350426, -0.0031244142, 0.010009698, -0.027541133, -0.0048312703, -0.015364918, 0.013005535, 0.0010085236, -0.021215158, -0.029624077, 0.0015147944, -0.0013934502, -0.01960795, -0.021189444, -0.032787062, -0.0092382375, 0.012227646, -0.003899089, 0.020070825, -0.0065188394, 0.01690784, -0.0012054067, 0.023542397, -0.01828361, -0.03422712, -0.01530063, 0.0027001111, 0.03103842, 0.023876697, 0.012375509, -0.022513783, 0.02512389, 0.0033558523, -0.02021226, -0.005577015, -0.018257894, -0.0109804515, -0.03417569, 0.008518208, 0.009051801, 0.018566478, -0.0074960226, -0.01551921, -0.017370714, -0.0097654015, -0.0041015972, -0.004821627, -0.009206093, -0.012934818, 0.0047573387, 0.0021504457, -0.015017761, 0.017074987, -0.0040276656, 0.008601783, 0.02921263, 0.0013902357, 0.019029355, 0.029135484, 0.020366551, -0.008003901, 0.005483797, -0.014130581, 0.008704644, -0.017345, -0.039473053, 0.014567742, -0.017332142, 0.030986989, 0.023825265, 0.030986989, -0.004847342, 0.015249198, -0.001099331, 0.016714973, -0.010832588, -0.024506722, 0.008871794, -0.021279447, -0.025213894, -0.032349903, -0.016149236, -0.044873275, 0.003699795, 0.016329244, -0.013500555, 0.0127998125, -0.012767668, -0.013963431, 0.0050466363, 0.016740689, 0.05073637, 0.009456818, 0.020790854, 0.006329189, -0.001030221, -0.019132216, 0.016046375, -0.018605052, -0.020353695, 0.019183647, 0.018360754, 0.011925491, 0.0006927071, 0.017460719, -0.002438136, -0.011726197, -0.02738684, 0.02307952, 0.0077403183, -0.012934818, -0.01253623, -0.00049100234, -0.014657746, 0.017062131, -0.01937651, -0.018540762, 0.008518208, -0.013989147, -0.024146708, 0.035410028, 0.0012648734, 0.030524112, 0.0101125585, -0.000100802135, -0.007991043, 0.0023674187, 0.019003639, 0.005081995, 0.0033044217, 0.0007702549, -0.011713339, 0.0045773312, -0.008344629, 0.0056284457, -0.019183647, 0.0074574496, 0.003429784, 0.02523961, -0.012491228, -0.022603787, -0.024172423, 0.003060126, 0.021112297, 0.0011587976, -0.002344918, -0.0133205475, -0.03157844, -0.016586397, 0.024866737, -0.015750648, 0.0067952797, -0.008183908, -0.0153134875, 0.0037640834, 0.003407283, -0.023516681, -0.0075860266, -0.023490967, -0.011282607, -0.013371979, 0.003799442, 0.016264955, 0.02622965, 0.016046375, 0.020173687, 0.016496394, -0.00045966177, 0.023015233, 0.0050594937, 0.012819099, -0.015390634, -0.0048794863, 0.0027049328, -0.03533288, -0.0043169633, -0.014953473, -0.0035519318, -0.025046745, 0.023683831, 0.025998212, -0.012291934, 0.014837753, 0.011481901, 0.040013075, -0.013886286, -0.021009436, -0.022436637, 0.025535336, -0.008093905, 0.011751912, 0.008955369, 0.0065027676, -0.018862205, -0.011173317, -0.009662541, 0.002531354, -0.025226751, -0.02275808, -0.0060945363, 0.026435373, -0.014182012, -0.020019395, -0.022950944, 0.013564844, -0.0056413035, 0.01838647, 0.00068828725, 0.004766982, 0.01518491, 0.02495674, 0.010408285, -0.0050980668, 0.007746747, -0.043998953, -0.014760607, -0.0047862683, -0.02666681, -0.008132477, -0.018630767, -0.008222481, 0.01369342, -0.027155403, -0.051893562, 0.0008445883, -0.01744786, -0.018373612, -0.021215158, -0.006444908, 0.0065477695, -0.0012954104, -0.022410922, 0.015982086, 0.007624599, 0.014824895, -0.008653213, -0.011436899, 0.010388999, 0.006891712, -0.008100334, 0.005644518, -0.0046930504, 0.00038974817, 0.020610848, 0.01563493, -0.010684725, 0.030524112, -0.013873428, 0.013166256, -0.018013598, 0.008511779, 0.008820363, 0.013912001, 0.0032545982, -0.008344629, -0.023400962, 0.012343365, 0.021652319, 0.02016083, -0.009302526, 0.023349533, -0.016817834, 0.022449495, -0.009450389, 0.013847712, -0.006454551, -0.012433369, 0.0084603485, -0.02529104, -0.036387213, 0.018913636, -0.03340423, -0.010041841, 0.002576356, 0.006454551, -0.018206464, 0.014156297, 0.04353608, -0.018129317, 0.02512389, 0.0030954846, 0.0074638785, -0.024352431, -0.0062713292, -0.0023111666, 0.0013500556, -0.014503454, 0.004622333, 0.003429784, -0.013031251, -0.009122518, -0.009077516, -0.0005717646, 0.001050311, -0.0011162066, -0.0028961906, -0.0073803035, 0.0033076361, -0.0013580916, -0.0042719613, -0.016740689, -0.0060977507, 0.011816201, 0.002783686, 0.009257523, 0.24110706, -0.019530803, 0.019080784, 0.031141281, -0.009926123, 0.007997472, -0.008704644, -0.013166256, 0.0015895297, 0.004783054, -0.0006718133, -0.001288178, -0.02766971, -0.0012037995, -0.0015871188, -0.002460637, -0.014452023, -0.007798178, -0.028415455, -0.04312463, -0.010704012, -0.025779633, -0.008473205, -6.790458e-05, 0.010832588, -0.0057055918, -0.013731994, 0.011256891, 0.031321287, 0.017589295, -0.010286137, -0.020366551, 0.0053037894, 0.00023967504, -0.010562577, -0.007836751, -0.0045805457, 0.007978185, 0.023092378, 0.042173162, -0.013294833, -0.0066088433, 0.012819099, -0.0016425676, -0.007759605, 0.010408285, -0.010408285, -0.020958005, -0.001645782, 0.018875062, -0.013204829, 0.018836489, 0.018103601, 0.039190184, -0.019067928, 0.005435581, 0.0010888841, 0.0035165732, -0.0037705123, 0.015416348, -0.006814566, 0.020469414, -0.009488962, 0.0027660066, -0.008312485, -0.0018643624, -0.020057969, -0.007643886, -0.0015292594, -0.010343997, -0.031166997, -0.0023433107, 0.01253623, -0.0037126527, -0.041658856, -0.02176804, 0.049116306, 0.003545503, 0.028415455, 0.04633905, -0.014927757, -0.014079151, -0.0033333513, -0.021896616, 0.011109028, -0.037210103, 0.031604156, 0.008396059, -0.016162094, 0.01535206, 9.638231e-05, -0.025972497, 0.016663542, 0.0046673347, -0.0002151651, 0.03162987, -0.01684355, 0.023130951, 0.0051719984, 0.009296097, -0.02959836, -0.0071938676, 0.0059241722, -0.0001261659, -0.014400592, 0.0012745167, -0.0126262335, -0.017705014, 0.015364918, -0.0024477793, -0.01684355, -0.012439798, 0.018707912, -0.026409658, -0.01281267, -0.010614008, 0.0191065, 0.0013757709, 0.0006967251, 0.014220585, 0.0054387953, -0.021935187, 0.016393531, 0.0092382375, -0.022796651, -0.013770566, -0.0058566695, 0.0042430316, 0.022989517, -0.015943512, 0.025278183, -0.005361649, 0.015043476, -0.025946781, -0.021588031, 0.020945147, 0.022848083, -0.008100334, 0.010266851, 0.009694684, 0.003008695, 0.004191601, 0.004738052, -0.008106762, 0.0073095863, -0.017589295, 0.0066731316, 0.0009281632, -0.012021923, -0.010086844, -0.038984463, -0.004480899, 0.0024943883, -0.014722034, 0.010974023, -0.0127998125, -0.024943883, -0.030678404, 0.002169732, 0.022719506, -0.024712445, -0.0071938676, 0.0031276287, -0.027361125, -0.035924334, -0.0074767363, -0.16581254, 0.03026696, 0.017267853, -0.007759605, 0.0019350796, 0.013256259, 0.0101961335, -0.0062038265, -0.0066667027, -8.598568e-05, 0.02307952, 0.0005066726, -0.054927975, -0.0023593828, 0.013018393, 0.010710441, -0.010678296, 0.017679298, -0.001503544, 0.017087845, 0.015146337, -0.0063099023, -0.003600148, 0.014837753, -0.023812408, 0.006522054, -0.013886286, 0.028029725, -0.025136748, 0.012671236, -0.032221325, -0.011546189, 0.027772572, 0.017525006, 0.0054580816, -0.0027338625, 0.019247934, -0.0170107, 0.016637828, 0.006377405, 0.013487698, 0.02766971, 0.00039898962, 0.00944396, -0.018193606, 0.014696319, 0.0041273125, -0.015750648, 0.029521214, -0.0050080633, -0.018347898, -0.011880489, 0.022475211, 0.006583128, 0.0134105515, 0.026435373, 0.002676003, 0.0022645574, 0.016612113, -0.0057570226, 0.019646522, -0.03026696, 0.0012303184, -0.025856778, -0.002221163, -0.022436637, -0.012304792, 0.003423355, -0.008582496, 0.023015233, -0.000782309, -0.004821627, 0.026795387, -0.011301894, 0.0069560003, 0.013461983, -0.01530063, 0.023426678, 0.006554198, -0.0038122996, -0.016046375, 0.02098372, 0.00017739569, 0.015506352, 0.009630396, 0.022873798, 0.0132305445, -0.0012857672, -0.018566478, -0.0075024515, 0.04811341, -0.017717872, -0.010009698, 0.004384466, -0.002184197, 0.008511779, -0.015506352, 0.0058952426, -0.0062102554, -0.027772572, -0.0063870484, -0.015943512, -0.009726829, 0.008351058, 0.020996578, 0.008813934, 0.011829058, 0.0077017453, 0.029778369, -0.015043476, -0.0073803035, 0.0132305445, 0.009013228, 0.029906945, 0.003568004, 0.035692897, -0.014902041, -0.0030954846, -0.008415346, -0.00767603, 0.05533942, -0.013500555, -0.008601783, 0.0085503515, -0.01513348, -0.010144703, -0.058888137, -0.031141281, 0.0239667, 0.023259528, -0.008537494, 0.005397008, 0.0045355437, 0.015082049, -0.029418353, 0.016856408, -0.0056927344, -0.015827794, -0.012966962, -0.004468041, 0.038007278, -0.022873798, -0.009116089, 0.005233072, -0.013731994, 0.0239667, -0.025831062, -0.0012889816, 0.0011113851, -0.009681826, -0.0065477695, 0.0015903333, -0.04585046, 0.014734892, 0.0066538453, 0.010607579, -0.0043748226, 0.0013404123, 0.008293198, -0.021279447, -0.022449495, -0.010652581, -0.023825265, -0.006859568, 0.020585133, -0.030035522, 0.012156929, -0.00090244785, -0.0010896877, -0.021498026, -0.010646152, -0.005898457, -0.0038476584, 0.017306427, 0.00065453583, -0.031681303, -0.018913636, -0.024095276, -0.03155273, 0.023555255, 0.025561051, -0.021125155, 0.014477738, 0.021793753, 0.018836489, 0.005840597, 0.012555516, -0.00025313543, -0.023696689, 0.019633666, 0.013359121, 0.018990781, -0.026769673, 0.003452285, 0.012465512, 0.0035326453, -0.0028511886, 0.025329614, -0.016496394, 0.009861834, -0.010999738, -0.008537494, -0.008736788, -0.01236908, 0.018707912, -0.006512411, -0.00576988, -0.02700111, 0.002184197, 0.0014633638, 0.024095276, 0.01717785, 0.011546189, -0.018309325, -0.009598252, -0.016316386, -0.0052427156, 0.018759344, 0.00472198, -0.018849347, -0.014053435, -0.0061266804, 0.0035326453, -0.0066152723, 0.0032176324, 0.0042494605, 6.438881e-05, -0.018322183, -0.07154009, 0.021960903, -0.0071488656, -0.026923966, 0.015660644, -0.0101125585, 0.008813934, -0.026641095, 0.012876959, -0.011790485, -0.006885283, 0.016136378, -0.0010792408, 0.012221217, -0.004378037, -0.00635169, 0.035307165, -0.0033815678, 0.00850535, 0.010549719, 0.0059788176, 0.0037705123, 0.020289406, -0.014812038, 0.019312223, -0.0035776473, -0.012439798, 0.019800814, -0.033275656, 0.0011571904, -0.0046962644, -0.037827272, 1.2041511e-05, 0.023053806, -0.0024799234, -0.033661384, 0.012407653, 0.009855405, 0.013307691, 0.0065895566, -0.01694641, -0.033095647, 0.01888792, -0.029701222, -0.019852245, -0.0050466363, -0.017306427, 0.011835487, 0.022012334, -0.0020925861, 0.01690784, 0.027309695, -0.02302809, -0.00051189604, 0.019967964, -0.055905156, 0.028646892, 0.028955476, 0.0015509566, -7.850211e-05, 0.023696689, 0.010929021, 0.012613376, -0.017692156, -0.00037447968, 0.009983982, -0.011141173, -0.008801077, 0.0015887261, -0.03440713, -0.009386101, 0.0063806195, 0.002992623, 0.009701113, 0.0066859894, 0.0031019133, -0.0063034734, 0.008498921, -0.026242508, 0.023606686, 0.013513413, 0.0017454289, -0.008376773, -0.00201544, 0.048164837, 0.0074188765, -0.0010181669, -0.017190708, 0.008029616, 0.029572645, -0.025008172, -0.005091638, -0.024866737, 0.007271013, -0.002328846, 0.0062713292, -0.016894981, 7.393161e-05, 0.022732364, 0.012375509, 0.0014272016, 1.2298916e-05, -0.0191065, -0.016637828, -0.01452917, -0.012137642, -0.02307952, -0.0001341015, 0.004043738, 0.024545295, 0.014516312, -0.01766644, -0.020893717, 0.009263952, 0.008563209, 0.0018948994, -0.013500555, -0.0034780002, -0.015814936, 0.044204675, 0.008093905, 0.007367446, 0.011366182, 0.004853771, 0.0030826267, -0.0080231875, -0.006621701, -0.03985878, 0.007791749, -0.00018603443, -0.0026872533, -0.016419247, -0.008408917, -0.027489703, -0.024545295, 0.0034490705, -0.020456556, 0.010427572, 0.01578922, 0.04991348, -0.0014159511, -0.005191285, 0.021253731, 0.00052837, 0.03108985, 0.0034940722, 0.0030553043, 0.0004680996, -0.009630396, 0.0140148625, -0.031115565, -0.013976289, -0.007766034, -0.021742323, -0.0062552574, -0.017164992, 0.013513413, -0.025535336, -0.006444908, 0.027412556, 0.0075345957, 0.01264552, -0.0009112875, -0.029315492, -0.021215158, 0.028801184, -0.0032497765, -0.020687994, -0.03129557, 0.0037962275, -0.001365324, -0.02805544, -0.005638089, 0.02689825, -0.007695317, -0.0027724355, -0.00074895937, -0.0056798765, 0.0045580445, -0.008325342, -0.008858936, -0.0070717195, -0.020276548, 0.03600148, -0.0047123367, -0.016599255, 0.01573779, -0.028595462]}], "model": "text-embedding-ada-002-v2", "usage": {"prompt_tokens": 3, "total_tokens": 3}} \ No newline at end of file diff --git a/tests/metagpt/actions/test_debug_error.py b/tests/metagpt/actions/test_debug_error.py index 2e57a95c9..e093eb83f 100644 --- a/tests/metagpt/actions/test_debug_error.py +++ b/tests/metagpt/actions/test_debug_error.py @@ -11,9 +11,9 @@ import uuid import pytest from metagpt.actions.debug_error import DebugError -from metagpt.const import TEST_CODES_FILE_REPO, TEST_OUTPUTS_FILE_REPO from metagpt.context import CONTEXT from metagpt.schema import RunCodeContext, RunCodeResult +from metagpt.utils.project_repo import ProjectRepo CODE_CONTENT = ''' from typing import List @@ -118,6 +118,7 @@ if __name__ == '__main__': @pytest.mark.asyncio async def test_debug_error(): CONTEXT.src_workspace = CONTEXT.git_repo.workdir / uuid.uuid4().hex + project_repo = ProjectRepo(CONTEXT.git_repo) ctx = RunCodeContext( code_filename="player.py", test_filename="test_player.py", @@ -125,9 +126,8 @@ async def test_debug_error(): output_filename="output.log", ) - repo = CONTEXT.file_repo - await repo.save_file(filename=ctx.code_filename, content=CODE_CONTENT, relative_path=CONTEXT.src_workspace) - await repo.save_file(filename=ctx.test_filename, content=TEST_CONTENT, relative_path=TEST_CODES_FILE_REPO) + await project_repo.with_src_path(CONTEXT.src_workspace).srcs.save(filename=ctx.code_filename, content=CODE_CONTENT) + await project_repo.tests.save(filename=ctx.test_filename, content=TEST_CONTENT) output_data = RunCodeResult( stdout=";", stderr="", @@ -141,9 +141,7 @@ async def test_debug_error(): "----------------------------------------------------------------------\n" "Ran 5 tests in 0.007s\n\nFAILED (failures=1)\n;\n", ) - await repo.save_file( - filename=ctx.output_filename, content=output_data.model_dump_json(), relative_path=TEST_OUTPUTS_FILE_REPO - ) + await project_repo.test_outputs.save(filename=ctx.output_filename, content=output_data.model_dump_json()) debug_error = DebugError(i_context=ctx) rsp = await debug_error.run() diff --git a/tests/metagpt/actions/test_design_api.py b/tests/metagpt/actions/test_design_api.py index 027f7ca20..fc231e578 100644 --- a/tests/metagpt/actions/test_design_api.py +++ b/tests/metagpt/actions/test_design_api.py @@ -9,18 +9,18 @@ import pytest from metagpt.actions.design_api import WriteDesign -from metagpt.const import PRDS_FILE_REPO from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.schema import Message +from metagpt.utils.project_repo import ProjectRepo @pytest.mark.asyncio async def test_design_api(): inputs = ["我们需要一个音乐播放器，它应该有播放、暂停、上一曲、下一曲等功能。"] # PRD_SAMPLE - repo = CONTEXT.file_repo + project_repo = ProjectRepo(CONTEXT.git_repo) for prd in inputs: - await repo.save_file("new_prd.txt", content=prd, relative_path=PRDS_FILE_REPO) + await project_repo.docs.prd.save(filename="new_prd.txt", content=prd) design_api = WriteDesign() diff --git a/tests/metagpt/actions/test_prepare_documents.py b/tests/metagpt/actions/test_prepare_documents.py index 317683113..a72019c5c 100644 --- a/tests/metagpt/actions/test_prepare_documents.py +++ b/tests/metagpt/actions/test_prepare_documents.py @@ -9,9 +9,10 @@ import pytest from metagpt.actions.prepare_documents import PrepareDocuments -from metagpt.const import DOCS_FILE_REPO, REQUIREMENT_FILENAME +from metagpt.const import REQUIREMENT_FILENAME from metagpt.context import CONTEXT from metagpt.schema import Message +from metagpt.utils.project_repo import ProjectRepo @pytest.mark.asyncio @@ -24,6 +25,6 @@ async def test_prepare_documents(): await PrepareDocuments(context=CONTEXT).run(with_messages=[msg]) assert CONTEXT.git_repo - doc = await CONTEXT.file_repo.get_file(filename=REQUIREMENT_FILENAME, relative_path=DOCS_FILE_REPO) + doc = await ProjectRepo(CONTEXT.git_repo).docs.get(filename=REQUIREMENT_FILENAME) assert doc assert doc.content == msg.content diff --git a/tests/metagpt/actions/test_project_management.py b/tests/metagpt/actions/test_project_management.py index 1eadb49fb..9fd3b1721 100644 --- a/tests/metagpt/actions/test_project_management.py +++ b/tests/metagpt/actions/test_project_management.py @@ -9,17 +9,18 @@ import pytest from metagpt.actions.project_management import WriteTasks -from metagpt.const import PRDS_FILE_REPO, SYSTEM_DESIGN_FILE_REPO from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.schema import Message +from metagpt.utils.project_repo import ProjectRepo from tests.metagpt.actions.mock_json import DESIGN, PRD @pytest.mark.asyncio async def test_design_api(): - await CONTEXT.file_repo.save_file("1.txt", content=str(PRD), relative_path=PRDS_FILE_REPO) - await CONTEXT.file_repo.save_file("1.txt", content=str(DESIGN), relative_path=SYSTEM_DESIGN_FILE_REPO) + project_repo = ProjectRepo(CONTEXT.git_repo) + await project_repo.docs.prd.save("1.txt", content=str(PRD)) + await project_repo.docs.system_design.save("1.txt", content=str(DESIGN)) logger.info(CONTEXT.git_repo) action = WriteTasks() diff --git a/tests/metagpt/actions/test_rebuild_sequence_view.py b/tests/metagpt/actions/test_rebuild_sequence_view.py index 0511f0308..717aee964 100644 --- a/tests/metagpt/actions/test_rebuild_sequence_view.py +++ b/tests/metagpt/actions/test_rebuild_sequence_view.py @@ -15,6 +15,7 @@ from metagpt.context import CONTEXT from metagpt.llm import LLM from metagpt.utils.common import aread from metagpt.utils.git_repository import ChangeType +from metagpt.utils.project_repo import ProjectRepo @pytest.mark.asyncio @@ -22,12 +23,8 @@ async def test_rebuild(): # Mock data = await aread(filename=Path(__file__).parent / "../../data/graph_db/networkx.json") graph_db_filename = Path(CONTEXT.git_repo.workdir.name).with_suffix(".json") - repo = CONTEXT.file_repo - await repo.save_file( - filename=str(graph_db_filename), - relative_path=GRAPH_REPO_FILE_REPO, - content=data, - ) + project_repo = ProjectRepo(CONTEXT.git_repo) + await project_repo.docs.graph_repo.save(filename=str(graph_db_filename), content=data) CONTEXT.git_repo.add_change({f"{GRAPH_REPO_FILE_REPO}/{graph_db_filename}": ChangeType.UNTRACTED}) CONTEXT.git_repo.commit("commit1") @@ -35,8 +32,7 @@ async def test_rebuild(): name="RedBean", i_context=str(Path(__file__).parent.parent.parent.parent / "metagpt"), llm=LLM() ) await action.run() - graph_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=GRAPH_REPO_FILE_REPO) - assert graph_file_repo.changed_files + assert project_repo.docs.graph_repo.changed_files @pytest.mark.parametrize( diff --git a/tests/metagpt/actions/test_summarize_code.py b/tests/metagpt/actions/test_summarize_code.py index b617b59ae..88d432b5e 100644 --- a/tests/metagpt/actions/test_summarize_code.py +++ b/tests/metagpt/actions/test_summarize_code.py @@ -9,10 +9,10 @@ import pytest from metagpt.actions.summarize_code import SummarizeCode -from metagpt.const import SYSTEM_DESIGN_FILE_REPO, TASK_FILE_REPO from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.schema import CodeSummarizeContext +from metagpt.utils.project_repo import ProjectRepo DESIGN_CONTENT = """ {"Implementation approach": "To develop this snake game, we will use the Python language and choose the Pygame library. Pygame is an open-source Python module collection specifically designed for writing video games. It provides functionalities such as displaying images and playing sounds, making it suitable for creating intuitive and responsive user interfaces. We will ensure efficient game logic to prevent any delays during gameplay. The scoring system will be simple, with the snake gaining points for each food it eats. We will use Pygame's event handling system to implement pause and resume functionality, as well as high-score tracking. The difficulty will increase by speeding up the snake's movement. In the initial version, we will focus on single-player mode and consider adding multiplayer mode and customizable skins in future updates. Based on the new requirement, we will also add a moving obstacle that appears randomly. If the snake eats this obstacle, the game will end. If the snake does not eat the obstacle, it will disappear after 5 seconds. For this, we need to add mechanisms for obstacle generation, movement, and disappearance in the game logic.", "Project_name": "snake_game", "File list": ["main.py", "game.py", "snake.py", "food.py", "obstacle.py", "scoreboard.py", "constants.py", "assets/styles.css", "assets/index.html"], "Data structures and interfaces": "```mermaid\n classDiagram\n class Game{\n +int score\n +int speed\n +bool game_over\n +bool paused\n +Snake snake\n +Food food\n +Obstacle obstacle\n +Scoreboard scoreboard\n +start_game() void\n +pause_game() void\n +resume_game() void\n +end_game() void\n +increase_difficulty() void\n +update() void\n +render() void\n Game()\n }\n class Snake{\n +list body_parts\n +str direction\n +bool grow\n +move() void\n +grow() void\n +check_collision() bool\n Snake()\n }\n class Food{\n +tuple position\n +spawn() void\n Food()\n }\n class Obstacle{\n +tuple position\n +int lifetime\n +bool active\n +spawn() void\n +move() void\n +check_collision() bool\n +disappear() void\n Obstacle()\n }\n class Scoreboard{\n +int high_score\n +update_score(int) void\n +reset_score() void\n +load_high_score() void\n +save_high_score() void\n Scoreboard()\n }\n class Constants{\n }\n Game \"1\" -- \"1\" Snake: has\n Game \"1\" -- \"1\" Food: has\n Game \"1\" -- \"1\" Obstacle: has\n Game \"1\" -- \"1\" Scoreboard: has\n ```", "Program call flow": "```sequenceDiagram\n participant M as Main\n participant G as Game\n participant S as Snake\n participant F as Food\n participant O as Obstacle\n participant SB as Scoreboard\n M->>G: start_game()\n loop game loop\n G->>S: move()\n G->>S: check_collision()\n G->>F: spawn()\n G->>O: spawn()\n G->>O: move()\n G->>O: check_collision()\n G->>O: disappear()\n G->>SB: update_score(score)\n G->>G: update()\n G->>G: render()\n alt if paused\n M->>G: pause_game()\n M->>G: resume_game()\n end\n alt if game_over\n G->>M: end_game()\n end\n end\n```", "Anything UNCLEAR": "There is no need for further clarification as the requirements are already clear."} @@ -178,17 +178,22 @@ class Snake: @pytest.mark.asyncio async def test_summarize_code(): CONTEXT.src_workspace = CONTEXT.git_repo.workdir / "src" - await CONTEXT.file_repo.save_file(filename="1.json", relative_path=SYSTEM_DESIGN_FILE_REPO, content=DESIGN_CONTENT) - await CONTEXT.file_repo.save_file(filename="1.json", relative_path=TASK_FILE_REPO, content=TASK_CONTENT) - await CONTEXT.file_repo.save_file(filename="food.py", relative_path=CONTEXT.src_workspace, content=FOOD_PY) - await CONTEXT.file_repo.save_file(filename="game.py", relative_path=CONTEXT.src_workspace, content=GAME_PY) - await CONTEXT.file_repo.save_file(filename="main.py", relative_path=CONTEXT.src_workspace, content=MAIN_PY) - await CONTEXT.file_repo.save_file(filename="snake.py", relative_path=CONTEXT.src_workspace, content=SNAKE_PY) + project_repo = ProjectRepo(CONTEXT.git_repo) + await project_repo.docs.system_design.save(filename="1.json", content=DESIGN_CONTENT) + await project_repo.docs.task.save(filename="1.json", content=TASK_CONTENT) + await project_repo.with_src_path(CONTEXT.src_workspace).srcs.save(filename="food.py", content=FOOD_PY) + assert project_repo.srcs.workdir == CONTEXT.src_workspace + await project_repo.srcs.save(filename="game.py", content=GAME_PY) + await project_repo.srcs.save(filename="main.py", content=MAIN_PY) + await project_repo.srcs.save(filename="snake.py", content=SNAKE_PY) - src_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=CONTEXT.src_workspace) - all_files = src_file_repo.all_files + all_files = project_repo.srcs.all_files ctx = CodeSummarizeContext(design_filename="1.json", task_filename="1.json", codes_filenames=all_files) action = SummarizeCode(i_context=ctx) rsp = await action.run() assert rsp logger.info(rsp) + + +if __name__ == "__main__": + pytest.main([__file__, "-s"]) diff --git a/tests/metagpt/actions/test_write_code.py b/tests/metagpt/actions/test_write_code.py index 792b89d90..96d982c69 100644 --- a/tests/metagpt/actions/test_write_code.py +++ b/tests/metagpt/actions/test_write_code.py @@ -12,26 +12,24 @@ from pathlib import Path import pytest from metagpt.actions.write_code import WriteCode -from metagpt.const import ( - CODE_SUMMARIES_FILE_REPO, - SYSTEM_DESIGN_FILE_REPO, - TASK_FILE_REPO, - TEST_OUTPUTS_FILE_REPO, -) from metagpt.context import CONTEXT from metagpt.llm import LLM from metagpt.logs import logger from metagpt.schema import CodingContext, Document from metagpt.utils.common import aread +from metagpt.utils.project_repo import ProjectRepo from tests.metagpt.actions.mock_markdown import TASKS_2, WRITE_CODE_PROMPT_SAMPLE @pytest.mark.asyncio async def test_write_code(): - ccontext = CodingContext( + # Prerequisites + CONTEXT.src_workspace = CONTEXT.git_repo.workdir / "writecode" + + coding_ctx = CodingContext( filename="task_filename.py", design_doc=Document(content="设计一个名为'add'的函数，该函数接受两个整数作为输入，并返回它们的和。") ) - doc = Document(content=ccontext.model_dump_json()) + doc = Document(content=coding_ctx.model_dump_json()) write_code = WriteCode(i_context=doc) code = await write_code.run() @@ -55,33 +53,28 @@ async def test_write_code_deps(): # Prerequisites CONTEXT.src_workspace = CONTEXT.git_repo.workdir / "snake1/snake1" demo_path = Path(__file__).parent / "../../data/demo_project" - await CONTEXT.file_repo.save_file( - filename="test_game.py.json", - content=await aread(str(demo_path / "test_game.py.json")), - relative_path=TEST_OUTPUTS_FILE_REPO, + project_repo = ProjectRepo(CONTEXT.git_repo) + await project_repo.test_outputs.save( + filename="test_game.py.json", content=await aread(str(demo_path / "test_game.py.json")) ) - await CONTEXT.file_repo.save_file( + await project_repo.docs.code_summary.save( filename="20231221155954.json", content=await aread(str(demo_path / "code_summaries.json")), - relative_path=CODE_SUMMARIES_FILE_REPO, ) - await CONTEXT.file_repo.save_file( + await project_repo.docs.system_design.save( filename="20231221155954.json", content=await aread(str(demo_path / "system_design.json")), - relative_path=SYSTEM_DESIGN_FILE_REPO, ) - await CONTEXT.file_repo.save_file( - filename="20231221155954.json", content=await aread(str(demo_path / "tasks.json")), relative_path=TASK_FILE_REPO + await project_repo.docs.task.save( + filename="20231221155954.json", content=await aread(str(demo_path / "tasks.json")) ) - await CONTEXT.file_repo.save_file( - filename="main.py", content='if __name__ == "__main__":\nmain()', relative_path=CONTEXT.src_workspace + await project_repo.with_src_path(CONTEXT.src_workspace).srcs.save( + filename="main.py", content='if __name__ == "__main__":\nmain()' ) ccontext = CodingContext( filename="game.py", - design_doc=await CONTEXT.file_repo.get_file( - filename="20231221155954.json", relative_path=SYSTEM_DESIGN_FILE_REPO - ), - task_doc=await CONTEXT.file_repo.get_file(filename="20231221155954.json", relative_path=TASK_FILE_REPO), + design_doc=await project_repo.docs.system_design.get(filename="20231221155954.json"), + task_doc=await project_repo.docs.task.get(filename="20231221155954.json"), code_doc=Document(filename="game.py", content="", root_path="snake1"), ) coding_doc = Document(root_path="snake1", filename="game.py", content=ccontext.json()) diff --git a/tests/metagpt/actions/test_write_prd.py b/tests/metagpt/actions/test_write_prd.py index 1a897ac2e..d854cd8d2 100644 --- a/tests/metagpt/actions/test_write_prd.py +++ b/tests/metagpt/actions/test_write_prd.py @@ -9,21 +9,22 @@ import pytest from metagpt.actions import UserRequirement, WritePRD -from metagpt.const import DOCS_FILE_REPO, PRDS_FILE_REPO, REQUIREMENT_FILENAME +from metagpt.const import REQUIREMENT_FILENAME from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.roles.product_manager import ProductManager from metagpt.roles.role import RoleReactMode from metagpt.schema import Message from metagpt.utils.common import any_to_str +from metagpt.utils.project_repo import ProjectRepo @pytest.mark.asyncio async def test_write_prd(new_filename): product_manager = ProductManager() requirements = "开发一个基于大语言模型与私有知识库的搜索引擎，希望可以基于大语言模型进行搜索总结" - repo = CONTEXT.file_repo - await repo.save_file(filename=REQUIREMENT_FILENAME, content=requirements, relative_path=DOCS_FILE_REPO) + project_repo = ProjectRepo(CONTEXT.git_repo) + await project_repo.docs.save(filename=REQUIREMENT_FILENAME, content=requirements) product_manager.rc.react_mode = RoleReactMode.BY_ORDER prd = await product_manager.run(Message(content=requirements, cause_by=UserRequirement)) assert prd.cause_by == any_to_str(WritePRD) @@ -33,7 +34,7 @@ async def test_write_prd(new_filename): # Assert the prd is not None or empty assert prd is not None assert prd.content != "" - assert CONTEXT.git_repo.new_file_repository(relative_path=PRDS_FILE_REPO).changed_files + assert ProjectRepo(product_manager.context.git_repo).docs.prd.changed_files if __name__ == "__main__": diff --git a/tests/metagpt/learn/test_text_to_embedding.py b/tests/metagpt/learn/test_text_to_embedding.py index cbc8ddf18..d8a251dc8 100644 --- a/tests/metagpt/learn/test_text_to_embedding.py +++ b/tests/metagpt/learn/test_text_to_embedding.py @@ -6,17 +6,30 @@ @File : test_text_to_embedding.py @Desc : Unit tests. """ +import json +from pathlib import Path import pytest from metagpt.config2 import config from metagpt.learn.text_to_embedding import text_to_embedding +from metagpt.utils.common import aread @pytest.mark.asyncio -async def test_text_to_embedding(): +async def test_text_to_embedding(mocker): + # mock + mock_post = mocker.patch("aiohttp.ClientSession.post") + mock_response = mocker.AsyncMock() + mock_response.status = 200 + data = await aread(Path(__file__).parent / "../../data/openai/embedding.json") + mock_response.json.return_value = json.loads(data) + mock_post.return_value.__aenter__.return_value = mock_response + type(config.get_openai_llm()).proxy = mocker.PropertyMock(return_value="http://mock.proxy") + # Prerequisites assert config.get_openai_llm() + assert config.get_openai_llm().proxy v = await text_to_embedding(text="Panda emoji") assert len(v.data) > 0 diff --git a/tests/metagpt/learn/test_text_to_image.py b/tests/metagpt/learn/test_text_to_image.py index 7c133149d..b58ff6580 100644 --- a/tests/metagpt/learn/test_text_to_image.py +++ b/tests/metagpt/learn/test_text_to_image.py @@ -6,9 +6,11 @@ @File : test_text_to_image.py @Desc : Unit tests. """ +import base64 - +import openai import pytest +from pydantic import BaseModel from metagpt.config2 import Config from metagpt.learn.text_to_image import text_to_image @@ -34,7 +36,23 @@ async def test_text_to_image(mocker): @pytest.mark.asyncio -async def test_openai_text_to_image(): +async def test_openai_text_to_image(mocker): + # mocker + mock_url = mocker.Mock() + mock_url.url.return_value = "http://mock.com/0.png" + + class _MockData(BaseModel): + data: list + + mock_data = _MockData(data=[mock_url]) + mocker.patch.object(openai.resources.images.AsyncImages, "generate", return_value=mock_data) + mock_post = mocker.patch("aiohttp.ClientSession.get") + mock_response = mocker.AsyncMock() + mock_response.status = 200 + mock_response.read.return_value = base64.b64encode(b"success") + mock_post.return_value.__aenter__.return_value = mock_response + mocker.patch.object(S3, "cache", return_value="http://mock.s3.com/0.png") + config = Config.default() assert config.get_openai_llm() diff --git a/tests/metagpt/tools/test_azure_tts.py b/tests/metagpt/tools/test_azure_tts.py index e856d3b27..74d23e439 100644 --- a/tests/metagpt/tools/test_azure_tts.py +++ b/tests/metagpt/tools/test_azure_tts.py @@ -7,21 +7,31 @@ @Modified By: mashenquan, 2023-8-9, add more text formatting options @Modified By: mashenquan, 2023-8-17, move to `tools` folder. """ +from pathlib import Path import pytest -from azure.cognitiveservices.speech import ResultReason +from azure.cognitiveservices.speech import ResultReason, SpeechSynthesizer from metagpt.config2 import config from metagpt.tools.azure_tts import AzureTTS @pytest.mark.asyncio -async def test_azure_tts(): +async def test_azure_tts(mocker): + # mock + mock_result = mocker.Mock() + mock_result.audio_data = b"mock audio data" + mock_result.reason = ResultReason.SynthesizingAudioCompleted + mock_data = mocker.Mock() + mock_data.get.return_value = mock_result + mocker.patch.object(SpeechSynthesizer, "speak_ssml_async", return_value=mock_data) + mocker.patch.object(Path, "exists", return_value=True) + # Prerequisites assert config.AZURE_TTS_SUBSCRIPTION_KEY and config.AZURE_TTS_SUBSCRIPTION_KEY != "YOUR_API_KEY" assert config.AZURE_TTS_REGION - azure_tts = AzureTTS(subscription_key="", region="") + azure_tts = AzureTTS(subscription_key=config.AZURE_TTS_SUBSCRIPTION_KEY, region=config.AZURE_TTS_REGION) text = """ 女儿看见父亲走了进来，问道： diff --git a/tests/metagpt/tools/test_openai_text_to_embedding.py b/tests/metagpt/tools/test_openai_text_to_embedding.py index 58c38d480..b4e9b3383 100644 --- a/tests/metagpt/tools/test_openai_text_to_embedding.py +++ b/tests/metagpt/tools/test_openai_text_to_embedding.py @@ -5,17 +5,30 @@ @Author : mashenquan @File : test_openai_text_to_embedding.py """ +import json +from pathlib import Path import pytest from metagpt.config2 import config from metagpt.tools.openai_text_to_embedding import oas3_openai_text_to_embedding +from metagpt.utils.common import aread @pytest.mark.asyncio -async def test_embedding(): +async def test_embedding(mocker): + # mock + mock_post = mocker.patch("aiohttp.ClientSession.post") + mock_response = mocker.AsyncMock() + mock_response.status = 200 + data = await aread(Path(__file__).parent / "../../data/openai/embedding.json") + mock_response.json.return_value = json.loads(data) + mock_post.return_value.__aenter__.return_value = mock_response + type(config.get_openai_llm()).proxy = mocker.PropertyMock(return_value="http://mock.proxy") + # Prerequisites assert config.get_openai_llm() + assert config.get_openai_llm().proxy result = await oas3_openai_text_to_embedding("Panda emoji") assert result diff --git a/tests/metagpt/tools/test_openai_text_to_image.py b/tests/metagpt/tools/test_openai_text_to_image.py index 1a1c9540f..5a6214d17 100644 --- a/tests/metagpt/tools/test_openai_text_to_image.py +++ b/tests/metagpt/tools/test_openai_text_to_image.py @@ -5,22 +5,44 @@ @Author : mashenquan @File : test_openai_text_to_image.py """ +import base64 +import openai import pytest +from pydantic import BaseModel from metagpt.config2 import config +from metagpt.llm import LLM from metagpt.tools.openai_text_to_image import ( OpenAIText2Image, oas3_openai_text_to_image, ) +from metagpt.utils.s3 import S3 @pytest.mark.asyncio -async def test_draw(): +async def test_draw(mocker): + # mock + mock_url = mocker.Mock() + mock_url.url.return_value = "http://mock.com/0.png" + + class _MockData(BaseModel): + data: list + + mock_data = _MockData(data=[mock_url]) + mocker.patch.object(openai.resources.images.AsyncImages, "generate", return_value=mock_data) + mock_post = mocker.patch("aiohttp.ClientSession.get") + mock_response = mocker.AsyncMock() + mock_response.status = 200 + mock_response.read.return_value = base64.b64encode(b"success") + mock_post.return_value.__aenter__.return_value = mock_response + mocker.patch.object(S3, "cache", return_value="http://mock.s3.com/0.png") + # Prerequisites assert config.get_openai_llm() + assert config.get_openai_llm().proxy - binary_data = await oas3_openai_text_to_image("Panda emoji") + binary_data = await oas3_openai_text_to_image("Panda emoji", llm=LLM()) assert binary_data From e350656725cf6a7a6ad083df243e87c980321767 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=8E=98=E6=9D=83=20=E9=A9=AC?= Date: Fri, 12 Jan 2024 15:27:07 +0800 Subject: [PATCH 52/61] fixbug: unit test --- metagpt/actions/skill_action.py | 9 +- metagpt/actions/write_teaching_plan.py | 12 ++- metagpt/context.py | 18 +++- metagpt/learn/text_to_embedding.py | 11 ++- metagpt/learn/text_to_image.py | 10 +-- metagpt/learn/text_to_speech.py | 17 ++-- metagpt/roles/assistant.py | 8 +- metagpt/roles/teacher.py | 10 +-- metagpt/tools/openai_text_to_embedding.py | 19 ++-- tests/data/demo_project/dependencies.json | 2 +- tests/metagpt/learn/test_text_to_embedding.py | 4 +- tests/metagpt/learn/test_text_to_image.py | 5 +- tests/metagpt/learn/test_text_to_speech.py | 73 +++++++++------ tests/metagpt/roles/test_assistant.py | 14 ++- tests/metagpt/roles/test_engineer.py | 88 ++++++++++--------- tests/metagpt/roles/test_teacher.py | 22 +++-- tests/metagpt/tools/test_iflytek_tts.py | 16 +++- .../tools/test_openai_text_to_embedding.py | 9 +- .../tools/test_openai_text_to_image.py | 6 +- 19 files changed, 207 insertions(+), 146 deletions(-) diff --git a/metagpt/actions/skill_action.py b/metagpt/actions/skill_action.py index 301cebaab..b68596809 100644 --- a/metagpt/actions/skill_action.py +++ b/metagpt/actions/skill_action.py @@ -29,9 +29,7 @@ class ArgumentsParingAction(Action): @property def prompt(self): - prompt = "You are a function parser. You can convert spoken words into function parameters.\n" - prompt += "\n---\n" - prompt += f"{self.skill.name} function parameters description:\n" + prompt = f"{self.skill.name} function parameters description:\n" for k, v in self.skill.arguments.items(): prompt += f"parameter `{k}`: {v}\n" prompt += "\n---\n" @@ -49,7 +47,10 @@ class ArgumentsParingAction(Action): async def run(self, with_message=None, **kwargs) -> Message: prompt = self.prompt - rsp = await self.llm.aask(msg=prompt, system_msgs=[]) + rsp = await self.llm.aask( + msg=prompt, + system_msgs=["You are a function parser.", "You can convert spoken words into function parameters."], + ) logger.debug(f"SKILL:{prompt}\n, RESULT:{rsp}") self.args = ArgumentsParingAction.parse_arguments(skill_name=self.skill.name, txt=rsp) self.rsp = Message(content=rsp, role="assistant", instruct_content=self.args, cause_by=self) diff --git a/metagpt/actions/write_teaching_plan.py b/metagpt/actions/write_teaching_plan.py index 1678bc8dc..834f07006 100644 --- a/metagpt/actions/write_teaching_plan.py +++ b/metagpt/actions/write_teaching_plan.py @@ -8,7 +8,6 @@ from typing import Optional from metagpt.actions import Action -from metagpt.context import CONTEXT from metagpt.logs import logger @@ -24,7 +23,7 @@ class WriteTeachingPlanPart(Action): statement_patterns = TeachingPlanBlock.TOPIC_STATEMENTS.get(self.topic, []) statements = [] for p in statement_patterns: - s = self.format_value(p) + s = self.format_value(p, options=self.context.options) statements.append(s) formatter = ( TeachingPlanBlock.PROMPT_TITLE_TEMPLATE @@ -68,21 +67,20 @@ class WriteTeachingPlanPart(Action): return self.topic @staticmethod - def format_value(value): + def format_value(value, options): """Fill parameters inside `value` with `options`.""" if not isinstance(value, str): return value if "{" not in value: return value - # FIXME: 从Context中获取参数，而非从options - merged_opts = CONTEXT.options or {} + opts = {k: v for k, v in options.items() if v is not None} try: - return value.format(**merged_opts) + return value.format(**opts) except KeyError as e: logger.warning(f"Parameter is missing:{e}") - for k, v in merged_opts.items(): + for k, v in opts.items(): value = value.replace("{" + f"{k}" + "}", str(v)) return value diff --git a/metagpt/context.py b/metagpt/context.py index 0ce2f4b40..75dc31ef2 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -7,13 +7,12 @@ """ import os from pathlib import Path -from typing import Optional +from typing import Any, Optional from pydantic import BaseModel, ConfigDict from metagpt.config2 import Config from metagpt.configs.llm_config import LLMConfig -from metagpt.const import OPTIONS from metagpt.provider.base_llm import BaseLLM from metagpt.provider.llm_provider_registry import create_llm_instance from metagpt.utils.cost_manager import CostManager @@ -41,6 +40,16 @@ class AttrDict(BaseModel): else: raise AttributeError(f"No such attribute: {key}") + def set(self, key, val: Any): + self.__dict__[key] = val + + def get(self, key, default: Any = None): + return self.__dict__.get(key, default) + + def remove(self, key): + if key in self.__dict__: + self.__delattr__(key) + class Context(BaseModel): """Env context for MetaGPT""" @@ -58,7 +67,10 @@ class Context(BaseModel): @property def options(self): """Return all key-values""" - return OPTIONS.get() + opts = self.config.model_dump() + for k, v in self.kwargs: + opts[k] = v # None value is allowed to override and disable the value from config. + return opts def new_environ(self): """Return a new os.environ object""" diff --git a/metagpt/learn/text_to_embedding.py b/metagpt/learn/text_to_embedding.py index 6a4342b06..f859ab638 100644 --- a/metagpt/learn/text_to_embedding.py +++ b/metagpt/learn/text_to_embedding.py @@ -6,16 +6,19 @@ @File : text_to_embedding.py @Desc : Text-to-Embedding skill, which provides text-to-embedding functionality. """ - +import metagpt.config2 +from metagpt.config2 import Config from metagpt.tools.openai_text_to_embedding import oas3_openai_text_to_embedding -async def text_to_embedding(text, model="text-embedding-ada-002", openai_api_key="", **kwargs): +async def text_to_embedding(text, model="text-embedding-ada-002", config: Config = metagpt.config2.config): """Text to embedding :param text: The text used for embedding. :param model: One of ['text-embedding-ada-002'], ID of the model to use. For more details, checkout: `https://api.openai.com/v1/models`. - :param openai_api_key: OpenAI API key, For more details, checkout: `https://platform.openai.com/account/api-keys` + :param config: OpenAI config with API key, For more details, checkout: `https://platform.openai.com/account/api-keys` :return: A json object of :class:`ResultEmbedding` class if successful, otherwise `{}`. """ - return await oas3_openai_text_to_embedding(text, model=model, openai_api_key=openai_api_key) + openai_api_key = config.get_openai_llm().api_key + proxy = config.get_openai_llm().proxy + return await oas3_openai_text_to_embedding(text, model=model, openai_api_key=openai_api_key, proxy=proxy) diff --git a/metagpt/learn/text_to_image.py b/metagpt/learn/text_to_image.py index 8b2cb4473..e2fac7647 100644 --- a/metagpt/learn/text_to_image.py +++ b/metagpt/learn/text_to_image.py @@ -8,6 +8,7 @@ """ import base64 +import metagpt.config2 from metagpt.config2 import Config from metagpt.const import BASE64_FORMAT from metagpt.llm import LLM @@ -16,27 +17,26 @@ from metagpt.tools.openai_text_to_image import oas3_openai_text_to_image from metagpt.utils.s3 import S3 -async def text_to_image(text, size_type: str = "512x512", model_url="", config: Config = None): +async def text_to_image(text, size_type: str = "512x512", config: Config = metagpt.config2.config): """Text to image :param text: The text used for image conversion. - :param openai_api_key: OpenAI API key, For more details, checkout: `https://platform.openai.com/account/api-keys` :param size_type: If using OPENAI, the available size options are ['256x256', '512x512', '1024x1024'], while for MetaGPT, the options are ['512x512', '512x768']. - :param model_url: MetaGPT model url :param config: Config :return: The image data is returned in Base64 encoding. """ image_declaration = "data:image/png;base64," + model_url = config.METAGPT_TEXT_TO_IMAGE_MODEL_URL if model_url: binary_data = await oas3_metagpt_text_to_image(text, size_type, model_url) elif config.get_openai_llm(): - binary_data = await oas3_openai_text_to_image(text, size_type, LLM()) + llm = LLM(llm_config=config.get_openai_llm()) + binary_data = await oas3_openai_text_to_image(text, size_type, llm=llm) else: raise ValueError("Missing necessary parameters.") base64_data = base64.b64encode(binary_data).decode("utf-8") - assert config.s3, "S3 config is required." s3 = S3(config.s3) url = await s3.cache(data=base64_data, file_ext=".png", format=BASE64_FORMAT) if url: diff --git a/metagpt/learn/text_to_speech.py b/metagpt/learn/text_to_speech.py index 8ffafbd0e..37e56eaff 100644 --- a/metagpt/learn/text_to_speech.py +++ b/metagpt/learn/text_to_speech.py @@ -6,8 +6,8 @@ @File : text_to_speech.py @Desc : Text-to-Speech skill, which provides text-to-speech functionality """ - -from metagpt.config2 import config +import metagpt.config2 +from metagpt.config2 import Config from metagpt.const import BASE64_FORMAT from metagpt.tools.azure_tts import oas3_azsure_tts from metagpt.tools.iflytek_tts import oas3_iflytek_tts @@ -20,12 +20,7 @@ async def text_to_speech( voice="zh-CN-XiaomoNeural", style="affectionate", role="Girl", - subscription_key="", - region="", - iflytek_app_id="", - iflytek_api_key="", - iflytek_api_secret="", - **kwargs, + config: Config = metagpt.config2.config, ): """Text to speech For more details, check out:`https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=tts` @@ -44,6 +39,8 @@ async def text_to_speech( """ + subscription_key = config.AZURE_TTS_SUBSCRIPTION_KEY + region = config.AZURE_TTS_REGION if subscription_key and region: audio_declaration = "data:audio/wav;base64," base64_data = await oas3_azsure_tts(text, lang, voice, style, role, subscription_key, region) @@ -52,6 +49,10 @@ async def text_to_speech( if url: return f"[{text}]({url})" return audio_declaration + base64_data if base64_data else base64_data + + iflytek_app_id = config.IFLYTEK_APP_ID + iflytek_api_key = config.IFLYTEK_API_KEY + iflytek_api_secret = config.IFLYTEK_API_SECRET if iflytek_app_id and iflytek_api_key and iflytek_api_secret: audio_declaration = "data:audio/mp3;base64," base64_data = await oas3_iflytek_tts( diff --git a/metagpt/roles/assistant.py b/metagpt/roles/assistant.py index 8939094ed..1c5315eee 100644 --- a/metagpt/roles/assistant.py +++ b/metagpt/roles/assistant.py @@ -65,7 +65,7 @@ class Assistant(Role): prompt += f"If the text explicitly want you to {desc}, return `[SKILL]: {name}` brief and clear. For instance: [SKILL]: {name}\n" prompt += 'Otherwise, return `[TALK]: {talk}` brief and clear. For instance: if {talk} is "xxxx" return [TALK]: xxxx\n\n' prompt += f"Now what specific action is explicitly mentioned in the text: {last_talk}\n" - rsp = await self.llm.aask(prompt, []) + rsp = await self.llm.aask(prompt, ["You are an action classifier"]) logger.info(f"THINK: {prompt}\n, THINK RESULT: {rsp}\n") return await self._plan(rsp, last_talk=last_talk) @@ -98,9 +98,7 @@ class Assistant(Role): history = self.memory.history_text text = kwargs.get("last_talk") or text self.set_todo( - TalkAction( - context=text, knowledge=self.memory.get_knowledge(), history_summary=history, llm=self.llm, **kwargs - ) + TalkAction(i_context=text, knowledge=self.memory.get_knowledge(), history_summary=history, llm=self.llm) ) return True @@ -110,7 +108,7 @@ class Assistant(Role): if not skill: logger.info(f"skill not found: {text}") return await self.talk_handler(text=last_talk, **kwargs) - action = ArgumentsParingAction(skill=skill, llm=self.llm, ask=last_talk, **kwargs) + action = ArgumentsParingAction(skill=skill, llm=self.llm, ask=last_talk) await action.run(**kwargs) if action.args is None: return await self.talk_handler(text=last_talk, **kwargs) diff --git a/metagpt/roles/teacher.py b/metagpt/roles/teacher.py index d47f4af5b..a40ba69fe 100644 --- a/metagpt/roles/teacher.py +++ b/metagpt/roles/teacher.py @@ -31,11 +31,11 @@ class Teacher(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self.name = WriteTeachingPlanPart.format_value(self.name) - self.profile = WriteTeachingPlanPart.format_value(self.profile) - self.goal = WriteTeachingPlanPart.format_value(self.goal) - self.constraints = WriteTeachingPlanPart.format_value(self.constraints) - self.desc = WriteTeachingPlanPart.format_value(self.desc) + self.name = WriteTeachingPlanPart.format_value(self.name, self.context.options) + self.profile = WriteTeachingPlanPart.format_value(self.profile, self.context.options) + self.goal = WriteTeachingPlanPart.format_value(self.goal, self.context.options) + self.constraints = WriteTeachingPlanPart.format_value(self.constraints, self.context.options) + self.desc = WriteTeachingPlanPart.format_value(self.desc, self.context.options) async def _think(self) -> bool: """Everything will be done part by part.""" diff --git a/metagpt/tools/openai_text_to_embedding.py b/metagpt/tools/openai_text_to_embedding.py index 3eb9faac4..e93bfb271 100644 --- a/metagpt/tools/openai_text_to_embedding.py +++ b/metagpt/tools/openai_text_to_embedding.py @@ -13,7 +13,6 @@ import aiohttp import requests from pydantic import BaseModel, Field -from metagpt.config2 import config from metagpt.logs import logger @@ -43,12 +42,12 @@ class ResultEmbedding(BaseModel): class OpenAIText2Embedding: - def __init__(self, openai_api_key): + def __init__(self, api_key: str, proxy: str): """ :param openai_api_key: OpenAI API key, For more details, checkout: `https://platform.openai.com/account/api-keys` """ - self.openai_llm = config.get_openai_llm() - self.openai_api_key = openai_api_key or self.openai_llm.api_key + self.api_key = api_key + self.proxy = proxy async def text_2_embedding(self, text, model="text-embedding-ada-002"): """Text to embedding @@ -58,8 +57,8 @@ class OpenAIText2Embedding: :return: A json object of :class:`ResultEmbedding` class if successful, otherwise `{}`. """ - proxies = {"proxy": self.openai_llm.proxy} if self.openai_llm.proxy else {} - headers = {"Content-Type": "application/json", "Authorization": f"Bearer {self.openai_api_key}"} + proxies = {"proxy": self.proxy} if self.proxy else {} + headers = {"Content-Type": "application/json", "Authorization": f"Bearer {self.api_key}"} data = {"input": text, "model": model} url = "https://api.openai.com/v1/embeddings" try: @@ -73,16 +72,14 @@ class OpenAIText2Embedding: # Export -async def oas3_openai_text_to_embedding(text, model="text-embedding-ada-002", openai_api_key=""): +async def oas3_openai_text_to_embedding(text, openai_api_key: str, model="text-embedding-ada-002", proxy: str = ""): """Text to embedding :param text: The text used for embedding. :param model: One of ['text-embedding-ada-002'], ID of the model to use. For more details, checkout: `https://api.openai.com/v1/models`. - :param openai_api_key: OpenAI API key, For more details, checkout: `https://platform.openai.com/account/api-keys` + :param config: OpenAI config with API key, For more details, checkout: `https://platform.openai.com/account/api-keys` :return: A json object of :class:`ResultEmbedding` class if successful, otherwise `{}`. """ if not text: return "" - if not openai_api_key: - openai_api_key = config.get_openai_llm().api_key - return await OpenAIText2Embedding(openai_api_key).text_2_embedding(text, model=model) + return await OpenAIText2Embedding(api_key=openai_api_key, proxy=proxy).text_2_embedding(text, model=model) diff --git a/tests/data/demo_project/dependencies.json b/tests/data/demo_project/dependencies.json index cfcf6c165..738e5d9be 100644 --- a/tests/data/demo_project/dependencies.json +++ b/tests/data/demo_project/dependencies.json @@ -1 +1 @@ -{"docs/system_design/20231221155954.json": ["docs/prds/20231221155954.json"], "docs/tasks/20231221155954.json": ["docs/system_design/20231221155954.json"], "game_2048/game.py": ["docs/tasks/20231221155954.json", "docs/system_design/20231221155954.json"], "game_2048/main.py": ["docs/tasks/20231221155954.json", "docs/system_design/20231221155954.json"], "resources/code_summaries/20231221155954.md": ["docs/tasks/20231221155954.json", "game_2048/game.py", "docs/system_design/20231221155954.json", "game_2048/main.py"], "docs/code_summaries/20231221155954.json": ["docs/tasks/20231221155954.json", "game_2048/game.py", "docs/system_design/20231221155954.json", "game_2048/main.py"], "tests/test_main.py": ["game_2048/main.py"], "tests/test_game.py": ["game_2048/game.py"], "test_outputs/test_main.py.json": ["game_2048/main.py", "tests/test_main.py"], "test_outputs/test_game.py.json": ["game_2048/game.py", "tests/test_game.py"]} \ No newline at end of file +{"docs/system_design/20231221155954.json": ["docs/prd/20231221155954.json"], "docs/task/20231221155954.json": ["docs/system_design/20231221155954.json"], "game_2048/game.py": ["docs/task/20231221155954.json", "docs/system_design/20231221155954.json"], "game_2048/main.py": ["docs/task/20231221155954.json", "docs/system_design/20231221155954.json"], "resources/code_summary/20231221155954.md": ["docs/task/20231221155954.json", "game_2048/game.py", "docs/system_design/20231221155954.json", "game_2048/main.py"], "docs/code_summary/20231221155954.json": ["docs/task/20231221155954.json", "game_2048/game.py", "docs/system_design/20231221155954.json", "game_2048/main.py"], "tests/test_main.py": ["game_2048/main.py"], "tests/test_game.py": ["game_2048/game.py"], "test_outputs/test_main.py.json": ["game_2048/main.py", "tests/test_main.py"], "test_outputs/test_game.py.json": ["game_2048/game.py", "tests/test_game.py"]} \ No newline at end of file diff --git a/tests/metagpt/learn/test_text_to_embedding.py b/tests/metagpt/learn/test_text_to_embedding.py index d8a251dc8..8891960c1 100644 --- a/tests/metagpt/learn/test_text_to_embedding.py +++ b/tests/metagpt/learn/test_text_to_embedding.py @@ -28,10 +28,10 @@ async def test_text_to_embedding(mocker): type(config.get_openai_llm()).proxy = mocker.PropertyMock(return_value="http://mock.proxy") # Prerequisites - assert config.get_openai_llm() + assert config.get_openai_llm().api_key assert config.get_openai_llm().proxy - v = await text_to_embedding(text="Panda emoji") + v = await text_to_embedding(text="Panda emoji", config=config) assert len(v.data) > 0 diff --git a/tests/metagpt/learn/test_text_to_image.py b/tests/metagpt/learn/test_text_to_image.py index b58ff6580..167a35891 100644 --- a/tests/metagpt/learn/test_text_to_image.py +++ b/tests/metagpt/learn/test_text_to_image.py @@ -29,9 +29,7 @@ async def test_text_to_image(mocker): config = Config.default() assert config.METAGPT_TEXT_TO_IMAGE_MODEL_URL - data = await text_to_image( - "Panda emoji", size_type="512x512", model_url=config.METAGPT_TEXT_TO_IMAGE_MODEL_URL, config=config - ) + data = await text_to_image("Panda emoji", size_type="512x512", config=config) assert "base64" in data or "http" in data @@ -54,6 +52,7 @@ async def test_openai_text_to_image(mocker): mocker.patch.object(S3, "cache", return_value="http://mock.s3.com/0.png") config = Config.default() + config.METAGPT_TEXT_TO_IMAGE_MODEL_URL = None assert config.get_openai_llm() data = await text_to_image("Panda emoji", size_type="512x512", config=config) diff --git a/tests/metagpt/learn/test_text_to_speech.py b/tests/metagpt/learn/test_text_to_speech.py index 41611171c..38e051cc6 100644 --- a/tests/metagpt/learn/test_text_to_speech.py +++ b/tests/metagpt/learn/test_text_to_speech.py @@ -8,43 +8,64 @@ """ import pytest +from azure.cognitiveservices.speech import ResultReason, SpeechSynthesizer -from metagpt.config2 import config +from metagpt.config2 import Config from metagpt.learn.text_to_speech import text_to_speech +from metagpt.tools.iflytek_tts import IFlyTekTTS +from metagpt.utils.s3 import S3 @pytest.mark.asyncio -async def test_text_to_speech(): +async def test_azure_text_to_speech(mocker): + # mock + config = Config.default() + config.IFLYTEK_API_KEY = None + config.IFLYTEK_API_SECRET = None + config.IFLYTEK_APP_ID = None + mock_result = mocker.Mock() + mock_result.audio_data = b"mock audio data" + mock_result.reason = ResultReason.SynthesizingAudioCompleted + mock_data = mocker.Mock() + mock_data.get.return_value = mock_result + mocker.patch.object(SpeechSynthesizer, "speak_ssml_async", return_value=mock_data) + mocker.patch.object(S3, "cache", return_value="http://mock.s3.com/1.wav") + + # Prerequisites + assert not config.IFLYTEK_APP_ID + assert not config.IFLYTEK_API_KEY + assert not config.IFLYTEK_API_SECRET + assert config.AZURE_TTS_SUBSCRIPTION_KEY and config.AZURE_TTS_SUBSCRIPTION_KEY != "YOUR_API_KEY" + assert config.AZURE_TTS_REGION + + config.copy() + # test azure + data = await text_to_speech("panda emoji", config=config) + assert "base64" in data or "http" in data + + +@pytest.mark.asyncio +async def test_iflytek_text_to_speech(mocker): + # mock + config = Config.default() + config.AZURE_TTS_SUBSCRIPTION_KEY = None + config.AZURE_TTS_REGION = None + mocker.patch.object(IFlyTekTTS, "synthesize_speech", return_value=None) + mock_data = mocker.AsyncMock() + mock_data.read.return_value = b"mock iflytek" + mock_reader = mocker.patch("aiofiles.open") + mock_reader.return_value.__aenter__.return_value = mock_data + mocker.patch.object(S3, "cache", return_value="http://mock.s3.com/1.mp3") + # Prerequisites assert config.IFLYTEK_APP_ID assert config.IFLYTEK_API_KEY assert config.IFLYTEK_API_SECRET - assert config.AZURE_TTS_SUBSCRIPTION_KEY and config.AZURE_TTS_SUBSCRIPTION_KEY != "YOUR_API_KEY" - assert config.AZURE_TTS_REGION + assert not config.AZURE_TTS_SUBSCRIPTION_KEY or config.AZURE_TTS_SUBSCRIPTION_KEY == "YOUR_API_KEY" + assert not config.AZURE_TTS_REGION - i = config.copy() # test azure - data = await text_to_speech( - "panda emoji", - subscription_key=i.AZURE_TTS_SUBSCRIPTION_KEY, - region=i.AZURE_TTS_REGION, - iflytek_api_key=i.IFLYTEK_API_KEY, - iflytek_api_secret=i.IFLYTEK_API_SECRET, - iflytek_app_id=i.IFLYTEK_APP_ID, - ) - assert "base64" in data or "http" in data - - # test iflytek - ## Mock session env - i.AZURE_TTS_SUBSCRIPTION_KEY = "" - data = await text_to_speech( - "panda emoji", - subscription_key=i.AZURE_TTS_SUBSCRIPTION_KEY, - region=i.AZURE_TTS_REGION, - iflytek_api_key=i.IFLYTEK_API_KEY, - iflytek_api_secret=i.IFLYTEK_API_SECRET, - iflytek_app_id=i.IFLYTEK_APP_ID, - ) + data = await text_to_speech("panda emoji", config=config) assert "base64" in data or "http" in data diff --git a/tests/metagpt/roles/test_assistant.py b/tests/metagpt/roles/test_assistant.py index 4ef44d77a..b9740a112 100644 --- a/tests/metagpt/roles/test_assistant.py +++ b/tests/metagpt/roles/test_assistant.py @@ -20,7 +20,10 @@ from metagpt.utils.common import any_to_str @pytest.mark.asyncio -async def test_run(): +async def test_run(mocker): + # mock + mocker.patch("metagpt.learn.text_to_image", return_value="http://mock.com/1.png") + CONTEXT.kwargs.language = "Chinese" class Input(BaseModel): @@ -65,7 +68,7 @@ async def test_run(): "cause_by": any_to_str(SkillAction), }, ] - CONTEXT.kwargs.agent_skills = [ + agent_skills = [ {"id": 1, "name": "text_to_speech", "type": "builtin", "config": {}, "enabled": True}, {"id": 2, "name": "text_to_image", "type": "builtin", "config": {}, "enabled": True}, {"id": 3, "name": "ai_call", "type": "builtin", "config": {}, "enabled": True}, @@ -77,9 +80,11 @@ async def test_run(): for i in inputs: seed = Input(**i) - CONTEXT.kwargs.language = seed.language - CONTEXT.kwargs.agent_description = seed.agent_description role = Assistant(language="Chinese") + role.context.kwargs.language = seed.language + role.context.kwargs.agent_description = seed.agent_description + role.context.kwargs.agent_skills = agent_skills + role.memory = seed.memory # Restore historical conversation content. while True: has_action = await role.think() @@ -112,6 +117,7 @@ async def test_run(): @pytest.mark.asyncio async def test_memory(memory): role = Assistant() + role.context.kwargs.agent_skills = [] role.load_memory(memory) val = role.get_memory() diff --git a/tests/metagpt/roles/test_engineer.py b/tests/metagpt/roles/test_engineer.py index 710e74b8f..17b94828c 100644 --- a/tests/metagpt/roles/test_engineer.py +++ b/tests/metagpt/roles/test_engineer.py @@ -8,23 +8,25 @@ distribution feature for message handling. """ import json +import uuid from pathlib import Path import pytest from metagpt.actions import WriteCode, WriteTasks from metagpt.const import ( - PRDS_FILE_REPO, + DEFAULT_WORKSPACE_ROOT, REQUIREMENT_FILENAME, SYSTEM_DESIGN_FILE_REPO, TASK_FILE_REPO, ) -from metagpt.context import CONTEXT +from metagpt.context import CONTEXT, Context from metagpt.logs import logger from metagpt.roles.engineer import Engineer from metagpt.schema import CodingContext, Message from metagpt.utils.common import CodeParser, any_to_name, any_to_str, aread, awrite -from metagpt.utils.git_repository import ChangeType +from metagpt.utils.git_repository import ChangeType, GitRepository +from metagpt.utils.project_repo import ProjectRepo from tests.metagpt.roles.mock import STRS_FOR_PARSING, TASKS, MockMessages @@ -32,20 +34,18 @@ from tests.metagpt.roles.mock import STRS_FOR_PARSING, TASKS, MockMessages async def test_engineer(): # Prerequisites rqno = "20231221155954.json" - await CONTEXT.file_repo.save_file(REQUIREMENT_FILENAME, content=MockMessages.req.content) - await CONTEXT.file_repo.save_file(rqno, relative_path=PRDS_FILE_REPO, content=MockMessages.prd.content) - await CONTEXT.file_repo.save_file( - rqno, relative_path=SYSTEM_DESIGN_FILE_REPO, content=MockMessages.system_design.content - ) - await CONTEXT.file_repo.save_file(rqno, relative_path=TASK_FILE_REPO, content=MockMessages.json_tasks.content) + project_repo = ProjectRepo(CONTEXT.git_repo) + await project_repo.save(REQUIREMENT_FILENAME, content=MockMessages.req.content) + await project_repo.docs.prd.save(rqno, content=MockMessages.prd.content) + await project_repo.docs.system_design.save(rqno, content=MockMessages.system_design.content) + await project_repo.docs.task.save(rqno, content=MockMessages.json_tasks.content) engineer = Engineer() rsp = await engineer.run(Message(content="", cause_by=WriteTasks)) logger.info(rsp) assert rsp.cause_by == any_to_str(WriteCode) - src_file_repo = CONTEXT.git_repo.new_file_repository(CONTEXT.src_workspace) - assert src_file_repo.changed_files + assert project_repo.with_src_path(CONTEXT.src_workspace).srcs.changed_files def test_parse_str(): @@ -114,48 +114,50 @@ def test_todo(): @pytest.mark.asyncio async def test_new_coding_context(): # Prerequisites + context = Context() + context.git_repo = GitRepository(local_path=DEFAULT_WORKSPACE_ROOT / f"unittest/{uuid.uuid4().hex}") demo_path = Path(__file__).parent / "../../data/demo_project" deps = json.loads(await aread(demo_path / "dependencies.json")) - dependency = await CONTEXT.git_repo.get_dependency() + dependency = await context.git_repo.get_dependency() for k, v in deps.items(): await dependency.update(k, set(v)) data = await aread(demo_path / "system_design.json") rqno = "20231221155954.json" - await awrite(CONTEXT.git_repo.workdir / SYSTEM_DESIGN_FILE_REPO / rqno, data) + await awrite(context.git_repo.workdir / SYSTEM_DESIGN_FILE_REPO / rqno, data) data = await aread(demo_path / "tasks.json") - await awrite(CONTEXT.git_repo.workdir / TASK_FILE_REPO / rqno, data) + await awrite(context.git_repo.workdir / TASK_FILE_REPO / rqno, data) - CONTEXT.src_workspace = Path(CONTEXT.git_repo.workdir) / "game_2048" - src_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=CONTEXT.src_workspace) - task_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=TASK_FILE_REPO) - design_file_repo = CONTEXT.git_repo.new_file_repository(relative_path=SYSTEM_DESIGN_FILE_REPO) + context.src_workspace = Path(context.git_repo.workdir) / "game_2048" - filename = "game.py" - ctx_doc = await Engineer._new_coding_doc( - filename=filename, - src_file_repo=src_file_repo, - task_file_repo=task_file_repo, - design_file_repo=design_file_repo, - dependency=dependency, - ) - assert ctx_doc - assert ctx_doc.filename == filename - assert ctx_doc.content - ctx = CodingContext.model_validate_json(ctx_doc.content) - assert ctx.filename == filename - assert ctx.design_doc - assert ctx.design_doc.content - assert ctx.task_doc - assert ctx.task_doc.content - assert ctx.code_doc + try: + filename = "game.py" + engineer = Engineer(context=context) + ctx_doc = await engineer._new_coding_doc( + filename=filename, + dependency=dependency, + ) + assert ctx_doc + assert ctx_doc.filename == filename + assert ctx_doc.content + ctx = CodingContext.model_validate_json(ctx_doc.content) + assert ctx.filename == filename + assert ctx.design_doc + assert ctx.design_doc.content + assert ctx.task_doc + assert ctx.task_doc.content + assert ctx.code_doc - CONTEXT.git_repo.add_change({f"{TASK_FILE_REPO}/{rqno}": ChangeType.UNTRACTED}) - CONTEXT.git_repo.commit("mock env") - await src_file_repo.save(filename=filename, content="content") - role = Engineer() - assert not role.code_todos - await role._new_code_actions() - assert role.code_todos + context.git_repo.add_change({f"{TASK_FILE_REPO}/{rqno}": ChangeType.UNTRACTED}) + context.git_repo.commit("mock env") + await ProjectRepo(context.git_repo).with_src_path(context.src_workspace).srcs.save( + filename=filename, content="content" + ) + role = Engineer(context=context) + assert not role.code_todos + await role._new_code_actions() + assert role.code_todos + finally: + context.git_repo.delete_repository() if __name__ == "__main__": diff --git a/tests/metagpt/roles/test_teacher.py b/tests/metagpt/roles/test_teacher.py index 8bd37f482..83a7e382a 100644 --- a/tests/metagpt/roles/test_teacher.py +++ b/tests/metagpt/roles/test_teacher.py @@ -8,15 +8,14 @@ from typing import Dict, Optional import pytest -from pydantic import BaseModel +from pydantic import BaseModel, Field -from metagpt.context import CONTEXT +from metagpt.context import Context from metagpt.roles.teacher import Teacher from metagpt.schema import Message @pytest.mark.asyncio -@pytest.mark.skip async def test_init(): class Inputs(BaseModel): name: str @@ -30,6 +29,7 @@ async def test_init(): expect_goal: str expect_constraints: str expect_desc: str + exclude: list = Field(default_factory=list) inputs = [ { @@ -44,6 +44,7 @@ async def test_init(): "kwargs": {}, "desc": "aaa{language}", "expect_desc": "aaa{language}", + "exclude": ["language", "key1", "something_big", "teaching_language"], }, { "name": "Lily{language}", @@ -57,13 +58,21 @@ async def test_init(): "kwargs": {"language": "CN", "key1": "HaHa", "something_big": "sleep", "teaching_language": "EN"}, "desc": "aaa{language}", "expect_desc": "aaaCN", + "language": "CN", + "teaching_language": "EN", }, ] for i in inputs: seed = Inputs(**i) + context = Context() + for k in seed.exclude: + context.kwargs.set(k, None) + for k, v in seed.kwargs.items(): + context.kwargs.set(k, v) teacher = Teacher( + context=context, name=seed.name, profile=seed.profile, goal=seed.goal, @@ -97,8 +106,6 @@ async def test_new_file_name(): @pytest.mark.asyncio async def test_run(): - CONTEXT.kwargs.language = "Chinese" - CONTEXT.kwargs.teaching_language = "English" lesson = """ UNIT 1 Making New Friends TOPIC 1 Welcome to China! @@ -142,7 +149,10 @@ async def test_run(): 3c Match the big letters with the small ones. Then write them on the lines. """ - teacher = Teacher() + context = Context() + context.kwargs.language = "Chinese" + context.kwargs.teaching_language = "English" + teacher = Teacher(context=context) rsp = await teacher.run(Message(content=lesson)) assert rsp diff --git a/tests/metagpt/tools/test_iflytek_tts.py b/tests/metagpt/tools/test_iflytek_tts.py index 18af0a723..8e4c0cf54 100644 --- a/tests/metagpt/tools/test_iflytek_tts.py +++ b/tests/metagpt/tools/test_iflytek_tts.py @@ -7,12 +7,22 @@ """ import pytest -from metagpt.config2 import config -from metagpt.tools.iflytek_tts import oas3_iflytek_tts +from metagpt.config2 import Config +from metagpt.tools.iflytek_tts import IFlyTekTTS, oas3_iflytek_tts @pytest.mark.asyncio -async def test_tts(): +async def test_iflytek_tts(mocker): + # mock + config = Config.default() + config.AZURE_TTS_SUBSCRIPTION_KEY = None + config.AZURE_TTS_REGION = None + mocker.patch.object(IFlyTekTTS, "synthesize_speech", return_value=None) + mock_data = mocker.AsyncMock() + mock_data.read.return_value = b"mock iflytek" + mock_reader = mocker.patch("aiofiles.open") + mock_reader.return_value.__aenter__.return_value = mock_data + # Prerequisites assert config.IFLYTEK_APP_ID assert config.IFLYTEK_API_KEY diff --git a/tests/metagpt/tools/test_openai_text_to_embedding.py b/tests/metagpt/tools/test_openai_text_to_embedding.py index b4e9b3383..047206d48 100644 --- a/tests/metagpt/tools/test_openai_text_to_embedding.py +++ b/tests/metagpt/tools/test_openai_text_to_embedding.py @@ -27,10 +27,13 @@ async def test_embedding(mocker): type(config.get_openai_llm()).proxy = mocker.PropertyMock(return_value="http://mock.proxy") # Prerequisites - assert config.get_openai_llm() - assert config.get_openai_llm().proxy + llm_config = config.get_openai_llm() + assert llm_config + assert llm_config.proxy - result = await oas3_openai_text_to_embedding("Panda emoji") + result = await oas3_openai_text_to_embedding( + "Panda emoji", openai_api_key=llm_config.api_key, proxy=llm_config.proxy + ) assert result assert result.model assert len(result.data) > 0 diff --git a/tests/metagpt/tools/test_openai_text_to_image.py b/tests/metagpt/tools/test_openai_text_to_image.py index 5a6214d17..3f9169ddd 100644 --- a/tests/metagpt/tools/test_openai_text_to_image.py +++ b/tests/metagpt/tools/test_openai_text_to_image.py @@ -39,10 +39,10 @@ async def test_draw(mocker): mocker.patch.object(S3, "cache", return_value="http://mock.s3.com/0.png") # Prerequisites - assert config.get_openai_llm() - assert config.get_openai_llm().proxy + llm_config = config.get_openai_llm() + assert llm_config - binary_data = await oas3_openai_text_to_image("Panda emoji", llm=LLM()) + binary_data = await oas3_openai_text_to_image("Panda emoji", llm=LLM(llm_config=llm_config)) assert binary_data From 35d8f4d85627d9f11c237b0fa2944a9a1806cd8e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=8E=98=E6=9D=83=20=E9=A9=AC?= Date: Fri, 12 Jan 2024 16:00:20 +0800 Subject: [PATCH 53/61] fixbug: unit test --- tests/metagpt/utils/test_redis.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tests/metagpt/utils/test_redis.py b/tests/metagpt/utils/test_redis.py index 5d6eb1042..748c44f54 100644 --- a/tests/metagpt/utils/test_redis.py +++ b/tests/metagpt/utils/test_redis.py @@ -8,7 +8,6 @@ from unittest.mock import AsyncMock import pytest -from pytest_mock import mocker from metagpt.config2 import Config from metagpt.utils.redis import Redis @@ -22,7 +21,7 @@ async def async_mock_from_url(*args, **kwargs): @pytest.mark.asyncio -async def test_redis(i): +async def test_redis(mocker): redis = Config.default().redis mocker.patch("aioredis.from_url", return_value=async_mock_from_url()) From 1e523f68407e9a3c18597020dccc8884d6560ab6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=8E=98=E6=9D=83=20=E9=A9=AC?= Date: Fri, 12 Jan 2024 16:10:14 +0800 Subject: [PATCH 54/61] feat: +catch for window rm dirs --- metagpt/utils/git_repository.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/metagpt/utils/git_repository.py b/metagpt/utils/git_repository.py index 4feed89d5..61e5f3251 100644 --- a/metagpt/utils/git_repository.py +++ b/metagpt/utils/git_repository.py @@ -107,7 +107,10 @@ class GitRepository: def delete_repository(self): """Delete the entire repository directory.""" if self.is_valid: - shutil.rmtree(self._repository.working_dir) + try: + shutil.rmtree(self._repository.working_dir) + except Exception as e: + logger.exception(f"Failed delete git repo:{self.workdir}, error:{e}") @property def changed_files(self) -> Dict[str, str]: From b858cc7d83cf38d652dfda18f9e966b54605e1de Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=8E=98=E6=9D=83=20=E9=A9=AC?= Date: Fri, 12 Jan 2024 17:43:14 +0800 Subject: [PATCH 55/61] feat: remove Context.options --- metagpt/actions/write_teaching_plan.py | 8 ++++++-- metagpt/context.py | 8 -------- metagpt/roles/teacher.py | 10 +++++----- 3 files changed, 11 insertions(+), 15 deletions(-) diff --git a/metagpt/actions/write_teaching_plan.py b/metagpt/actions/write_teaching_plan.py index 834f07006..c5f70ae05 100644 --- a/metagpt/actions/write_teaching_plan.py +++ b/metagpt/actions/write_teaching_plan.py @@ -8,6 +8,7 @@ from typing import Optional from metagpt.actions import Action +from metagpt.context import Context from metagpt.logs import logger @@ -23,7 +24,7 @@ class WriteTeachingPlanPart(Action): statement_patterns = TeachingPlanBlock.TOPIC_STATEMENTS.get(self.topic, []) statements = [] for p in statement_patterns: - s = self.format_value(p, options=self.context.options) + s = self.format_value(p, context=self.context) statements.append(s) formatter = ( TeachingPlanBlock.PROMPT_TITLE_TEMPLATE @@ -67,13 +68,16 @@ class WriteTeachingPlanPart(Action): return self.topic @staticmethod - def format_value(value, options): + def format_value(value, context: Context): """Fill parameters inside `value` with `options`.""" if not isinstance(value, str): return value if "{" not in value: return value + options = context.config.model_dump() + for k, v in context.kwargs: + options[k] = v # None value is allowed to override and disable the value from config. opts = {k: v for k, v in options.items() if v is not None} try: return value.format(**opts) diff --git a/metagpt/context.py b/metagpt/context.py index 75dc31ef2..1e0d91237 100644 --- a/metagpt/context.py +++ b/metagpt/context.py @@ -64,14 +64,6 @@ class Context(BaseModel): _llm: Optional[BaseLLM] = None - @property - def options(self): - """Return all key-values""" - opts = self.config.model_dump() - for k, v in self.kwargs: - opts[k] = v # None value is allowed to override and disable the value from config. - return opts - def new_environ(self): """Return a new os.environ object""" env = os.environ.copy() diff --git a/metagpt/roles/teacher.py b/metagpt/roles/teacher.py index a40ba69fe..d6715dcd1 100644 --- a/metagpt/roles/teacher.py +++ b/metagpt/roles/teacher.py @@ -31,11 +31,11 @@ class Teacher(Role): def __init__(self, **kwargs): super().__init__(**kwargs) - self.name = WriteTeachingPlanPart.format_value(self.name, self.context.options) - self.profile = WriteTeachingPlanPart.format_value(self.profile, self.context.options) - self.goal = WriteTeachingPlanPart.format_value(self.goal, self.context.options) - self.constraints = WriteTeachingPlanPart.format_value(self.constraints, self.context.options) - self.desc = WriteTeachingPlanPart.format_value(self.desc, self.context.options) + self.name = WriteTeachingPlanPart.format_value(self.name, self.context) + self.profile = WriteTeachingPlanPart.format_value(self.profile, self.context) + self.goal = WriteTeachingPlanPart.format_value(self.goal, self.context) + self.constraints = WriteTeachingPlanPart.format_value(self.constraints, self.context) + self.desc = WriteTeachingPlanPart.format_value(self.desc, self.context) async def _think(self) -> bool: """Everything will be done part by part.""" From 31eb3fe0ee7e564c9473d3144bff91b393004cd7 Mon Sep 17 00:00:00 2001 From: geekan Date: Fri, 12 Jan 2024 15:56:07 +0800 Subject: [PATCH 56/61] refine code --- examples/example.pkl | Bin 624 -> 624 bytes metagpt/actions/write_code_an_draft.py | 24 +++++++++++------------- metagpt/config2.py | 2 +- metagpt/utils/yaml_model.py | 4 ++-- tests/data/rsp_cache.json | 7 ++++++- 5 files changed, 20 insertions(+), 17 deletions(-) diff --git a/examples/example.pkl b/examples/example.pkl index eac758f441110e558dea4e507ba67aa3c3b53eb0..0469a2e4670ab73437d853671ac4f5f4c22606b7 100644 GIT binary patch delta 103 zcmeys@_}VSv`T8CxoMh#af+^GqDi8zNs@`7Zc?gAny#f$Vrrs+fq7!8iP^;ZSImML z{F8GS9aIv{43kog&5d=9QY=$-O_CE$bS*5?%ydo7(tx7I=B7XelP@rqf;D(BX#fCA C^c`aW delta 103 zcmeys@_}VSv`Vsxv6+FPajI^baiXQJNlL1TuBEY|p{`|$abjAcsj-Ebq2a{(SIqnw zf|GL?9aPLsOie9KlPq-;lTwUyP0W)_b(2y}OmvMcEYg6&#ui3KMw2fvmVz~SFlhh) D`;i<^ diff --git a/metagpt/actions/write_code_an_draft.py b/metagpt/actions/write_code_an_draft.py index 968c8924b..ce030b0e9 100644 --- a/metagpt/actions/write_code_an_draft.py +++ b/metagpt/actions/write_code_an_draft.py @@ -5,7 +5,7 @@ @File : write_review.py """ import asyncio -from typing import List +from typing import List, Literal from metagpt.actions import Action from metagpt.actions.action_node import ActionNode @@ -21,16 +21,15 @@ REVIEW = ActionNode( ], ) -LGTM = ActionNode( - key="LGTM", - expected_type=str, - instruction="LGTM/LBTM. If the code is fully implemented, " - "give a LGTM (Looks Good To Me), otherwise provide a LBTM (Looks Bad To Me).", +REVIEW_RESULT = ActionNode( + key="ReviewResult", + expected_type=Literal["LGTM", "LBTM"], + instruction="LGTM/LBTM. If the code is fully implemented, " "give a LGTM, otherwise provide a LBTM.", example="LBTM", ) -ACTIONS = ActionNode( - key="Actions", +NEXT_STEPS = ActionNode( + key="NextSteps", expected_type=str, instruction="Based on the code review outcome, suggest actionable steps. This can include code changes, " "refactoring suggestions, or any follow-up tasks.", @@ -69,7 +68,7 @@ WRITE_DRAFT = ActionNode( ) -WRITE_MOVE_FUNCTION = ActionNode( +WRITE_FUNCTION = ActionNode( key="WriteFunction", expected_type=str, instruction="write code for the function not implemented.", @@ -555,8 +554,8 @@ LBTM """ -WRITE_CODE_NODE = ActionNode.from_children("WRITE_REVIEW_NODE", [REVIEW, LGTM, ACTIONS]) -WRITE_MOVE_NODE = ActionNode.from_children("WRITE_MOVE_NODE", [WRITE_DRAFT, WRITE_MOVE_FUNCTION]) +WRITE_CODE_NODE = ActionNode.from_children("WRITE_REVIEW_NODE", [REVIEW, REVIEW_RESULT, NEXT_STEPS]) +WRITE_MOVE_NODE = ActionNode.from_children("WRITE_MOVE_NODE", [WRITE_DRAFT, WRITE_FUNCTION]) CR_FOR_MOVE_FUNCTION_BY_3 = """ @@ -579,8 +578,7 @@ class WriteCodeAN(Action): async def run(self, context): self.llm.system_prompt = "You are an outstanding engineer and can implement any code" - return await WRITE_MOVE_FUNCTION.fill(context=context, llm=self.llm, schema="json") - # return await WRITE_CODE_NODE.fill(context=context, llm=self.llm, schema="markdown") + return await WRITE_MOVE_NODE.fill(context=context, llm=self.llm, schema="json") async def main(): diff --git a/metagpt/config2.py b/metagpt/config2.py index 2d4ac0930..1d58b9d63 100644 --- a/metagpt/config2.py +++ b/metagpt/config2.py @@ -84,7 +84,7 @@ class Config(CLIParams, YamlModel): @classmethod def from_home(cls, path): """Load config from ~/.metagpt/config.yaml""" - return Config.model_validate_yaml(CONFIG_ROOT / path) + return Config.from_yaml_file(CONFIG_ROOT / path) @classmethod def default(cls): diff --git a/metagpt/utils/yaml_model.py b/metagpt/utils/yaml_model.py index 60f866f7e..412a59825 100644 --- a/metagpt/utils/yaml_model.py +++ b/metagpt/utils/yaml_model.py @@ -23,10 +23,10 @@ class YamlModel(BaseModel): return yaml.safe_load(file) @classmethod - def model_validate_yaml(cls, file_path: Path) -> "YamlModel": + def from_yaml_file(cls, file_path: Path) -> "YamlModel": return cls(**cls.read_yaml(file_path)) - def model_dump_yaml(self, file_path: Path) -> None: + def to_yaml_file(self, file_path: Path) -> None: with open(file_path, "w") as file: yaml.dump(self.model_dump(), file) diff --git a/tests/data/rsp_cache.json b/tests/data/rsp_cache.json index 456a4146e..df5300feb 100644 --- a/tests/data/rsp_cache.json +++ b/tests/data/rsp_cache.json @@ -192,5 +192,10 @@ "\n## context\n\n### Project Name\n20240111181426\n\n### Original Requirements\n['']\n\n### Search Information\n-\n\n\n-----\n\n## format example\n[CONTENT]\n{\n \"Language\": \"en_us\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"Create a 2048 game\",\n \"Product Goals\": [\n \"Create an engaging user experience\",\n \"Improve accessibility, be responsive\",\n \"More beautiful UI\"\n ],\n \"User Stories\": [\n \"As a player, I want to be able to choose difficulty levels\",\n \"As a player, I want to see my score after each game\",\n \"As a player, I want to get restart button when I lose\",\n \"As a player, I want to see beautiful UI that make me feel good\",\n \"As a player, I want to play game via mobile phone\"\n ],\n \"Competitive Analysis\": [\n \"2048 Game A: Simple interface, lacks responsive features\",\n \"play2048.co: Beautiful and responsive UI with my best score shown\",\n \"2048game.com: Responsive UI with my best score shown, but many ads\"\n ],\n \"Competitive Quadrant Chart\": \"quadrantChart\\n title \\\"Reach and engagement of campaigns\\\"\\n x-axis \\\"Low Reach\\\" --> \\\"High Reach\\\"\\n y-axis \\\"Low Engagement\\\" --> \\\"High Engagement\\\"\\n quadrant-1 \\\"We should expand\\\"\\n quadrant-2 \\\"Need to promote\\\"\\n quadrant-3 \\\"Re-evaluate\\\"\\n quadrant-4 \\\"May be improved\\\"\\n \\\"Campaign A\\\": [0.3, 0.6]\\n \\\"Campaign B\\\": [0.45, 0.23]\\n \\\"Campaign C\\\": [0.57, 0.69]\\n \\\"Campaign D\\\": [0.78, 0.34]\\n \\\"Campaign E\\\": [0.40, 0.34]\\n \\\"Campaign F\\\": [0.35, 0.78]\\n \\\"Our Target Product\\\": [0.5, 0.6]\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [\n [\n \"P0\",\n \"The main code ...\"\n ],\n [\n \"P0\",\n \"The game algorithm ...\"\n ]\n ],\n \"UI Design draft\": \"Basic function description with a simple style and layout.\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]\n\n## nodes: \": # \"\n- Language: # Provide the language used in the project, typically matching the user's requirement language.\n- Programming Language: # Python/JavaScript or other mainstream programming language.\n- Original Requirements: # Place the original user's requirements here.\n- Product Goals: typing.List[str] # Provide up to three clear, orthogonal product goals.\n- User Stories: typing.List[str] # Provide up to 3 to 5 scenario-based user stories.\n- Competitive Analysis: typing.List[str] # Provide 5 to 7 competitive products.\n- Competitive Quadrant Chart: # Use mermaid quadrantChart syntax. Distribute scores evenly between 0 and 1\n- Requirement Analysis: # Provide a detailed analysis of the requirements.\n- Requirement Pool: typing.List[typing.List[str]] # List down the top-5 requirements with their priority (P0, P1, P2).\n- UI Design draft: # Provide a simple description of UI elements, functions, style, and layout.\n- Anything UNCLEAR: # Mention any aspects of the project that are unclear and try to clarify them.\n\n\n## constraint\nLanguage: Please use the same language as Human INPUT.\nFormat: output wrapped inside [CONTENT][/CONTENT] like format example, nothing else.\n\n## action\nFollow instructions of nodes, generate output and make sure it follows the format example.\n": "[CONTENT]\n{\n \"Language\": \"en_us\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"\",\n \"Product Goals\": [],\n \"User Stories\": [],\n \"Competitive Analysis\": [],\n \"Competitive Quadrant Chart\": \"quadrantChart\\n title \\\"Reach and engagement of campaigns\\\"\\n x-axis \\\"Low Reach\\\" --> \\\"High Reach\\\"\\n y-axis \\\"Low Engagement\\\" --> \\\"High Engagement\\\"\\n quadrant-1 \\\"We should expand\\\"\\n quadrant-2 \\\"Need to promote\\\"\\n quadrant-3 \\\"Re-evaluate\\\"\\n quadrant-4 \\\"May be improved\\\"\\n \\\"Campaign A\\\": [0.3, 0.6]\\n \\\"Campaign B\\\": [0.45, 0.23]\\n \\\"Campaign C\\\": [0.57, 0.69]\\n \\\"Campaign D\\\": [0.78, 0.34]\\n \\\"Campaign E\\\": [0.40, 0.34]\\n \\\"Campaign F\\\": [0.35, 0.78]\\n \\\"Our Target Product\\\": [0.5, 0.6]\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [],\n \"UI Design draft\": \"Basic function description with a simple style and layout.\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]", "## History Messages\n0: Human: Topic: climate change. Under 80 words per message.\n\n## Actions\nLanguage: Please use the same language as Human INPUT.\nSay your opinion with emotion and don't repeat it": "I believe that climate change is a critical issue that requires urgent action. It's alarming to see the impact of human activities on the environment and the devastating consequences it has on ecosystems and communities. We need to prioritize sustainable practices and reduce our carbon footprint to mitigate the effects of climate change. It's essential for the well-being of future generations and the health of our planet.", "## History Messages\n0: Alex(Democratic candidate): I believe that climate change is a critical issue that requires urgent action. It's alarming to see the impact of human activities on the environment and the devastating consequences it has on ecosystems and communities. We need to prioritize sustainable practices and reduce our carbon footprint to mitigate the effects of climate change. It's essential for the well-being of future generations and the health of our planet.\n\n## Actions\nLanguage: Please use the same language as Human INPUT.\nSay your opinion with emotion and don't repeat it": "I completely agree with Alex. Climate change is a critical issue that demands immediate attention. The impact of human activities on the environment is devastating, and urgent action is necessary to prioritize sustainable practices and reduce our carbon footprint. It's essential for the well-being of future generations and the health of our planet.", - "## History Messages\n0: Bob(Republican candidate): I completely agree with Alex. Climate change is a critical issue that demands immediate attention. The impact of human activities on the environment is devastating, and urgent action is necessary to prioritize sustainable practices and reduce our carbon footprint. It's essential for the well-being of future generations and the health of our planet.\n1: Alex(Democratic candidate): I believe that climate change is a critical issue that requires urgent action. It's alarming to see the impact of human activities on the environment and the devastating consequences it has on ecosystems and communities. We need to prioritize sustainable practices and reduce our carbon footprint to mitigate the effects of climate change. It's essential for the well-being of future generations and the health of our planet.\n2: Human: Topic: climate change. Under 80 words per message.\n\n## Actions\nLanguage: Please use the same language as Human INPUT.\nSay your opinion with emotion and don't repeat it": "I completely agree with both Bob and Alex. Climate change is a critical issue that demands immediate attention. The impact of human activities on the environment is devastating, and urgent action is necessary to prioritize sustainable practices and reduce our carbon footprint. It's essential for the well-being of future generations and the health of our planet." + "## History Messages\n0: Bob(Republican candidate): I completely agree with Alex. Climate change is a critical issue that demands immediate attention. The impact of human activities on the environment is devastating, and urgent action is necessary to prioritize sustainable practices and reduce our carbon footprint. It's essential for the well-being of future generations and the health of our planet.\n1: Alex(Democratic candidate): I believe that climate change is a critical issue that requires urgent action. It's alarming to see the impact of human activities on the environment and the devastating consequences it has on ecosystems and communities. We need to prioritize sustainable practices and reduce our carbon footprint to mitigate the effects of climate change. It's essential for the well-being of future generations and the health of our planet.\n2: Human: Topic: climate change. Under 80 words per message.\n\n## Actions\nLanguage: Please use the same language as Human INPUT.\nSay your opinion with emotion and don't repeat it": "I completely agree with both Bob and Alex. Climate change is a critical issue that demands immediate attention. The impact of human activities on the environment is devastating, and urgent action is necessary to prioritize sustainable practices and reduce our carbon footprint. It's essential for the well-being of future generations and the health of our planet.", + "\n## context\n\n### Project Name\n20240112110621\n\n### Original Requirements\n['需要一个基于LLM做总结的搜索引擎']\n\n### Search Information\n-\n\n\n-----\n\n## format example\n[CONTENT]\n{\n \"Language\": \"en_us\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"Create a 2048 game\",\n \"Product Goals\": [\n \"Create an engaging user experience\",\n \"Improve accessibility, be responsive\",\n \"More beautiful UI\"\n ],\n \"User Stories\": [\n \"As a player, I want to be able to choose difficulty levels\",\n \"As a player, I want to see my score after each game\",\n \"As a player, I want to get restart button when I lose\",\n \"As a player, I want to see beautiful UI that make me feel good\",\n \"As a player, I want to play game via mobile phone\"\n ],\n \"Competitive Analysis\": [\n \"2048 Game A: Simple interface, lacks responsive features\",\n \"play2048.co: Beautiful and responsive UI with my best score shown\",\n \"2048game.com: Responsive UI with my best score shown, but many ads\"\n ],\n \"Competitive Quadrant Chart\": \"quadrantChart\\n title \\\"Reach and engagement of campaigns\\\"\\n x-axis \\\"Low Reach\\\" --> \\\"High Reach\\\"\\n y-axis \\\"Low Engagement\\\" --> \\\"High Engagement\\\"\\n quadrant-1 \\\"We should expand\\\"\\n quadrant-2 \\\"Need to promote\\\"\\n quadrant-3 \\\"Re-evaluate\\\"\\n quadrant-4 \\\"May be improved\\\"\\n \\\"Campaign A\\\": [0.3, 0.6]\\n \\\"Campaign B\\\": [0.45, 0.23]\\n \\\"Campaign C\\\": [0.57, 0.69]\\n \\\"Campaign D\\\": [0.78, 0.34]\\n \\\"Campaign E\\\": [0.40, 0.34]\\n \\\"Campaign F\\\": [0.35, 0.78]\\n \\\"Our Target Product\\\": [0.5, 0.6]\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [\n [\n \"P0\",\n \"The main code ...\"\n ],\n [\n \"P0\",\n \"The game algorithm ...\"\n ]\n ],\n \"UI Design draft\": \"Basic function description with a simple style and layout.\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]\n\n## nodes: \": # \"\n- Language: # Provide the language used in the project, typically matching the user's requirement language.\n- Programming Language: # Python/JavaScript or other mainstream programming language.\n- Original Requirements: # Place the original user's requirements here.\n- Product Goals: typing.List[str] # Provide up to three clear, orthogonal product goals.\n- User Stories: typing.List[str] # Provide up to 3 to 5 scenario-based user stories.\n- Competitive Analysis: typing.List[str] # Provide 5 to 7 competitive products.\n- Competitive Quadrant Chart: # Use mermaid quadrantChart syntax. Distribute scores evenly between 0 and 1\n- Requirement Analysis: # Provide a detailed analysis of the requirements.\n- Requirement Pool: typing.List[typing.List[str]] # List down the top-5 requirements with their priority (P0, P1, P2).\n- UI Design draft: # Provide a simple description of UI elements, functions, style, and layout.\n- Anything UNCLEAR: # Mention any aspects of the project that are unclear and try to clarify them.\n\n\n## constraint\nLanguage: Please use the same language as Human INPUT.\nFormat: output wrapped inside [CONTENT][/CONTENT] like format example, nothing else.\n\n## action\nFollow instructions of nodes, generate output and make sure it follows the format example.\n": "[CONTENT]\n{\n \"Language\": \"zh_cn\",\n \"Programming Language\": \"LLM\",\n \"Original Requirements\": \"需要一个基于LLM做总结的搜索引擎\",\n \"Product Goals\": [],\n \"User Stories\": [],\n \"Competitive Analysis\": [],\n \"Competitive Quadrant Chart\": \"\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [],\n \"UI Design draft\": \"\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]", + "You are a python code to Mermaid Sequence Diagram translator in function detail#SYSTEM_MSG_END#```python\n#!/usr/bin/env python\n# -*- coding: utf-8 -*-\nimport asyncio\nimport shutil\nfrom pathlib import Path\n\nimport typer\n\nfrom metagpt.config2 import config\nfrom metagpt.const import CONFIG_ROOT, METAGPT_ROOT\n\napp = typer.Typer(add_completion=False, pretty_exceptions_show_locals=False)\n\n\ndef generate_repo(\n idea,\n investment,\n n_round,\n code_review,\n run_tests,\n implement,\n project_name,\n inc,\n project_path,\n reqa_file,\n max_auto_summarize_code,\n recover_path,\n):\n \"\"\"Run the startup logic. Can be called from CLI or other Python scripts.\"\"\"\n from metagpt.roles import (\n Architect,\n Engineer,\n ProductManager,\n ProjectManager,\n QaEngineer,\n )\n from metagpt.team import Team\n\n config.update_via_cli(project_path, project_name, inc, reqa_file, max_auto_summarize_code)\n\n if not recover_path:\n company = Team()\n company.hire(\n [\n ProductManager(),\n Architect(),\n ProjectManager(),\n ]\n )\n\n if implement or code_review:\n company.hire([Engineer(n_borg=5, use_code_review=code_review)])\n\n if run_tests:\n company.hire([QaEngineer()])\n else:\n stg_path = Path(recover_path)\n if not stg_path.exists() or not str(stg_path).endswith(\"team\"):\n raise FileNotFoundError(f\"{recover_path} not exists or not endswith `team`\")\n\n company = Team.deserialize(stg_path=stg_path)\n idea = company.idea\n\n company.invest(investment)\n company.run_project(idea)\n asyncio.run(company.run(n_round=n_round))\n\n\n@app.command(\"\", help=\"Start a new project.\")\ndef startup(\n idea: str = typer.Argument(None, help=\"Your innovative idea, such as 'Create a 2048 game.'\"),\n investment: float = typer.Option(default=3.0, help=\"Dollar amount to invest in the AI company.\"),\n n_round: int = typer.Option(default=5, help=\"Number of rounds for the simulation.\"),\n code_review: bool = typer.Option(default=True, help=\"Whether to use code review.\"),\n run_tests: bool = typer.Option(default=False, help=\"Whether to enable QA for adding & running tests.\"),\n implement: bool = typer.Option(default=True, help=\"Enable or disable code implementation.\"),\n project_name: str = typer.Option(default=\"\", help=\"Unique project name, such as 'game_2048'.\"),\n inc: bool = typer.Option(default=False, help=\"Incremental mode. Use it to coop with existing repo.\"),\n project_path: str = typer.Option(\n default=\"\",\n help=\"Specify the directory path of the old version project to fulfill the incremental requirements.\",\n ),\n reqa_file: str = typer.Option(\n default=\"\", help=\"Specify the source file name for rewriting the quality assurance code.\"\n ),\n max_auto_summarize_code: int = typer.Option(\n default=0,\n help=\"The maximum number of times the 'SummarizeCode' action is automatically invoked, with -1 indicating \"\n \"unlimited. This parameter is used for debugging the workflow.\",\n ),\n recover_path: str = typer.Option(default=None, help=\"recover the project from existing serialized storage\"),\n init_config: bool = typer.Option(default=False, help=\"Initialize the configuration file for MetaGPT.\"),\n):\n \"\"\"Run a startup. Be a boss.\"\"\"\n if init_config:\n copy_config_to()\n return\n\n if idea is None:\n typer.echo(\"Missing argument 'IDEA'. Run 'metagpt --help' for more information.\")\n raise typer.Exit()\n\n return generate_repo(\n idea,\n investment,\n n_round,\n code_review,\n run_tests,\n implement,\n project_name,\n inc,\n project_path,\n reqa_file,\n max_auto_summarize_code,\n recover_path,\n )\n\n\ndef copy_config_to(config_path=METAGPT_ROOT / \"config\" / \"config2.yaml\"):\n \"\"\"Initialize the configuration file for MetaGPT.\"\"\"\n target_path = CONFIG_ROOT / \"config2.yaml\"\n\n # 创建目标目录（如果不存在）\n target_path.parent.mkdir(parents=True, exist_ok=True)\n\n # 如果目标文件已经存在，则重命名为 .bak\n if target_path.exists():\n backup_path = target_path.with_suffix(\".bak\")\n target_path.rename(backup_path)\n print(f\"Existing configuration file backed up at {backup_path}\")\n\n # 复制文件\n shutil.copy(str(config_path), target_path)\n print(f\"Configuration file initialized at {target_path}\")\n\n\nif __name__ == \"__main__\":\n app()\n\n```\n\n---\nTranslate the code above into Mermaid Sequence Diagram.": "```mermaid\nsequenceDiagram\n participant app\n participant generate_repo\n participant copy_config_to\n participant Team\n participant ProductManager\n participant Architect\n participant ProjectManager\n participant Engineer\n participant QaEngineer\n\n app -> generate_repo: startup()\n generate_repo -> config: update_via_cli()\n generate_repo -> Team: hire()\n Team -> ProductManager: hire()\n Team -> Architect: hire()\n Team -> ProjectManager: hire()\n generate_repo -> Engineer: hire()\n generate_repo -> QaEngineer: hire()\n generate_repo -> Team: invest()\n generate_repo -> Team: run_project()\n generate_repo -> Team: run()\n\n app -> copy_config_to: copy_config_to()\n copy_config_to -> config: update_via_cli()\n```", + "You are a python code to Mermaid Sequence Diagram translator in function detail#SYSTEM_MSG_END#```python\n#!/usr/bin/env python\n# -*- coding: utf-8 -*-\n\"\"\"\n@Time : 2023/12/14 11:40\n@Author : alexanderwu\n@File : write_prd_an.py\n\"\"\"\nfrom typing import List\n\nfrom metagpt.actions.action_node import ActionNode\n\nLANGUAGE = ActionNode(\n key=\"Language\",\n expected_type=str,\n instruction=\"Provide the language used in the project, typically matching the user's requirement language.\",\n example=\"en_us\",\n)\n\nPROGRAMMING_LANGUAGE = ActionNode(\n key=\"Programming Language\",\n expected_type=str,\n instruction=\"Python/JavaScript or other mainstream programming language.\",\n example=\"Python\",\n)\n\nORIGINAL_REQUIREMENTS = ActionNode(\n key=\"Original Requirements\",\n expected_type=str,\n instruction=\"Place the original user's requirements here.\",\n example=\"Create a 2048 game\",\n)\n\nPROJECT_NAME = ActionNode(\n key=\"Project Name\",\n expected_type=str,\n instruction='According to the content of \"Original Requirements,\" name the project using snake case style , '\n \"like 'game_2048' or 'simple_crm.\",\n example=\"game_2048\",\n)\n\nPRODUCT_GOALS = ActionNode(\n key=\"Product Goals\",\n expected_type=List[str],\n instruction=\"Provide up to three clear, orthogonal product goals.\",\n example=[\"Create an engaging user experience\", \"Improve accessibility, be responsive\", \"More beautiful UI\"],\n)\n\nUSER_STORIES = ActionNode(\n key=\"User Stories\",\n expected_type=List[str],\n instruction=\"Provide up to 3 to 5 scenario-based user stories.\",\n example=[\n \"As a player, I want to be able to choose difficulty levels\",\n \"As a player, I want to see my score after each game\",\n \"As a player, I want to get restart button when I lose\",\n \"As a player, I want to see beautiful UI that make me feel good\",\n \"As a player, I want to play game via mobile phone\",\n ],\n)\n\nCOMPETITIVE_ANALYSIS = ActionNode(\n key=\"Competitive Analysis\",\n expected_type=List[str],\n instruction=\"Provide 5 to 7 competitive products.\",\n example=[\n \"2048 Game A: Simple interface, lacks responsive features\",\n \"play2048.co: Beautiful and responsive UI with my best score shown\",\n \"2048game.com: Responsive UI with my best score shown, but many ads\",\n ],\n)\n\nCOMPETITIVE_QUADRANT_CHART = ActionNode(\n key=\"Competitive Quadrant Chart\",\n expected_type=str,\n instruction=\"Use mermaid quadrantChart syntax. Distribute scores evenly between 0 and 1\",\n example=\"\"\"quadrantChart\n title \"Reach and engagement of campaigns\"\n x-axis \"Low Reach\" --> \"High Reach\"\n y-axis \"Low Engagement\" --> \"High Engagement\"\n quadrant-1 \"We should expand\"\n quadrant-2 \"Need to promote\"\n quadrant-3 \"Re-evaluate\"\n quadrant-4 \"May be improved\"\n \"Campaign A\": [0.3, 0.6]\n \"Campaign B\": [0.45, 0.23]\n \"Campaign C\": [0.57, 0.69]\n \"Campaign D\": [0.78, 0.34]\n \"Campaign E\": [0.40, 0.34]\n \"Campaign F\": [0.35, 0.78]\n \"Our Target Product\": [0.5, 0.6]\"\"\",\n)\n\nREQUIREMENT_ANALYSIS = ActionNode(\n key=\"Requirement Analysis\",\n expected_type=str,\n instruction=\"Provide a detailed analysis of the requirements.\",\n example=\"\",\n)\n\nREQUIREMENT_POOL = ActionNode(\n key=\"Requirement Pool\",\n expected_type=List[List[str]],\n instruction=\"List down the top-5 requirements with their priority (P0, P1, P2).\",\n example=[[\"P0\", \"The main code ...\"], [\"P0\", \"The game algorithm ...\"]],\n)\n\nUI_DESIGN_DRAFT = ActionNode(\n key=\"UI Design draft\",\n expected_type=str,\n instruction=\"Provide a simple description of UI elements, functions, style, and layout.\",\n example=\"Basic function description with a simple style and layout.\",\n)\n\nANYTHING_UNCLEAR = ActionNode(\n key=\"Anything UNCLEAR\",\n expected_type=str,\n instruction=\"Mention any aspects of the project that are unclear and try to clarify them.\",\n example=\"\",\n)\n\nISSUE_TYPE = ActionNode(\n key=\"issue_type\",\n expected_type=str,\n instruction=\"Answer BUG/REQUIREMENT. If it is a bugfix, answer BUG, otherwise answer Requirement\",\n example=\"BUG\",\n)\n\nIS_RELATIVE = ActionNode(\n key=\"is_relative\",\n expected_type=str,\n instruction=\"Answer YES/NO. If the requirement is related to the old PRD, answer YES, otherwise NO\",\n example=\"YES\",\n)\n\nREASON = ActionNode(\n key=\"reason\", expected_type=str, instruction=\"Explain the reasoning process from question to answer\", example=\"...\"\n)\n\n\nNODES = [\n LANGUAGE,\n PROGRAMMING_LANGUAGE,\n ORIGINAL_REQUIREMENTS,\n PROJECT_NAME,\n PRODUCT_GOALS,\n USER_STORIES,\n COMPETITIVE_ANALYSIS,\n COMPETITIVE_QUADRANT_CHART,\n REQUIREMENT_ANALYSIS,\n REQUIREMENT_POOL,\n UI_DESIGN_DRAFT,\n ANYTHING_UNCLEAR,\n]\n\nWRITE_PRD_NODE = ActionNode.from_children(\"WritePRD\", NODES)\nWP_ISSUE_TYPE_NODE = ActionNode.from_children(\"WP_ISSUE_TYPE\", [ISSUE_TYPE, REASON])\nWP_IS_RELATIVE_NODE = ActionNode.from_children(\"WP_IS_RELATIVE\", [IS_RELATIVE, REASON])\n\n```\n\n---\nTranslate the code above into Mermaid Sequence Diagram.": "```mermaid\nclassDef actionNode fill:#f9f,stroke:#333,stroke-width:2px;\nclassDef actionNodeTitle fill:#f9f,stroke:#333,stroke-width:2px,font-weight:bold;\nclassDef actionNodeExample fill:#f9f,stroke:#333,stroke-width:2px,font-style:italic;\n\nclass ActionNodeTitle actionNodeTitle\nclass ActionNodeExample actionNodeExample\n\nActionNodeTitle:::Language --> \"Language\"\nActionNodeExample:::Language --> \"Provide the language used in the project, typically matching the user's requirement language.\\nExample: en_us\"\n\nActionNodeTitle:::ProgrammingLanguage --> \"Programming Language\"\nActionNodeExample:::ProgrammingLanguage --> \"Python/JavaScript or other mainstream programming language.\\nExample: Python\"\n\nActionNodeTitle:::OriginalRequirements --> \"Original Requirements\"\nActionNodeExample:::OriginalRequirements --> \"Place the original user's requirements here.\\nExample: Create a 2048 game\"\n\nActionNodeTitle:::ProjectName --> \"Project Name\"\nActionNodeExample:::ProjectName --> 'According to the content of \"Original Requirements,\" name the project using snake case style , like \\'game_2048\\' or \\'simple_crm.\\nExample: game_2048'\n\nActionNodeTitle:::ProductGoals --> \"Product Goals\"\nActionNodeExample:::ProductGoals --> \"Provide up to three clear, orthogonal product goals.\\nExample:\\n- Create an engaging user experience\\n- Improve accessibility, be responsive\\n- More beautiful UI\"\n\nActionNodeTitle:::UserStories --> \"User Stories\"\nActionNodeExample:::UserStories --> \"Provide up to 3 to 5 scenario-based user stories.\\nExample:\\n- As a player, I want to be able to choose difficulty levels\\n- As a player, I want to see my score after each game\\n- As a player, I want to get restart button when I lose\\n- As a player, I want to see beautiful UI that make me feel good\\n- As a player, I want to play game via mobile phone\"\n\nActionNodeTitle:::CompetitiveAnalysis --> \"Competitive Analysis\"\nActionNodeExample:::CompetitiveAnalysis --> \"Provide 5 to 7 competitive products.\\nExample:\\n- 2048 Game A: Simple interface, lacks responsive features\\n- play2048.co: Beautiful and responsive UI with my best score shown\\n- 2048game.com: Responsive UI with my best score shown, but many ads\"\n\nActionNodeTitle:::CompetitiveQuadrantChart --> \"Competitive Quadrant Chart\"\nActionNodeExample:::CompetitiveQuadrantChart --> \"Use mermaid quadrantChart syntax. Distribute scores evenly between 0 and 1\\nExample:\\nquadrantChart\\n title \\\"Reach and engagement of campaigns\\\"\\n x-axis \\\"Low Reach\\\" --> \\\"High Reach\\\"\\n y-axis \\\"Low Engagement\\\" --> \\\"High Engagement\\\"\\n quadrant-1 \\\"We should expand\\\"\\n quadrant-2 \\\"Need to promote\\\"\\n quadrant-3 \\\"Re-evaluate\\\"\\n quadrant-4 \\\"May be improved\\\"\\n \\\"Campaign A\\\": [0.3, 0.6]\\n \\\"Campaign B\\\": [0.45, 0.23]\\n \\\"Campaign C\\\": [0.57, 0.69]\\n \\\"Campaign D\\\": [0.78, 0.34]\\n \\\"Campaign E\\\": [0.40, 0.34]\\n \\\"Campaign F\\\": [0.35, 0.78]\\n \\\"Our Target Product\\\": [0.5, 0.6]\"\n\nActionNodeTitle:::RequirementAnalysis --> \"Requirement Analysis\"\nActionNodeExample:::RequirementAnalysis --> \"Provide a detailed analysis of the requirements.\\nExample: \"\n\nActionNodeTitle:::RequirementPool --> \"Requirement Pool\"\nActionNodeExample:::RequirementPool --> \"List down the top-5 requirements with their priority (P0, P1, P2).\\nExample:\\n- P0: The main code ...\\n- P0: The game algorithm ...\"\n\nActionNodeTitle:::UIDesignDraft --> \"UI Design draft\"\nActionNodeExample:::UIDesignDraft --> \"Provide a simple description of UI elements, functions, style, and layout.\\nExample: Basic function description with a simple style and layout.\"\n\nActionNodeTitle:::AnythingUNCLEAR --> \"Anything UNCLEAR\"\nActionNodeExample:::AnythingUNCLEAR --> \"Mention any aspects of the project that are unclear and try to clarify them.\\nExample: \"\n\nActionNodeTitle:::issue_type --> \"issue_type\"\nActionNodeExample:::issue_type --> \"Answer BUG/REQUIREMENT. If it is a bugfix, answer BUG, otherwise answer Requirement\\nExample: BUG\"\n\nActionNodeTitle:::is_relative --> \"is_relative\"\nActionNodeExample:::is_relative --> \"Answer YES/NO. If the requirement is related to the old PRD, answer YES, otherwise NO\\nExample: YES\"\n\nActionNodeTitle:::reason --> \"reason\"\nActionNodeExample:::reason --> \"Explain the reasoning process from question to answer\\nExample: ...\"\n\nActionNodeTitle:::WritePRD --> \"WritePRD\"\nActionNodeExample:::WritePRD --> \"Language\\nProgramming Language\\nOriginal Requirements\\nProject Name\\nProduct Goals\\nUser Stories\\nCompetitive Analysis\\nCompetitive Quadrant Chart\\nRequirement Analysis\\nRequirement Pool\\nUI Design draft\\nAnything UNCLEAR\"\n\nActionNodeTitle:::WP_ISSUE_TYPE --> \"WP_ISSUE_TYPE\"\nActionNodeExample:::WP_ISSUE_TYPE --> \"issue_type\\nreason\"\n\nActionNodeTitle:::WP_IS_RELATIVE --> \"WP_IS_RELATIVE\"\nActionNodeExample:::WP_IS_RELATIVE --> \"is_relative\\nreason\"\n```", + "\n## context\n\n### Project Name\n20240112110833\n\n### Original Requirements\n['开发一个基于大语言模型与私有知识库的搜索引擎，希望可以基于大语言模型进行搜索总结']\n\n### Search Information\n-\n\n\n-----\n\n## format example\n[CONTENT]\n{\n \"Language\": \"en_us\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"Create a 2048 game\",\n \"Product Goals\": [\n \"Create an engaging user experience\",\n \"Improve accessibility, be responsive\",\n \"More beautiful UI\"\n ],\n \"User Stories\": [\n \"As a player, I want to be able to choose difficulty levels\",\n \"As a player, I want to see my score after each game\",\n \"As a player, I want to get restart button when I lose\",\n \"As a player, I want to see beautiful UI that make me feel good\",\n \"As a player, I want to play game via mobile phone\"\n ],\n \"Competitive Analysis\": [\n \"2048 Game A: Simple interface, lacks responsive features\",\n \"play2048.co: Beautiful and responsive UI with my best score shown\",\n \"2048game.com: Responsive UI with my best score shown, but many ads\"\n ],\n \"Competitive Quadrant Chart\": \"quadrantChart\\n title \\\"Reach and engagement of campaigns\\\"\\n x-axis \\\"Low Reach\\\" --> \\\"High Reach\\\"\\n y-axis \\\"Low Engagement\\\" --> \\\"High Engagement\\\"\\n quadrant-1 \\\"We should expand\\\"\\n quadrant-2 \\\"Need to promote\\\"\\n quadrant-3 \\\"Re-evaluate\\\"\\n quadrant-4 \\\"May be improved\\\"\\n \\\"Campaign A\\\": [0.3, 0.6]\\n \\\"Campaign B\\\": [0.45, 0.23]\\n \\\"Campaign C\\\": [0.57, 0.69]\\n \\\"Campaign D\\\": [0.78, 0.34]\\n \\\"Campaign E\\\": [0.40, 0.34]\\n \\\"Campaign F\\\": [0.35, 0.78]\\n \\\"Our Target Product\\\": [0.5, 0.6]\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [\n [\n \"P0\",\n \"The main code ...\"\n ],\n [\n \"P0\",\n \"The game algorithm ...\"\n ]\n ],\n \"UI Design draft\": \"Basic function description with a simple style and layout.\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]\n\n## nodes: \": # \"\n- Language: # Provide the language used in the project, typically matching the user's requirement language.\n- Programming Language: # Python/JavaScript or other mainstream programming language.\n- Original Requirements: # Place the original user's requirements here.\n- Product Goals: typing.List[str] # Provide up to three clear, orthogonal product goals.\n- User Stories: typing.List[str] # Provide up to 3 to 5 scenario-based user stories.\n- Competitive Analysis: typing.List[str] # Provide 5 to 7 competitive products.\n- Competitive Quadrant Chart: # Use mermaid quadrantChart syntax. Distribute scores evenly between 0 and 1\n- Requirement Analysis: # Provide a detailed analysis of the requirements.\n- Requirement Pool: typing.List[typing.List[str]] # List down the top-5 requirements with their priority (P0, P1, P2).\n- UI Design draft: # Provide a simple description of UI elements, functions, style, and layout.\n- Anything UNCLEAR: # Mention any aspects of the project that are unclear and try to clarify them.\n\n\n## constraint\nLanguage: Please use the same language as Human INPUT.\nFormat: output wrapped inside [CONTENT][/CONTENT] like format example, nothing else.\n\n## action\nFollow instructions of nodes, generate output and make sure it follows the format example.\n": "[CONTENT]\n{\n \"Language\": \"zh_cn\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"开发一个基于大语言模型与私有知识库的搜索引擎，希望可以基于大语言模型进行搜索总结\",\n \"Product Goals\": [],\n \"User Stories\": [],\n \"Competitive Analysis\": [],\n \"Competitive Quadrant Chart\": \"\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [],\n \"UI Design draft\": \"\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]", + "\n## context\n\n### Project Name\n20240112110833\n\n### Original Requirements\n['']\n\n### Search Information\n-\n\n\n-----\n\n## format example\n[CONTENT]\n{\n \"Language\": \"en_us\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"Create a 2048 game\",\n \"Product Goals\": [\n \"Create an engaging user experience\",\n \"Improve accessibility, be responsive\",\n \"More beautiful UI\"\n ],\n \"User Stories\": [\n \"As a player, I want to be able to choose difficulty levels\",\n \"As a player, I want to see my score after each game\",\n \"As a player, I want to get restart button when I lose\",\n \"As a player, I want to see beautiful UI that make me feel good\",\n \"As a player, I want to play game via mobile phone\"\n ],\n \"Competitive Analysis\": [\n \"2048 Game A: Simple interface, lacks responsive features\",\n \"play2048.co: Beautiful and responsive UI with my best score shown\",\n \"2048game.com: Responsive UI with my best score shown, but many ads\"\n ],\n \"Competitive Quadrant Chart\": \"quadrantChart\\n title \\\"Reach and engagement of campaigns\\\"\\n x-axis \\\"Low Reach\\\" --> \\\"High Reach\\\"\\n y-axis \\\"Low Engagement\\\" --> \\\"High Engagement\\\"\\n quadrant-1 \\\"We should expand\\\"\\n quadrant-2 \\\"Need to promote\\\"\\n quadrant-3 \\\"Re-evaluate\\\"\\n quadrant-4 \\\"May be improved\\\"\\n \\\"Campaign A\\\": [0.3, 0.6]\\n \\\"Campaign B\\\": [0.45, 0.23]\\n \\\"Campaign C\\\": [0.57, 0.69]\\n \\\"Campaign D\\\": [0.78, 0.34]\\n \\\"Campaign E\\\": [0.40, 0.34]\\n \\\"Campaign F\\\": [0.35, 0.78]\\n \\\"Our Target Product\\\": [0.5, 0.6]\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [\n [\n \"P0\",\n \"The main code ...\"\n ],\n [\n \"P0\",\n \"The game algorithm ...\"\n ]\n ],\n \"UI Design draft\": \"Basic function description with a simple style and layout.\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]\n\n## nodes: \": # \"\n- Language: # Provide the language used in the project, typically matching the user's requirement language.\n- Programming Language: # Python/JavaScript or other mainstream programming language.\n- Original Requirements: # Place the original user's requirements here.\n- Product Goals: typing.List[str] # Provide up to three clear, orthogonal product goals.\n- User Stories: typing.List[str] # Provide up to 3 to 5 scenario-based user stories.\n- Competitive Analysis: typing.List[str] # Provide 5 to 7 competitive products.\n- Competitive Quadrant Chart: # Use mermaid quadrantChart syntax. Distribute scores evenly between 0 and 1\n- Requirement Analysis: # Provide a detailed analysis of the requirements.\n- Requirement Pool: typing.List[typing.List[str]] # List down the top-5 requirements with their priority (P0, P1, P2).\n- UI Design draft: # Provide a simple description of UI elements, functions, style, and layout.\n- Anything UNCLEAR: # Mention any aspects of the project that are unclear and try to clarify them.\n\n\n## constraint\nLanguage: Please use the same language as Human INPUT.\nFormat: output wrapped inside [CONTENT][/CONTENT] like format example, nothing else.\n\n## action\nFollow instructions of nodes, generate output and make sure it follows the format example.\n": "[CONTENT]\n{\n \"Language\": \"en_us\",\n \"Programming Language\": \"Python\",\n \"Original Requirements\": \"\",\n \"Product Goals\": [],\n \"User Stories\": [],\n \"Competitive Analysis\": [],\n \"Competitive Quadrant Chart\": \"quadrantChart\\n title \\\"Reach and engagement of campaigns\\\"\\n x-axis \\\"Low Reach\\\" --> \\\"High Reach\\\"\\n y-axis \\\"Low Engagement\\\" --> \\\"High Engagement\\\"\\n quadrant-1 \\\"We should expand\\\"\\n quadrant-2 \\\"Need to promote\\\"\\n quadrant-3 \\\"Re-evaluate\\\"\\n quadrant-4 \\\"May be improved\\\"\\n \\\"Campaign A\\\": [0.3, 0.6]\\n \\\"Campaign B\\\": [0.45, 0.23]\\n \\\"Campaign C\\\": [0.57, 0.69]\\n \\\"Campaign D\\\": [0.78, 0.34]\\n \\\"Campaign E\\\": [0.40, 0.34]\\n \\\"Campaign F\\\": [0.35, 0.78]\\n \\\"Our Target Product\\\": [0.5, 0.6]\",\n \"Requirement Analysis\": \"\",\n \"Requirement Pool\": [],\n \"UI Design draft\": \"Basic function description with a simple style and layout.\",\n \"Anything UNCLEAR\": \"\"\n}\n[/CONTENT]" } \ No newline at end of file From ef4323c6b4739d5c7b409072dfeb171ec859f7e0 Mon Sep 17 00:00:00 2001 From: geekan Date: Fri, 12 Jan 2024 17:02:07 +0800 Subject: [PATCH 57/61] refine code --- metagpt/utils/yaml_model.py | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/metagpt/utils/yaml_model.py b/metagpt/utils/yaml_model.py index 412a59825..8f2d22c3d 100644 --- a/metagpt/utils/yaml_model.py +++ b/metagpt/utils/yaml_model.py @@ -13,28 +13,36 @@ from pydantic import BaseModel, model_validator class YamlModel(BaseModel): + """Base class for yaml model""" + extra_fields: Optional[Dict[str, str]] = None @classmethod - def read_yaml(cls, file_path: Path) -> Dict: + def read_yaml(cls, file_path: Path, encoding: str = "utf-8") -> Dict: + """Read yaml file and return a dict""" if not file_path.exists(): return {} - with open(file_path, "r") as file: + with open(file_path, "r", encoding=encoding) as file: return yaml.safe_load(file) @classmethod def from_yaml_file(cls, file_path: Path) -> "YamlModel": + """Read yaml file and return a YamlModel instance""" return cls(**cls.read_yaml(file_path)) - def to_yaml_file(self, file_path: Path) -> None: - with open(file_path, "w") as file: + def to_yaml_file(self, file_path: Path, encoding: str = "utf-8") -> None: + """Dump YamlModel instance to yaml file""" + with open(file_path, "w", encoding=encoding) as file: yaml.dump(self.model_dump(), file) class YamlModelWithoutDefault(YamlModel): + """YamlModel without default values""" + @model_validator(mode="before") @classmethod def check_not_default_config(cls, values): + """Check if there is any default config in config.yaml""" if any(["YOUR" in v for v in values]): raise ValueError("Please set your config in config.yaml") return values From feedafeb7846ee5eb981192a3212b5fbb8371fc4 Mon Sep 17 00:00:00 2001 From: geekan Date: Fri, 12 Jan 2024 17:24:29 +0800 Subject: [PATCH 58/61] fix bug --- metagpt/provider/openai_api.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/metagpt/provider/openai_api.py b/metagpt/provider/openai_api.py index 05a8d75f8..3f3a4e1a7 100644 --- a/metagpt/provider/openai_api.py +++ b/metagpt/provider/openai_api.py @@ -223,7 +223,7 @@ class OpenAILLM(BaseLLM): def get_costs(self) -> Costs: if not self.cost_manager: - return Costs() + return Costs(0, 0, 0, 0) return self.cost_manager.get_costs() def _get_max_tokens(self, messages: list[dict]): From 273b85d609a12151c9c0205be300e484e1183b12 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=8E=98=E6=9D=83=20=E9=A9=AC?= Date: Fri, 12 Jan 2024 21:56:59 +0800 Subject: [PATCH 59/61] feat: remove OPTIONS --- metagpt/actions/rebuild_class_view.py | 7 +++---- metagpt/actions/rebuild_sequence_view.py | 5 +++-- metagpt/const.py | 5 ----- 3 files changed, 6 insertions(+), 11 deletions(-) diff --git a/metagpt/actions/rebuild_class_view.py b/metagpt/actions/rebuild_class_view.py index d25d9e49b..2140ad874 100644 --- a/metagpt/actions/rebuild_class_view.py +++ b/metagpt/actions/rebuild_class_view.py @@ -20,7 +20,6 @@ from metagpt.const import ( GENERALIZATION, GRAPH_REPO_FILE_REPO, ) -from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.repo_parser import RepoParser from metagpt.schema import ClassAttribute, ClassMethod, ClassView @@ -31,7 +30,7 @@ from metagpt.utils.graph_repository import GraphKeyword, GraphRepository class RebuildClassView(Action): async def run(self, with_messages=None, format=config.prompt_schema): - graph_repo_pathname = CONTEXT.git_repo.workdir / GRAPH_REPO_FILE_REPO / CONTEXT.git_repo.workdir.name + graph_repo_pathname = self.context.git_repo.workdir / GRAPH_REPO_FILE_REPO / self.context.git_repo.workdir.name graph_db = await DiGraphRepository.load_from(str(graph_repo_pathname.with_suffix(".json"))) repo_parser = RepoParser(base_directory=Path(self.i_context)) # use pylint @@ -49,9 +48,9 @@ class RebuildClassView(Action): await graph_db.save() async def _create_mermaid_class_views(self, graph_db): - path = Path(CONTEXT.git_repo.workdir) / DATA_API_DESIGN_FILE_REPO + path = Path(self.context.git_repo.workdir) / DATA_API_DESIGN_FILE_REPO path.mkdir(parents=True, exist_ok=True) - pathname = path / CONTEXT.git_repo.workdir.name + pathname = path / self.context.git_repo.workdir.name async with aiofiles.open(str(pathname.with_suffix(".mmd")), mode="w", encoding="utf-8") as writer: content = "classDiagram\n" logger.debug(content) diff --git a/metagpt/actions/rebuild_sequence_view.py b/metagpt/actions/rebuild_sequence_view.py index b701e66de..777dde8ce 100644 --- a/metagpt/actions/rebuild_sequence_view.py +++ b/metagpt/actions/rebuild_sequence_view.py @@ -14,7 +14,6 @@ from typing import List from metagpt.actions import Action from metagpt.config2 import config from metagpt.const import GRAPH_REPO_FILE_REPO -from metagpt.context import CONTEXT from metagpt.logs import logger from metagpt.utils.common import aread, list_files from metagpt.utils.di_graph_repository import DiGraphRepository @@ -23,7 +22,7 @@ from metagpt.utils.graph_repository import GraphKeyword class RebuildSequenceView(Action): async def run(self, with_messages=None, format=config.prompt_schema): - graph_repo_pathname = CONTEXT.git_repo.workdir / GRAPH_REPO_FILE_REPO / CONTEXT.git_repo.workdir.name + graph_repo_pathname = self.context.git_repo.workdir / GRAPH_REPO_FILE_REPO / self.context.git_repo.workdir.name graph_db = await DiGraphRepository.load_from(str(graph_repo_pathname.with_suffix(".json"))) entries = await RebuildSequenceView._search_main_entry(graph_db) for entry in entries: @@ -43,6 +42,8 @@ class RebuildSequenceView(Action): async def _rebuild_sequence_view(self, entry, graph_db): filename = entry.subject.split(":", 1)[0] src_filename = RebuildSequenceView._get_full_filename(root=self.i_context, pathname=filename) + if not src_filename: + return content = await aread(filename=src_filename, encoding="utf-8") content = f"```python\n{content}\n```\n\n---\nTranslate the code above into Mermaid Sequence Diagram." data = await self.llm.aask( diff --git a/metagpt/const.py b/metagpt/const.py index f917ee90d..0ae425a47 100644 --- a/metagpt/const.py +++ b/metagpt/const.py @@ -9,7 +9,6 @@ @Modified By: mashenquan, 2023-11-27. Defines file repository paths according to Section 2.2.3.4 of RFC 135. @Modified By: mashenquan, 2023/12/5. Add directories for code summarization.. """ -import contextvars import os from pathlib import Path @@ -17,8 +16,6 @@ from loguru import logger import metagpt -OPTIONS = contextvars.ContextVar("OPTIONS", default={}) - def get_metagpt_package_root(): """Get the root directory of the installed package.""" @@ -71,12 +68,10 @@ SOURCE_ROOT = METAGPT_ROOT / "metagpt" PROMPT_PATH = SOURCE_ROOT / "prompts" SKILL_DIRECTORY = SOURCE_ROOT / "skills" - # REAL CONSTS MEM_TTL = 24 * 30 * 3600 - MESSAGE_ROUTE_FROM = "sent_from" MESSAGE_ROUTE_TO = "send_to" MESSAGE_ROUTE_CAUSE_BY = "cause_by" From 9d1df5acd569fde6c17b297828b0b2848c2c2c00 Mon Sep 17 00:00:00 2001 From: shenchucheng Date: Sun, 14 Jan 2024 23:40:09 +0800 Subject: [PATCH 60/61] mock search engine api --- metagpt/tools/search_engine.py | 9 +- tests/conftest.py | 78 +- tests/data/search_rsp_cache.json | 879 ++++++++++++++++++++++ tests/metagpt/actions/test_research.py | 14 +- tests/metagpt/roles/test_researcher.py | 11 +- tests/metagpt/tools/test_search_engine.py | 29 +- tests/mock/mock_aiohttp.py | 41 + tests/mock/mock_curl_cffi.py | 22 + tests/mock/mock_httplib2.py | 29 + 9 files changed, 1062 insertions(+), 50 deletions(-) create mode 100644 tests/data/search_rsp_cache.json create mode 100644 tests/mock/mock_aiohttp.py create mode 100644 tests/mock/mock_curl_cffi.py create mode 100644 tests/mock/mock_httplib2.py diff --git a/metagpt/tools/search_engine.py b/metagpt/tools/search_engine.py index 4111dd106..0d0db9147 100644 --- a/metagpt/tools/search_engine.py +++ b/metagpt/tools/search_engine.py @@ -44,19 +44,20 @@ class SearchEngine: self, engine: Optional[SearchEngineType] = SearchEngineType.SERPER_GOOGLE, run_func: Callable[[str, int, bool], Coroutine[None, None, Union[str, list[str]]]] = None, + **kwargs, ): if engine == SearchEngineType.SERPAPI_GOOGLE: module = "metagpt.tools.search_engine_serpapi" - run_func = importlib.import_module(module).SerpAPIWrapper().run + run_func = importlib.import_module(module).SerpAPIWrapper(**kwargs).run elif engine == SearchEngineType.SERPER_GOOGLE: module = "metagpt.tools.search_engine_serper" - run_func = importlib.import_module(module).SerperWrapper().run + run_func = importlib.import_module(module).SerperWrapper(**kwargs).run elif engine == SearchEngineType.DIRECT_GOOGLE: module = "metagpt.tools.search_engine_googleapi" - run_func = importlib.import_module(module).GoogleAPIWrapper().run + run_func = importlib.import_module(module).GoogleAPIWrapper(**kwargs).run elif engine == SearchEngineType.DUCK_DUCK_GO: module = "metagpt.tools.search_engine_ddg" - run_func = importlib.import_module(module).DDGAPIWrapper().run + run_func = importlib.import_module(module).DDGAPIWrapper(**kwargs).run elif engine == SearchEngineType.CUSTOM_ENGINE: pass # run_func = run_func else: diff --git a/tests/conftest.py b/tests/conftest.py index 34429417b..f20c261a4 100644 --- a/tests/conftest.py +++ b/tests/conftest.py @@ -12,6 +12,7 @@ import logging import os import re import uuid +from typing import Callable import pytest @@ -20,6 +21,9 @@ from metagpt.context import CONTEXT from metagpt.llm import LLM from metagpt.logs import logger from metagpt.utils.git_repository import GitRepository +from tests.mock.mock_aiohttp import MockAioResponse +from tests.mock.mock_curl_cffi import MockCurlCffiResponse +from tests.mock.mock_httplib2 import MockHttplib2Response from tests.mock.mock_llm import MockLLM RSP_CACHE_NEW = {} # used globally for producing new and useful only response cache @@ -164,39 +168,63 @@ def new_filename(mocker): yield mocker +@pytest.fixture(scope="session") +def search_rsp_cache(): + rsp_cache_file_path = TEST_DATA_PATH / "search_rsp_cache.json" # read repo-provided + if os.path.exists(rsp_cache_file_path): + with open(rsp_cache_file_path, "r") as f1: + rsp_cache_json = json.load(f1) + else: + rsp_cache_json = {} + yield rsp_cache_json + with open(rsp_cache_file_path, "w") as f2: + json.dump(rsp_cache_json, f2, indent=4, ensure_ascii=False) + + @pytest.fixture def aiohttp_mocker(mocker): - class MockAioResponse: - async def json(self, *args, **kwargs): - return self._json - - def set_json(self, json): - self._json = json - - response = MockAioResponse() - - class MockCTXMng: - async def __aenter__(self): - return response - - async def __aexit__(self, *args, **kwargs): - pass - - def __await__(self): - yield - return response - - def mock_request(self, method, url, **kwargs): - return MockCTXMng() + MockResponse = type("MockResponse", (MockAioResponse,), {}) def wrap(method): def run(self, url, **kwargs): - return mock_request(self, method, url, **kwargs) + return MockResponse(self, method, url, **kwargs) return run - mocker.patch("aiohttp.ClientSession.request", mock_request) + mocker.patch("aiohttp.ClientSession.request", MockResponse) for i in ["get", "post", "delete", "patch"]: mocker.patch(f"aiohttp.ClientSession.{i}", wrap(i)) + yield MockResponse - yield response + +@pytest.fixture +def curl_cffi_mocker(mocker): + MockResponse = type("MockResponse", (MockCurlCffiResponse,), {}) + + def request(self, *args, **kwargs): + return MockResponse(self, *args, **kwargs) + + mocker.patch("curl_cffi.requests.Session.request", request) + yield MockResponse + + +@pytest.fixture +def httplib2_mocker(mocker): + MockResponse = type("MockResponse", (MockHttplib2Response,), {}) + + def request(self, *args, **kwargs): + return MockResponse(self, *args, **kwargs) + + mocker.patch("httplib2.Http.request", request) + yield MockResponse + + +@pytest.fixture +def search_engine_mocker(aiohttp_mocker, curl_cffi_mocker, httplib2_mocker, search_rsp_cache): + # aiohttp_mocker: serpapi/serper + # httplib2_mocker: google + # curl_cffi_mocker: ddg + check_funcs: dict[tuple[str, str], Callable[[dict], str]] = {} + aiohttp_mocker.rsp_cache = httplib2_mocker.rsp_cache = curl_cffi_mocker.rsp_cache = search_rsp_cache + aiohttp_mocker.check_funcs = httplib2_mocker.check_funcs = curl_cffi_mocker.check_funcs = check_funcs + yield check_funcs diff --git a/tests/data/search_rsp_cache.json b/tests/data/search_rsp_cache.json new file mode 100644 index 000000000..822fb2069 --- /dev/null +++ b/tests/data/search_rsp_cache.json @@ -0,0 +1,879 @@ +{ + "aiohttp-get-https://serpapi.com/search-{\"params\": {\"api_key\": \"mock-serpapi-key\", \"engine\": \"google\", \"gl\": \"us\", \"google_domain\": \"google.com\", \"hl\": \"en\", \"num\": 8, \"output\": \"json\", \"q\": \"metagpt\", \"source\": \"python\"}}": { + "search_metadata": { + "id": "65a3f6595b54ef7f1dfbcdd2", + "status": "Success", + "json_endpoint": "https://serpapi.com/searches/f3454e001dacdae1/65a3f6595b54ef7f1dfbcdd2.json", + "created_at": "2024-01-14 14:57:29 UTC", + "processed_at": "2024-01-14 14:57:29 UTC", + "google_url": "https://www.google.com/search?q=metagpt&oq=metagpt&hl=en&gl=us&num=8&sourceid=chrome&ie=UTF-8", + "raw_html_file": "https://serpapi.com/searches/f3454e001dacdae1/65a3f6595b54ef7f1dfbcdd2.html", + "total_time_taken": 2.5 + }, + "search_parameters": { + "engine": "google", + "q": "metagpt", + "google_domain": "google.com", + "hl": "en", + "gl": "us", + "num": "8", + "device": "desktop" + }, + "search_information": { + "query_displayed": "metagpt", + "total_results": 91600, + "time_taken_displayed": 0.27, + "menu_items": [ + { + "position": 1, + "title": "News", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=metagpt&tbm=nws&source=lnms&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8Q0pQJegQIEBAB", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=metagpt&tbm=nws" + }, + { + "position": 2, + "title": "Images", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=metagpt&tbm=isch&source=lnms&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8Q0pQJegQIERAB", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google_images&gl=us&google_domain=google.com&hl=en&q=metagpt" + }, + { + "position": 3, + "title": "Perspectives", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=metagpt&uds=AMwkrPv_BNR0fCL4lAUrdY_MslXnXP_8eZcaurn07wVclkT7zdZi70-PsAZ5cIYoShIriCGEG9cp7YID252SJZlezuQgGHVoaxAGC2P-K5BQMhuhn3rxBEI&udm=4&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8Qs6gLegQIEhAB", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=metagpt" + }, + { + "position": 4, + "title": "Download", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=MetaGPT+download&uds=AMwkrPs1tkKhl_yLs17ozqzdeOQpXginZ88vZAAruQSl2egWlmxzo18RJ2iSa2okRlGJpRvhNdkif_bMpSTk2MMlNadEZGUA9HcNBj9XUrqefB2G97SzGtM&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8QxKsJegQIDhAB&ictx=0", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=MetaGPT+download" + }, + { + "position": 5, + "title": "Videos", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=metagpt&tbm=vid&source=lnms&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8Q0pQJegQINRAB", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google_videos&gl=us&google_domain=google.com&hl=en&num=8&q=metagpt" + }, + { + "position": 6, + "title": "Review", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=MetaGPT+review&uds=AMwkrPsrb0_MXdPCtp0RJNoWQEuvuWMXOVdQk9bEznN4tlVCwT3QF14u76JluzhFRLe_8V0vj_J6GkI2lsgMS7iWf5vAS8_exlSGI2NPPyhxAtn0L9DpLP0&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8QxKsJegQINhAB&ictx=0", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=MetaGPT+review" + }, + { + "position": 7, + "title": "Online", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=MetaGPT+online&uds=AMwkrPsoRx99OfyO5-zj61oe0QMzGel38AesYPljQRlBU6r33ArXtPFSYaOzLdJPpJNVmudurhtqLwUnetN4svOtlXgjwySfgpxw9zgVeZ95Yk0B4ftC_Yw&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8QxKsJegQINxAB&ictx=0", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=MetaGPT+online" + }, + { + "position": 8, + "title": "App", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=Metagpt+app&uds=AMwkrPvM3iswphQGpo45MKxhFsVLtYmdTSGDwMjrC3YJfMStztBkIzhQ3LXUWRIS_9CLaKDV49EzlFRs65SDPWQRQ_UhZ9vnYjXCails2jTqGf73j7jxJ5g&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8QxKsJegQIOBAB&ictx=0", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=Metagpt+app" + }, + { + "position": 9, + "title": "AI", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=MetaGPT+AI&uds=AMwkrPtd3khZ7-4qbofZcpN4KpMaARLEVOHuvLVm0W3G2e-1vlpsKSHNi4ZplHhRz_p2lhtBxgOUBiCMoccC6ypD35_CMSI-u6d67n4mJNsyAnhftmvIlk8&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8QxKsJegQIORAB&ictx=0", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=MetaGPT+AI" + } + ], + "organic_results_state": "Results for exact spelling" + }, + "inline_videos": [ + { + "position": 1, + "title": "How To Install MetaGPT - Build A Startup With One Prompt!!", + "link": "https://www.youtube.com/watch?v=uT75J_KG_aY", + "thumbnail": "https://serpapi.com/searches/65a3f6595b54ef7f1dfbcdd2/images/a0db2f9f70f02dd11e3d3d4154df9fd65b46b2fbf4804f7038c9ce99c8efea1c.jpeg", + "channel": "Matthew Berman", + "duration": "6:36", + "platform": "YouTube", + "date": "Aug 14, 2023" + }, + { + "position": 2, + "title": "MetaGPT HUGE Update: Autonomous AI Agents with ...", + "link": "https://www.youtube.com/watch?v=Xyws6iI-eH8", + "thumbnail": "https://serpapi.com/searches/65a3f6595b54ef7f1dfbcdd2/images/a0db2f9f70f02dd1d578e6031265d66299cf6aecd327454cdf67b92808f3dd86.jpeg", + "channel": "WorldofAI", + "duration": "11:38", + "platform": "YouTube", + "date": "3 weeks ago" + }, + { + "position": 3, + "title": "🚀 MetaGPT Setup: Launch a Startup with One ✍️ Prompt!", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao", + "thumbnail": "https://serpapi.com/searches/65a3f6595b54ef7f1dfbcdd2/images/a0db2f9f70f02dd1c5666bd22292fdc357357dac89294aabb55ebea0a40ce322.jpeg", + "channel": "Prompt Engineering", + "duration": "14:15", + "platform": "YouTube", + "date": "Sep 4, 2023", + "key_moments": [ + { + "time": "00:00", + "title": "Intro", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=0", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQW-YKGXQDHplRpEDgL5Q-HlJ8HggTw_ghp_KWPh8xUcQ&s" + }, + { + "time": "00:12", + "title": "What is MetaGPT", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=12", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRJ4RRAXOG6yvGPYqkuj5cMoiyYdAN6g7E3VU04SA3P7w&s" + }, + { + "time": "01:06", + "title": "Setup", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=66", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTDlJBrAtfBkC8zI9wY4dOqVIaNFbjcYSZr4M1ZnD7RSw&s" + }, + { + "time": "05:23", + "title": "Changing configuration", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=323", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcT8MbsIRVXJy__UE4ba0FoCTMGfrykasHm3UGvSzMQAtQ&s" + }, + { + "time": "06:35", + "title": "How to Run", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=395", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRuX6mOUVQVRzvnkOPYNcDpcazRC1QGeHhZh-Az9btUNA&s" + }, + { + "time": "09:02", + "title": "What outputs to expect", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=542", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTFnNqvPfGrPnKJTJ1iOHGSNp6sVR5jn0Zy5N2JSGfeEQ&s" + }, + { + "time": "10:45", + "title": "Generated Design Documents", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=645", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSN3I0gxudI4Mew93w_tw34HmWREz5XX8ArebReM3Y2_g&s" + }, + { + "time": "12:25", + "title": "Run the created code base", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=745", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQLBx5bgKZ2Gqsu-PsIXuvtM0SBmHvBCndmKtresgqFCg&s" + } + ] + } + ], + "organic_results": [ + { + "position": 1, + "title": "geekan/MetaGPT: 🌟 The Multi-Agent Framework", + "link": "https://github.com/geekan/MetaGPT", + "redirect_link": "https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://github.com/geekan/MetaGPT&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8QFnoECBUQAQ", + "displayed_link": "https://github.com › geekan › MetaGPT", + "favicon": "https://serpapi.com/searches/65a3f6595b54ef7f1dfbcdd2/images/f37f87ccfb08b6fc2fe7e2076c022e7690f9b18357b8e5feb75a30ffbaaabfb1.png", + "snippet": "MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc.", + "snippet_highlighted_words": [ + "MetaGPT" + ], + "sitelinks": { + "inline": [ + { + "title": "Roadmap", + "link": "https://github.com/geekan/MetaGPT/blob/main/docs/ROADMAP.md" + }, + { + "title": "README.md", + "link": "https://github.com/geekan/MetaGPT/blob/main/README.md" + }, + { + "title": "Issues 161", + "link": "https://github.com/geekan/MetaGPT/issues" + }, + { + "title": "Actions", + "link": "https://github.com/geekan/MetaGPT/actions" + } + ] + }, + "source": "GitHub" + }, + { + "position": 2, + "title": "MetaGPT: Meta Programming for A Multi-Agent ...", + "link": "https://arxiv.org/abs/2308.00352", + "redirect_link": "https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://arxiv.org/abs/2308.00352&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8QFnoECBMQAQ", + "displayed_link": "https://arxiv.org › cs", + "favicon": "https://serpapi.com/searches/65a3f6595b54ef7f1dfbcdd2/images/f37f87ccfb08b6fc2fe7e2076c022e76592372342f3f5dd76573e051b50f1bce.png", + "author": "by S Hong", + "cited_by": "Cited by 63", + "extracted_cited_by": 63, + "date": "2023", + "snippet": "Abstract:Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs).", + "source": "arXiv" + }, + { + "position": 3, + "title": "MetaGPT: a Multi-Agent Framework to Automate Your ...", + "link": "https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-to-automate-your-software-company-4b6ae747cc36", + "redirect_link": "https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-to-automate-your-software-company-4b6ae747cc36&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8QFnoECBgQAQ", + "displayed_link": "https://medium.datadriveninvestor.com › metagpt-a-...", + "favicon": "https://serpapi.com/searches/65a3f6595b54ef7f1dfbcdd2/images/f37f87ccfb08b6fc2fe7e2076c022e76e8319069677ee18a99026fb1e05709cf.png", + "snippet": "MetaGPT is about to reach 10000 stars on Github. It's a Multi-Agent Framework that can behave as an engineer, product manager, architect, project managers.", + "snippet_highlighted_words": [ + "MetaGPT" + ], + "source": "DataDrivenInvestor" + }, + { + "position": 4, + "title": "MetaGPT - Apps on Google Play", + "link": "https://play.google.com/store/apps/details?id=com.metagpt.app&hl=en&gl=US", + "redirect_link": "https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://play.google.com/store/apps/details%3Fid%3Dcom.metagpt.app%26hl%3Den%26gl%3DUS&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8QFnoECCUQAQ", + "displayed_link": "https://play.google.com › store › apps › details › id=c...", + "favicon": "https://serpapi.com/searches/65a3f6595b54ef7f1dfbcdd2/images/f37f87ccfb08b6fc2fe7e2076c022e76334a7b2eeab09f16973a82a209ee6339.png", + "date": "Jan 1, 2024", + "snippet": "Real-time crypto monitor.Track prices, set alerts, seize opportunities instantly.", + "source": "Google Play" + }, + { + "position": 5, + "title": "MetaGPT: AI-Powered Web Development That Changes ...", + "link": "https://www.analyticsvidhya.com/blog/2024/01/meet-metagpt-the-chatgpt-powered-ai-assistant-that-turns-text-into-web-apps/", + "redirect_link": "https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://www.analyticsvidhya.com/blog/2024/01/meet-metagpt-the-chatgpt-powered-ai-assistant-that-turns-text-into-web-apps/&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8QFnoECCkQAQ", + "displayed_link": "https://www.analyticsvidhya.com › blog › 2024/01", + "favicon": "https://serpapi.com/searches/65a3f6595b54ef7f1dfbcdd2/images/f37f87ccfb08b6fc2fe7e2076c022e766a141f2bf05b1ab902f83ed00f4148a4.png", + "date": "Jan 4, 2024", + "snippet": "MetaGPT is an AI assistant that leverages the power of GPT-4, a state-of-the-art language model developed by OpenAI. ChatGPT is trained on vast ...", + "snippet_highlighted_words": [ + "MetaGPT" + ], + "source": "Analytics Vidhya" + }, + { + "position": 6, + "title": "MetaGPT | Discover AI use cases", + "link": "https://gpt3demo.com/apps/metagpt", + "redirect_link": "https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://gpt3demo.com/apps/metagpt&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8QFnoECCQQAQ", + "displayed_link": "https://gpt3demo.com › apps › metagpt", + "favicon": "https://serpapi.com/searches/65a3f6595b54ef7f1dfbcdd2/images/f37f87ccfb08b6fc2fe7e2076c022e76142721493557b5d95328dafb62b6b43a.jpeg", + "snippet": "Assign different roles to GPTs to form a collaborative software entity for complex tasks. MetaGPT takes a one-line requirement as input and outputs user ...", + "snippet_highlighted_words": [ + "MetaGPT" + ], + "source": "GPT-3 Demo" + } + ], + "related_searches": [ + { + "block_position": 1, + "query": "metagpt online", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=MetaGPT+online&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8Q1QJ6BAgnEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=MetaGPT+online" + }, + { + "block_position": 1, + "query": "metagpt paper", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=MetaGPT+paper&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8Q1QJ6BAgoEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=MetaGPT+paper" + }, + { + "block_position": 1, + "query": "Metagpt download", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=Metagpt+download&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8Q1QJ6BAgmEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=Metagpt+download" + }, + { + "block_position": 1, + "query": "metagpt github", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=Metagpt+github&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8Q1QJ6BAgiEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=Metagpt+github" + }, + { + "block_position": 1, + "query": "Metagpt review", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=Metagpt+review&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8Q1QJ6BAgjEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=Metagpt+review" + }, + { + "block_position": 1, + "query": "metagpt ai", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=MetaGPT+AI&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8Q1QJ6BAggEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=MetaGPT+AI" + }, + { + "block_position": 1, + "query": "metagpt huggingface", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=MetaGPT+huggingface&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8Q1QJ6BAghEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=MetaGPT+huggingface" + }, + { + "block_position": 1, + "query": "metagpt openai", + "link": "https://www.google.com/search?num=8&sca_esv=598392389&hl=en&gl=us&q=Metagpt+OpenAI&sa=X&ved=2ahUKEwiZ6tvukd2DAxWuFlkFHbnFBv8Q1QJ6BAgfEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=Metagpt+OpenAI" + } + ], + "pagination": { + "current": 1, + "next": "https://www.google.com/search?q=metagpt&oq=metagpt&hl=en&gl=us&num=8&start=8&sourceid=chrome&ie=UTF-8", + "other_pages": { + "2": "https://www.google.com/search?q=metagpt&oq=metagpt&hl=en&gl=us&num=8&start=8&sourceid=chrome&ie=UTF-8", + "3": "https://www.google.com/search?q=metagpt&oq=metagpt&hl=en&gl=us&num=8&start=16&sourceid=chrome&ie=UTF-8", + "4": "https://www.google.com/search?q=metagpt&oq=metagpt&hl=en&gl=us&num=8&start=24&sourceid=chrome&ie=UTF-8", + "5": "https://www.google.com/search?q=metagpt&oq=metagpt&hl=en&gl=us&num=8&start=32&sourceid=chrome&ie=UTF-8" + } + }, + "serpapi_pagination": { + "current": 1, + "next_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=metagpt&start=8", + "next": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=metagpt&start=8", + "other_pages": { + "2": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=metagpt&start=8", + "3": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=metagpt&start=16", + "4": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=metagpt&start=24", + "5": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=8&q=metagpt&start=32" + } + } + }, + "aiohttp-get-https://serpapi.com/search-{\"params\": {\"api_key\": \"mock-serpapi-key\", \"engine\": \"google\", \"gl\": \"us\", \"google_domain\": \"google.com\", \"hl\": \"en\", \"num\": 4, \"output\": \"json\", \"q\": \"metagpt\", \"source\": \"python\"}}": { + "search_metadata": { + "id": "65a3f65d8b7ed28c15233c79", + "status": "Success", + "json_endpoint": "https://serpapi.com/searches/2081c01f04a8e878/65a3f65d8b7ed28c15233c79.json", + "created_at": "2024-01-14 14:57:33 UTC", + "processed_at": "2024-01-14 14:57:33 UTC", + "google_url": "https://www.google.com/search?q=metagpt&oq=metagpt&hl=en&gl=us&num=4&sourceid=chrome&ie=UTF-8", + "raw_html_file": "https://serpapi.com/searches/2081c01f04a8e878/65a3f65d8b7ed28c15233c79.html", + "total_time_taken": 2.89 + }, + "search_parameters": { + "engine": "google", + "q": "metagpt", + "google_domain": "google.com", + "hl": "en", + "gl": "us", + "num": "4", + "device": "desktop" + }, + "search_information": { + "query_displayed": "metagpt", + "total_results": 91600, + "time_taken_displayed": 0.2, + "menu_items": [ + { + "position": 1, + "title": "News", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=metagpt&tbm=nws&source=lnms&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQ0pQJegQIChAB", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=metagpt&tbm=nws" + }, + { + "position": 2, + "title": "Images", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=metagpt&tbm=isch&source=lnms&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQ0pQJegQIDhAB", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google_images&gl=us&google_domain=google.com&hl=en&q=metagpt" + }, + { + "position": 3, + "title": "Perspectives", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=metagpt&uds=AMwkrPv_BNR0fCL4lAUrdY_MslXnXP_8eZcaurn07wVclkT7zdZi70-PsAZ5cIYoShIriCGEG9cp7YID252SJZlezuQgGHVoaxAGC2P-K5BQMhuhn3rxBEI&udm=4&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQs6gLegQIDRAB", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=metagpt" + }, + { + "position": 4, + "title": "Download", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=MetaGPT+download&uds=AMwkrPs1tkKhl_yLs17ozqzdeOQpXginZ88vZAAruQSl2egWlmxzo18RJ2iSa2okRlGJpRvhNdkif_bMpSTk2MMlNadEZGUA9HcNBj9XUrqefB2G97SzGtM&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQxKsJegQICxAB&ictx=0", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=MetaGPT+download" + }, + { + "position": 5, + "title": "Videos", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=metagpt&tbm=vid&source=lnms&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQ0pQJegQILBAB", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google_videos&gl=us&google_domain=google.com&hl=en&num=4&q=metagpt" + }, + { + "position": 6, + "title": "Review", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=MetaGPT+review&uds=AMwkrPsrb0_MXdPCtp0RJNoWQEuvuWMXOVdQk9bEznN4tlVCwT3QF14u76JluzhFRLe_8V0vj_J6GkI2lsgMS7iWf5vAS8_exlSGI2NPPyhxAtn0L9DpLP0&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQxKsJegQILhAB&ictx=0", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=MetaGPT+review" + }, + { + "position": 7, + "title": "Online", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=MetaGPT+online&uds=AMwkrPsoRx99OfyO5-zj61oe0QMzGel38AesYPljQRlBU6r33ArXtPFSYaOzLdJPpJNVmudurhtqLwUnetN4svOtlXgjwySfgpxw9zgVeZ95Yk0B4ftC_Yw&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQxKsJegQILRAB&ictx=0", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=MetaGPT+online" + }, + { + "position": 8, + "title": "App", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=Metagpt+app&uds=AMwkrPvM3iswphQGpo45MKxhFsVLtYmdTSGDwMjrC3YJfMStztBkIzhQ3LXUWRIS_9CLaKDV49EzlFRs65SDPWQRQ_UhZ9vnYjXCails2jTqGf73j7jxJ5g&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQxKsJegQILxAB&ictx=0", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=Metagpt+app" + }, + { + "position": 9, + "title": "AI", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=MetaGPT+AI&uds=AMwkrPtd3khZ7-4qbofZcpN4KpMaARLEVOHuvLVm0W3G2e-1vlpsKSHNi4ZplHhRz_p2lhtBxgOUBiCMoccC6ypD35_CMSI-u6d67n4mJNsyAnhftmvIlk8&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQxKsJegQIMBAB&ictx=0", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=MetaGPT+AI" + } + ], + "organic_results_state": "Results for exact spelling" + }, + "inline_videos": [ + { + "position": 1, + "title": "How To Install MetaGPT - Build A Startup With One Prompt!!", + "link": "https://www.youtube.com/watch?v=uT75J_KG_aY", + "thumbnail": "https://serpapi.com/searches/65a3f65d8b7ed28c15233c79/images/bfd65a15364211be961855b9ca9c1cbfeecac1fc4f084deba696fe02f511b2b0.jpeg", + "channel": "Matthew Berman", + "duration": "6:36", + "platform": "YouTube", + "date": "Aug 14, 2023" + }, + { + "position": 2, + "title": "MetaGPT HUGE Update: Autonomous AI Agents with ...", + "link": "https://www.youtube.com/watch?v=Xyws6iI-eH8", + "thumbnail": "https://serpapi.com/searches/65a3f65d8b7ed28c15233c79/images/bfd65a15364211be43551974ef1dbd0b4a3780c1caa0ef2d1edaaee2ebc89b3c.jpeg", + "channel": "WorldofAI", + "duration": "11:38", + "platform": "YouTube", + "date": "3 weeks ago" + }, + { + "position": 3, + "title": "🚀 MetaGPT Setup: Launch a Startup with One ✍️ Prompt!", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao", + "thumbnail": "https://serpapi.com/searches/65a3f65d8b7ed28c15233c79/images/bfd65a15364211be779beff6d19f978b32bf888581454f54a19b9b01c5d9a6a8.jpeg", + "channel": "Prompt Engineering", + "duration": "14:15", + "platform": "YouTube", + "date": "Sep 4, 2023", + "key_moments": [ + { + "time": "00:00", + "title": "Intro", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=0", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQW-YKGXQDHplRpEDgL5Q-HlJ8HggTw_ghp_KWPh8xUcQ&s" + }, + { + "time": "00:12", + "title": "What is MetaGPT", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=12", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRJ4RRAXOG6yvGPYqkuj5cMoiyYdAN6g7E3VU04SA3P7w&s" + }, + { + "time": "01:06", + "title": "Setup", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=66", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTDlJBrAtfBkC8zI9wY4dOqVIaNFbjcYSZr4M1ZnD7RSw&s" + }, + { + "time": "05:23", + "title": "Changing configuration", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=323", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcT8MbsIRVXJy__UE4ba0FoCTMGfrykasHm3UGvSzMQAtQ&s" + }, + { + "time": "06:35", + "title": "How to Run", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=395", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRuX6mOUVQVRzvnkOPYNcDpcazRC1QGeHhZh-Az9btUNA&s" + }, + { + "time": "09:02", + "title": "What outputs to expect", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=542", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTFnNqvPfGrPnKJTJ1iOHGSNp6sVR5jn0Zy5N2JSGfeEQ&s" + }, + { + "time": "10:45", + "title": "Generated Design Documents", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=645", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSN3I0gxudI4Mew93w_tw34HmWREz5XX8ArebReM3Y2_g&s" + }, + { + "time": "12:25", + "title": "Run the created code base", + "link": "https://www.youtube.com/watch?v=nqZlTV_L6Ao&t=745", + "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQLBx5bgKZ2Gqsu-PsIXuvtM0SBmHvBCndmKtresgqFCg&s" + } + ] + } + ], + "organic_results": [ + { + "position": 1, + "title": "geekan/MetaGPT: 🌟 The Multi-Agent Framework", + "link": "https://github.com/geekan/MetaGPT", + "redirect_link": "https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://github.com/geekan/MetaGPT&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQFnoECBcQAQ", + "displayed_link": "https://github.com › geekan › MetaGPT", + "favicon": "https://serpapi.com/searches/65a3f65d8b7ed28c15233c79/images/754322707626bed29162a2ba4a9960076a2cfb8f3558519e16fc8a6b74240174.png", + "snippet": "MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc.", + "snippet_highlighted_words": [ + "MetaGPT" + ], + "sitelinks": { + "inline": [ + { + "title": "README.md", + "link": "https://github.com/geekan/MetaGPT/blob/main/README.md" + }, + { + "title": "Roadmap", + "link": "https://github.com/geekan/MetaGPT/blob/main/docs/ROADMAP.md" + }, + { + "title": "Issues 161", + "link": "https://github.com/geekan/MetaGPT/issues" + }, + { + "title": "Actions", + "link": "https://github.com/geekan/MetaGPT/actions" + } + ] + }, + "source": "GitHub" + }, + { + "position": 2, + "title": "MetaGPT: Meta Programming for A Multi-Agent ...", + "link": "https://arxiv.org/abs/2308.00352", + "redirect_link": "https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://arxiv.org/abs/2308.00352&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQFnoECBUQAQ", + "displayed_link": "https://arxiv.org › cs", + "favicon": "https://serpapi.com/searches/65a3f65d8b7ed28c15233c79/images/754322707626bed29162a2ba4a996007d238ff23f244403a638b759e517db592.png", + "author": "by S Hong", + "cited_by": "Cited by 63", + "extracted_cited_by": 63, + "date": "2023", + "snippet": "Abstract:Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs).", + "source": "arXiv" + }, + { + "position": 3, + "title": "MetaGPT: a Multi-Agent Framework to Automate Your ...", + "link": "https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-to-automate-your-software-company-4b6ae747cc36", + "redirect_link": "https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-to-automate-your-software-company-4b6ae747cc36&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQFnoECBMQAQ", + "displayed_link": "https://medium.datadriveninvestor.com › metagpt-a-m...", + "favicon": "https://serpapi.com/searches/65a3f65d8b7ed28c15233c79/images/754322707626bed29162a2ba4a996007983965c804f215b78e84b23e3aabec98.png", + "snippet": "MetaGPT is about to reach 10000 stars on Github. It's a Multi-Agent Framework that can behave as an engineer, product manager, architect, project managers.", + "snippet_highlighted_words": [ + "MetaGPT" + ], + "source": "DataDrivenInvestor" + } + ], + "related_searches": [ + { + "block_position": 1, + "query": "metagpt online", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=MetaGPT+online&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQ1QJ6BAgmEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=MetaGPT+online" + }, + { + "block_position": 1, + "query": "metagpt paper", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=MetaGPT+paper&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQ1QJ6BAglEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=MetaGPT+paper" + }, + { + "block_position": 1, + "query": "Metagpt download", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=Metagpt+download&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQ1QJ6BAgjEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=Metagpt+download" + }, + { + "block_position": 1, + "query": "metagpt github", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=Metagpt+github&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQ1QJ6BAgkEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=Metagpt+github" + }, + { + "block_position": 1, + "query": "Metagpt review", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=Metagpt+review&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQ1QJ6BAgiEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=Metagpt+review" + }, + { + "block_position": 1, + "query": "metagpt ai", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=MetaGPT+AI&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQ1QJ6BAgfEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=MetaGPT+AI" + }, + { + "block_position": 1, + "query": "metagpt huggingface", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=MetaGPT+huggingface&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQ1QJ6BAggEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=MetaGPT+huggingface" + }, + { + "block_position": 1, + "query": "metagpt openai", + "link": "https://www.google.com/search?num=4&sca_esv=598392389&gl=us&hl=en&q=Metagpt+OpenAI&sa=X&ved=2ahUKEwigwuTwkd2DAxWyOkQIHc_uDdEQ1QJ6BAghEAE", + "serpapi_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=Metagpt+OpenAI" + } + ], + "pagination": { + "current": 1, + "next": "https://www.google.com/search?q=metagpt&oq=metagpt&hl=en&gl=us&num=4&start=4&sourceid=chrome&ie=UTF-8", + "other_pages": { + "2": "https://www.google.com/search?q=metagpt&oq=metagpt&hl=en&gl=us&num=4&start=4&sourceid=chrome&ie=UTF-8", + "3": "https://www.google.com/search?q=metagpt&oq=metagpt&hl=en&gl=us&num=4&start=8&sourceid=chrome&ie=UTF-8", + "4": "https://www.google.com/search?q=metagpt&oq=metagpt&hl=en&gl=us&num=4&start=12&sourceid=chrome&ie=UTF-8", + "5": "https://www.google.com/search?q=metagpt&oq=metagpt&hl=en&gl=us&num=4&start=16&sourceid=chrome&ie=UTF-8" + } + }, + "serpapi_pagination": { + "current": 1, + "next_link": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=metagpt&start=4", + "next": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=metagpt&start=4", + "other_pages": { + "2": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=metagpt&start=4", + "3": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=metagpt&start=8", + "4": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=metagpt&start=12", + "5": "https://serpapi.com/search.json?device=desktop&engine=google&gl=us&google_domain=google.com&hl=en&num=4&q=metagpt&start=16" + } + } + }, + "httplib2-GET-https://customsearch.googleapis.com/customsearch/v1-{\"params\": {\"q\": \"metagpt\", \"num\": \"8\", \"cx\": \"mock-google-cse\", \"key\": \"mock-google-key\", \"alt\": \"json\"}}": "{\n \"kind\": \"customsearch#search\",\n \"url\": {\n \"type\": \"application/json\",\n \"template\": \"https://www.googleapis.com/customsearch/v1?q={searchTerms}&num={count?}&start={startIndex?}&lr={language?}&safe={safe?}&cx={cx?}&sort={sort?}&filter={filter?}&gl={gl?}&cr={cr?}&googlehost={googleHost?}&c2coff={disableCnTwTranslation?}&hq={hq?}&hl={hl?}&siteSearch={siteSearch?}&siteSearchFilter={siteSearchFilter?}&exactTerms={exactTerms?}&excludeTerms={excludeTerms?}&linkSite={linkSite?}&orTerms={orTerms?}&dateRestrict={dateRestrict?}&lowRange={lowRange?}&highRange={highRange?}&searchType={searchType}&fileType={fileType?}&rights={rights?}&imgSize={imgSize?}&imgType={imgType?}&imgColorType={imgColorType?}&imgDominantColor={imgDominantColor?}&alt=json\"\n },\n \"queries\": {\n \"request\": [\n {\n \"title\": \"Google Custom Search - metagpt\",\n \"totalResults\": \"71300\",\n \"searchTerms\": \"metagpt\",\n \"count\": 8,\n \"startIndex\": 1,\n \"inputEncoding\": \"utf8\",\n \"outputEncoding\": \"utf8\",\n \"safe\": \"off\",\n \"cx\": \"mock-google-cse\"\n }\n ],\n \"nextPage\": [\n {\n \"title\": \"Google Custom Search - metagpt\",\n \"totalResults\": \"71300\",\n \"searchTerms\": \"metagpt\",\n \"count\": 8,\n \"startIndex\": 9,\n \"inputEncoding\": \"utf8\",\n \"outputEncoding\": \"utf8\",\n \"safe\": \"off\",\n \"cx\": \"mock-google-cse\"\n }\n ]\n },\n \"context\": {\n \"title\": \"metagpt1\"\n },\n \"searchInformation\": {\n \"searchTime\": 0.353952,\n \"formattedSearchTime\": \"0.35\",\n \"totalResults\": \"71300\",\n \"formattedTotalResults\": \"71,300\"\n },\n \"items\": [\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"geekan/MetaGPT: The Multi-Agent Framework: Given one ... - GitHub\",\n \"htmlTitle\": \"geekan/MetaGPT: The Multi-Agent Framework: Given one ... - GitHub\",\n \"link\": \"https://github.com/geekan/MetaGPT\",\n \"displayLink\": \"github.com\",\n \"snippet\": \"The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo - GitHub - geekan/MetaGPT: The Multi-Agent Framework: Given one ...\",\n \"htmlSnippet\": \"The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo - GitHub - geekan/\\u003cb\\u003eMetaGPT\\u003c/b\\u003e: The Multi-Agent Framework: Given one ...\",\n \"cacheId\": \"gsshb0APPNgJ\",\n \"formattedUrl\": \"https://github.com/geekan/MetaGPT\",\n \"htmlFormattedUrl\": \"https://github.com/geekan/\\u003cb\\u003eMetaGPT\\u003c/b\\u003e\",\n \"pagemap\": {\n \"cse_thumbnail\": [\n {\n \"src\": \"https://encrypted-tbn1.gstatic.com/images?q=tbn:ANd9GcRuD8YUvRcltmdoxKyuIbt8UZhg3LE5mwNX7KPXDB15YIJRKdT2m5JiweuS\",\n \"width\": \"318\",\n \"height\": \"159\"\n }\n ],\n \"softwaresourcecode\": [\n {\n \"author\": \"geekan\",\n \"name\": \"MetaGPT\",\n \"text\": \"MetaGPT: The Multi-Agent Framework Assign different roles to GPTs to form a collaborative software entity for complex tasks. MetaGPT takes a one line requirement as input and outputs user stories...\"\n }\n ],\n \"metatags\": [\n {\n \"octolytics-url\": \"https://collector.github.com/github/collect\",\n \"apple-itunes-app\": \"app-id=1477376905, app-argument=https://github.com/geekan/MetaGPT\",\n \"og:image\": \"https://opengraph.githubassets.com/6178eb2aa6711c676eafc956e52345e71225c58cd0a666b54871171e847c0905/geekan/MetaGPT\",\n \"twitter:card\": \"summary_large_image\",\n \"og:image:width\": \"1200\",\n \"theme-color\": \"#1e2327\",\n \"og:site_name\": \"GitHub\",\n \"hovercard-subject-tag\": \"repository:660551251\",\n \"turbo-body-classes\": \"logged-out env-production page-responsive\",\n \"html-safe-nonce\": \"a6964edcf12c9ea83de0bf16db8105c60333287597018548250a0fa92b93d3f9\",\n \"expected-hostname\": \"github.com\",\n \"og:description\": \"🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo - GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Task...\",\n \"browser-errors-url\": \"https://api.github.com/_private/browser/errors\",\n \"octolytics-dimension-user_login\": \"geekan\",\n \"hostname\": \"github.com\",\n \"twitter:site\": \"@github\",\n \"browser-stats-url\": \"https://api.github.com/_private/browser/stats\",\n \"route-pattern\": \"/:user_id/:repository\",\n \"visitor-payload\": \"eyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJBNjIxOjk2OUU6OTZERjlEQzpEM0UxM0RFOjY1QTNBQjU0IiwidmlzaXRvcl9pZCI6IjU2ODA2NDI2MDQ0ODY5MzA3NyIsInJlZ2lvbl9lZGdlIjoiaWFkIiwicmVnaW9uX3JlbmRlciI6ImlhZCJ9\",\n \"github-keyboard-shortcuts\": \"repository\",\n \"octolytics-dimension-repository_id\": \"660551251\",\n \"octolytics-dimension-repository_network_root_nwo\": \"geekan/MetaGPT\",\n \"twitter:title\": \"GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo\",\n \"og:image:alt\": \"🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo - GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Task...\",\n \"og:type\": \"object\",\n \"optimizely-datafile\": \"{\\\"accountId\\\": \\\"16737760170\\\", \\\"projectId\\\": \\\"16737760170\\\", \\\"revision\\\": \\\"23\\\", \\\"attributes\\\": [{\\\"id\\\": \\\"16822470375\\\", \\\"key\\\": \\\"user_id\\\"}, {\\\"id\\\": \\\"17143601254\\\", \\\"key\\\": \\\"spammy\\\"}, {\\\"id\\\": \\\"18175660309\\\", \\\"key\\\": \\\"organization_plan\\\"}, {\\\"id\\\": \\\"18813001570\\\", \\\"key\\\": \\\"is_logged_in\\\"}, {\\\"id\\\": \\\"19073851829\\\", \\\"key\\\": \\\"geo\\\"}, {\\\"id\\\": \\\"20175462351\\\", \\\"key\\\": \\\"requestedCurrency\\\"}, {\\\"id\\\": \\\"20785470195\\\", \\\"key\\\": \\\"country_code\\\"}, {\\\"id\\\": \\\"21656311196\\\", \\\"key\\\": \\\"opened_downgrade_dialog\\\"}], \\\"audiences\\\": [{\\\"id\\\": \\\"$opt_dummy_audience\\\", \\\"name\\\": \\\"Optimizely-Generated Audience for Backwards Compatibility\\\", \\\"conditions\\\": \\\"[\\\\\\\"or\\\\\\\", {\\\\\\\"match\\\\\\\": \\\\\\\"exact\\\\\\\", \\\\\\\"name\\\\\\\": \\\\\\\"$opt_dummy_attribute\\\\\\\", \\\\\\\"type\\\\\\\": \\\\\\\"custom_attribute\\\\\\\", \\\\\\\"value\\\\\\\": \\\\\\\"$opt_dummy_value\\\\\\\"}]\\\"}], \\\"version\\\": \\\"4\\\", \\\"events\\\": [{\\\"id\\\": \\\"18188530140\\\", \\\"experimentIds\\\": [], \\\"key\\\": \\\"test_event\\\"}], \\\"integrations\\\": [], \\\"anonymizeIP\\\": true, \\\"botFiltering\\\": false, \\\"typedAudiences\\\": [], \\\"variables\\\": [], \\\"environmentKey\\\": \\\"production\\\", \\\"sdkKey\\\": \\\"UpVyJZaLVEGwJPQWf5pAD\\\", \\\"featureFlags\\\": [], \\\"rollouts\\\": [],\",\n \"og:title\": \"GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo\",\n \"visitor-hmac\": \"471691c5f7e3204061bb09c630c440708f5c08a2824d60b0f28eea873d474cd7\",\n \"og:image:height\": \"600\",\n \"turbo-cache-control\": \"no-preview\",\n \"request-id\": \"A621:969E:96DF9DC:D3E13DE:65A3AB54\",\n \"analytics-location\": \"/\\u003cuser-name\\u003e/\\u003crepo-name\\u003e\",\n \"color-scheme\": \"light dark\",\n \"octolytics-dimension-repository_is_fork\": \"false\",\n \"go-import\": \"github.com/geekan/MetaGPT git https://github.com/geekan/MetaGPT.git\",\n \"browser-optimizely-client-errors-url\": \"https://api.github.com/_private/browser/optimizely_client/errors\",\n \"twitter:image:src\": \"https://opengraph.githubassets.com/6178eb2aa6711c676eafc956e52345e71225c58cd0a666b54871171e847c0905/geekan/MetaGPT\",\n \"octolytics-dimension-user_id\": \"2707039\",\n \"octolytics-dimension-repository_public\": \"true\",\n \"fb:app_id\": \"1401488693436528\",\n \"octolytics-dimension-repository_network_root_id\": \"660551251\",\n \"octolytics-dimension-repository_nwo\": \"geekan/MetaGPT\",\n \"viewport\": \"width=device-width\",\n \"twitter:description\": \"🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo - GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Task...\",\n \"current-catalog-service-hash\": \"82c569b93da5c18ed649ebd4c2c79437db4611a6a1373e805a3cb001c64130b7\",\n \"og:url\": \"https://github.com/geekan/MetaGPT\"\n }\n ],\n \"cse_image\": [\n {\n \"src\": \"https://opengraph.githubassets.com/6178eb2aa6711c676eafc956e52345e71225c58cd0a666b54871171e847c0905/geekan/MetaGPT\"\n }\n ]\n }\n },\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"[2308.00352] MetaGPT: Meta Programming for A Multi-Agent ...\",\n \"htmlTitle\": \"[2308.00352] \\u003cb\\u003eMetaGPT\\u003c/b\\u003e: Meta Programming for A Multi-Agent ...\",\n \"link\": \"https://arxiv.org/abs/2308.00352\",\n \"displayLink\": \"arxiv.org\",\n \"snippet\": \"Aug 1, 2023 ... Computer Science \\u003e Artificial Intelligence · Title:MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework · Bibliographic and ...\",\n \"htmlSnippet\": \"Aug 1, 2023 \\u003cb\\u003e...\\u003c/b\\u003e Computer Science > Artificial Intelligence · Title:\\u003cb\\u003eMetaGPT\\u003c/b\\u003e: Meta Programming for A Multi-Agent Collaborative Framework · Bibliographic and ...\",\n \"cacheId\": \"8_tddNY0jEYJ\",\n \"formattedUrl\": \"https://arxiv.org/abs/2308.00352\",\n \"htmlFormattedUrl\": \"https://arxiv.org/abs/2308.00352\",\n \"pagemap\": {\n \"cse_thumbnail\": [\n {\n \"src\": \"https://encrypted-tbn3.gstatic.com/images?q=tbn:ANd9GcStsc5IszP_UC7vkymrk7PhjHGOFQhTh862xtJcQkxDem2IteJQXpob6_Vb\",\n \"width\": \"336\",\n \"height\": \"150\"\n }\n ],\n \"metatags\": [\n {\n \"og:image\": \"/static/browse/0.3.4/images/arxiv-logo-fb.png\",\n \"theme-color\": \"#ffffff\",\n \"og:image:width\": \"1200\",\n \"twitter:card\": \"summary\",\n \"citation_title\": \"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework\",\n \"og:site_name\": \"arXiv.org\",\n \"citation_date\": \"2023/08/01\",\n \"og:description\": \"Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediate results and reduce errors. MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-base\",\n \"og:image:secure_url\": \"/static/browse/0.3.4/images/arxiv-logo-fb.png\",\n \"twitter:image\": \"https://static.arxiv.org/icons/twitter/arxiv-logo-twitter-square.png\",\n \"citation_arxiv_id\": \"2308.00352\",\n \"citation_online_date\": \"2023/11/06\",\n \"twitter:image:alt\": \"arXiv logo\",\n \"twitter:site\": \"@arxiv\",\n \"citation_pdf_url\": \"http://arxiv.org/pdf/2308.00352.pdf\",\n \"msapplication-tilecolor\": \"#da532c\",\n \"og:type\": \"website\",\n \"og:image:alt\": \"arXiv logo\",\n \"twitter:title\": \"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework\",\n \"og:title\": \"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework\",\n \"citation_abstract\": \"Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediate results and reduce errors. MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-base\",\n \"og:image:height\": \"700\",\n \"citation_author\": \"Hong, Sirui\",\n \"viewport\": \"width=device-width, initial-scale=1\",\n \"twitter:description\": \"Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple...\",\n \"og:url\": \"https://arxiv.org/abs/2308.00352v5\"\n }\n ],\n \"cse_image\": [\n {\n \"src\": \"https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-one-color-white.svg\"\n }\n ]\n }\n },\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"MetaGPT: Complete Guide to the Best AI Agent Available Right Now ...\",\n \"htmlTitle\": \"\\u003cb\\u003eMetaGPT\\u003c/b\\u003e: Complete Guide to the Best AI Agent Available Right Now ...\",\n \"link\": \"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\n \"displayLink\": \"www.unite.ai\",\n \"snippet\": \"Sep 11, 2023 ... The beauty of MetaGPT lies in its structuring. It capitalizes on meta-programming techniques to manipulate, analyze, and transform code in real- ...\",\n \"htmlSnippet\": \"Sep 11, 2023 \\u003cb\\u003e...\\u003c/b\\u003e The beauty of \\u003cb\\u003eMetaGPT\\u003c/b\\u003e lies in its structuring. It capitalizes on meta-programming techniques to manipulate, analyze, and transform code in real- ...\",\n \"cacheId\": \"qkZULzxVHNAJ\",\n \"formattedUrl\": \"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-...\",\n \"htmlFormattedUrl\": \"https://www.unite.ai/\\u003cb\\u003emetagpt\\u003c/b\\u003e-complete-guide-to-the-best-ai-agent-available-...\",\n \"pagemap\": {\n \"cse_thumbnail\": [\n {\n \"src\": \"https://encrypted-tbn2.gstatic.com/images?q=tbn:ANd9GcSVwf1WWLtVpqJCZ1E_t7TrpSZ7nrwsCUWar6x9YzlOsX1aSH7EGHbkIlY\",\n \"width\": \"290\",\n \"height\": \"174\"\n }\n ],\n \"imageobject\": [\n {\n \"width\": \"1000\",\n \"url\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929-1000x600.png\",\n \"height\": \"600\"\n },\n {\n \"url\": \"https://www.unite.ai/wp-content/uploads/2021/03/logoUNITE230X30BLACK-1.svg\"\n }\n ],\n \"person\": [\n {\n \"name\": \"Aayush Mittal\"\n }\n ],\n \"organization\": [\n {\n \"name\": \"Unite.AI\"\n }\n ],\n \"metatags\": [\n {\n \"og:image\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929-1000x600.png\",\n \"twitter:card\": \"summary\",\n \"article:published_time\": \"2023-09-11T18:03:48+00:00\",\n \"og:image:width\": \"1121\",\n \"og:site_name\": \"Unite.AI\",\n \"twitter:url\": \"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\n \"twitter:label1\": \"Written by\",\n \"twitter:label2\": \"Est. reading time\",\n \"og:image:type\": \"image/png\",\n \"msapplication-tileimage\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929.png\",\n \"og:description\": \"Discover why MetaGPT outperforms AutoGPT, BabyAgi, and other AI agents in complex coding tasks. Our in-depth article guides you through the setup process and provides illustrative examples. Build GPT-powered microapps with a single line of prompt\",\n \"twitter:creator\": \"@UniteAI\",\n \"twitter:image\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929-1000x600.png\",\n \"article:publisher\": \"https://www.facebook.com/uniteai\",\n \"twitter:data1\": \"Aayush Mittal\",\n \"og:image:secure_url\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929.png\",\n \"twitter:data2\": \"9 minutes\",\n \"twitter:site\": \"@UniteAI\",\n \"og:video:type\": \"video/mp4\",\n \"uri-translation\": \"on\",\n \"og:type\": \"article\",\n \"twitter:title\": \"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\n \"og:image:alt\": \"MetaGPBassed Illustration of human and machine collaborationT\",\n \"author\": \"Aayush Mittal\",\n \"og:title\": \"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\n \"og:image:height\": \"628\",\n \"og:updated_time\": \"2023-09-11T14:03:48-04:00\",\n \"article:tag\": \"AI AGENTS\",\n \"og:video\": \"https://www.unite.ai/wp-content/uploads/2023/09/ezgif.com-optimize-online-video-cutter.com_.mp4\",\n \"viewport\": \"width=device-width,initial-scale=1.0,user-scalable=yes\",\n \"og:locale\": \"en_US\",\n \"og:rich_attachment\": \"1\",\n \"og:url\": \"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\"\n }\n ],\n \"cse_image\": [\n {\n \"src\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929-1000x600.png\"\n }\n ],\n \"blogposting\": [\n {\n \"image\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929.png\",\n \"datemodified\": \"2023-09-11T18:03:48+00:00\",\n \"author\": \"Aayush Mittal\",\n \"name\": \"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\n \"description\": \"With Large Language Models (LLMs) like ChatGPT, OpenAI has witnessed a surge in enterprise and user adoption, currently raking in around $80 million in monthly revenue. According to a recent...\",\n \"headline\": \"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\n \"datepublished\": \"2023-09-11\"\n }\n ],\n \"newsarticle\": [\n {\n \"datemodified\": \"2023-09-11\",\n \"keywords\": \"AI AGENTSAutoGPTDockergenerative aiLLMMetaGPTnlpPROMPT ENGINEERINGpython\",\n \"headline\": \"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\n \"datepublished\": \"2023-09-11\"\n }\n ]\n }\n },\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"Thoughts on MetaGPT : r/ProductManagement\",\n \"htmlTitle\": \"Thoughts on \\u003cb\\u003eMetaGPT\\u003c/b\\u003e : r/ProductManagement\",\n \"link\": \"https://www.reddit.com/r/ProductManagement/comments/163vekc/thoughts_on_metagpt/\",\n \"displayLink\": \"www.reddit.com\",\n \"snippet\": \"Aug 28, 2023 ... Thoughts on MetaGPT. YT shorts - a quick summaryExplainer YT video - maynot be the best, but beginner friendly. ... PS: feel free to link more ...\",\n \"htmlSnippet\": \"Aug 28, 2023 \\u003cb\\u003e...\\u003c/b\\u003e Thoughts on \\u003cb\\u003eMetaGPT\\u003c/b\\u003e. YT shorts - a quick summaryExplainer YT video - maynot be the best, but beginner friendly. ... PS: feel free to link more ...\",\n \"cacheId\": \"fDkEZ_skdhcJ\",\n \"formattedUrl\": \"https://www.reddit.com/r/ProductManagement/.../thoughts_on_metagpt/\",\n \"htmlFormattedUrl\": \"https://www.reddit.com/r/ProductManagement/.../thoughts_on_\\u003cb\\u003emetagpt\\u003c/b\\u003e/\",\n \"pagemap\": {\n \"cse_thumbnail\": [\n {\n \"src\": \"https://encrypted-tbn2.gstatic.com/images?q=tbn:ANd9GcSnWudLgGG_2ao_7EWw3EW58JBUQkJ1m4LOHzyiajVHq10p0_TNAeCRlik\",\n \"width\": \"259\",\n \"height\": \"194\"\n }\n ],\n \"metatags\": [\n {\n \"og:image\": \"https://share.redd.it/preview/post/163vekc\",\n \"theme-color\": \"#000000\",\n \"og:image:width\": \"1200\",\n \"og:type\": \"website\",\n \"og:image:alt\": \"An image containing a preview of the post\",\n \"twitter:card\": \"summary_large_image\",\n \"twitter:title\": \"r/ProductManagement on Reddit: Thoughts on MetaGPT\",\n \"og:site_name\": \"Reddit\",\n \"og:title\": \"r/ProductManagement on Reddit: Thoughts on MetaGPT\",\n \"og:image:height\": \"630\",\n \"msapplication-navbutton-color\": \"#000000\",\n \"og:description\": \"Posted by u/CheraCholan - No votes and 4 comments\",\n \"twitter:image\": \"https://share.redd.it/preview/post/163vekc\",\n \"apple-mobile-web-app-status-bar-style\": \"black\",\n \"twitter:site\": \"@reddit\",\n \"viewport\": \"width=device-width, initial-scale=1, viewport-fit=cover\",\n \"apple-mobile-web-app-capable\": \"yes\",\n \"og:ttl\": \"600\",\n \"og:url\": \"https://www.reddit.com/r/ProductManagement/comments/163vekc/thoughts_on_metagpt/\"\n }\n ],\n \"cse_image\": [\n {\n \"src\": \"https://external-preview.redd.it/thoughts-on-metagpt-v0-VQP3cNl_-L2zHMe4QWMy1GTBsiLHKNj0lg-u_o_nZug.jpg?auto=webp&s=03900a2b49a801e7d769a0ae8d2ec7a05011c1fc\"\n }\n ]\n }\n },\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"MetaGPT: Meta Programming for Multi-Agent Collaborative ...\",\n \"htmlTitle\": \"\\u003cb\\u003eMetaGPT\\u003c/b\\u003e: Meta Programming for Multi-Agent Collaborative ...\",\n \"link\": \"https://news.ycombinator.com/item?id=37076125\",\n \"displayLink\": \"news.ycombinator.com\",\n \"snippet\": \"You can use multiple agents, or split a lot of information across multiple requests to one agent. The result is the same. Some problems require a full ...\",\n \"htmlSnippet\": \"You can use multiple agents, or split a lot of information across multiple requests to one agent. The result is the same. Some problems require a full ...\",\n \"cacheId\": \"PvjWUfqo0GAJ\",\n \"formattedUrl\": \"https://news.ycombinator.com/item?id=37076125\",\n \"htmlFormattedUrl\": \"https://news.ycombinator.com/item?id=37076125\",\n \"pagemap\": {\n \"metatags\": [\n {\n \"referrer\": \"origin\",\n \"viewport\": \"width=device-width, initial-scale=1.0\"\n }\n ]\n }\n },\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"MetaGPT: a Multi-Agent Framework to Automate Your Software ...\",\n \"htmlTitle\": \"\\u003cb\\u003eMetaGPT\\u003c/b\\u003e: a Multi-Agent Framework to Automate Your Software ...\",\n \"link\": \"https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-to-automate-your-software-company-4b6ae747cc36\",\n \"displayLink\": \"medium.datadriveninvestor.com\",\n \"snippet\": \"MetaGPT is about to reach 10000 stars on Github. It's a Multi-Agent Framework that can behave as an engineer, product manager, architect, project managers.\",\n \"htmlSnippet\": \"\\u003cb\\u003eMetaGPT\\u003c/b\\u003e is about to reach 10000 stars on Github. It's a Multi-Agent Framework that can behave as an engineer, product manager, architect, project managers.\",\n \"cacheId\": \"qWqvRF7SoGsJ\",\n \"formattedUrl\": \"https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-t...\",\n \"htmlFormattedUrl\": \"https://medium.datadriveninvestor.com/\\u003cb\\u003emetagpt\\u003c/b\\u003e-a-multi-agent-framework-t...\",\n \"pagemap\": {\n \"cse_thumbnail\": [\n {\n \"src\": \"https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRKDyUf8JumEvosQ1ZmxQ1dGmOGIx1jd4bvnICexOb2jFmKZHKagMGoQ0xI\",\n \"width\": \"242\",\n \"height\": \"209\"\n }\n ],\n \"metatags\": [\n {\n \"og:image\": \"https://miro.medium.com/v2/da:true/resize:fit:1200/0*g2b2hbP8HykGIIN3\",\n \"twitter:app:url:iphone\": \"medium://p/4b6ae747cc36\",\n \"theme-color\": \"#000000\",\n \"article:published_time\": \"2023-09-05T05:20:30.732Z\",\n \"twitter:card\": \"summary_large_image\",\n \"og:site_name\": \"Medium\",\n \"al:android:package\": \"com.medium.reader\",\n \"twitter:label1\": \"Reading time\",\n \"twitter:tile:template:testing\": \"2\",\n \"twitter:app:id:iphone\": \"828256236\",\n \"title\": \"MetaGPT: a Multi-Agent Framework to Automate Your Software Company | by Peter Xing | DataDrivenInvestor\",\n \"al:ios:url\": \"medium://p/4b6ae747cc36\",\n \"og:description\": \"MetaGPT is about to reach 10,000 stars on Github. It’s a Multi-Agent Framework that can behave as an engineer, product manager, architect…\",\n \"twitter:creator\": \"@peterxing\",\n \"al:ios:app_store_id\": \"828256236\",\n \"twitter:data1\": \"2 min read\",\n \"twitter:site\": \"@DDInvestorHQ\",\n \"twitter:tile:info1:text\": \"Peter Xing\",\n \"twitter:tile:info1:icon\": \"Person\",\n \"og:type\": \"article\",\n \"twitter:title\": \"MetaGPT: a Multi-Agent Framework to Automate Your Software Company\",\n \"al:ios:app_name\": \"Medium\",\n \"twitter:cta\": \"Read on Medium\",\n \"author\": \"Peter Xing\",\n \"og:title\": \"MetaGPT: a Multi-Agent Framework to Automate Your Software Company\",\n \"al:web:url\": \"https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-to-automate-your-software-company-4b6ae747cc36\",\n \"article:author\": \"https://medium.com/@peterxing\",\n \"twitter:tile:info2:text\": \"Sep 4, 2023\",\n \"twitter:image:src\": \"https://miro.medium.com/v2/da:true/resize:fit:1200/0*g2b2hbP8HykGIIN3\",\n \"al:android:url\": \"medium://p/4b6ae747cc36\",\n \"referrer\": \"unsafe-url\",\n \"fb:app_id\": \"542599432471018\",\n \"viewport\": \"width=device-width,minimum-scale=1,initial-scale=1,maximum-scale=1\",\n \"twitter:tile:info2:icon\": \"Calendar\",\n \"twitter:description\": \"MetaGPT is about to reach 10,000 stars on Github. It’s a Multi-Agent Framework that can behave as an engineer, product manager, architect…\",\n \"twitter:tile:image\": \"https://miro.medium.com/v2/da:true/resize:fit:1200/0*g2b2hbP8HykGIIN3\",\n \"og:url\": \"https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-to-automate-your-software-company-4b6ae747cc36\",\n \"twitter:app:name:iphone\": \"Medium\",\n \"al:android:app_name\": \"Medium\"\n }\n ],\n \"cse_image\": [\n {\n \"src\": \"https://miro.medium.com/v2/da:true/resize:fit:1200/0*g2b2hbP8HykGIIN3\"\n }\n ]\n }\n },\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"MetaGPT - ChatGPT\",\n \"htmlTitle\": \"MetaGPT - ChatGPT\",\n \"link\": \"https://chat.openai.com/g/g-gHceUPFhE-metagpt\",\n \"displayLink\": \"chat.openai.com\",\n \"snippet\": \"GPT. MetaGPT. Crafts specialized prompts for diverse GPT applications. By Ankit Pal. Sign up to chat. Requires ChatGPT Plus.\",\n \"htmlSnippet\": \"GPT. \\u003cb\\u003eMetaGPT\\u003c/b\\u003e. Crafts specialized prompts for diverse GPT applications. By Ankit Pal. Sign up to chat. Requires ChatGPT Plus.\",\n \"cacheId\": \"xhG1ItzjqPQJ\",\n \"formattedUrl\": \"https://chat.openai.com/g/g-gHceUPFhE-metagpt\",\n \"htmlFormattedUrl\": \"https://chat.openai.com/g/g-gHceUPFhE-\\u003cb\\u003emetagpt\\u003c/b\\u003e\",\n \"pagemap\": {\n \"metatags\": [\n {\n \"apple-itunes-app\": \"app-id=6448311069\",\n \"og:image\": \"https://files.oaiusercontent.com/file-pZO1spqW9XBbl6yhFEVA1xni?se=2123-10-18T23%3A51%3A44Z&sp=r&sv=2021-08-06&sr=b&rscc=max-age%3D31536000%2C%20immutable&rscd=attachment%3B%20filename%3Df77c7fb5-1ba1-487b-b610-19db286e62ab.png&sig=nPfDFuFwLLYoWGUotoX8wZ7mbXNRwg2wcIyXGpE19k0%3D\",\n \"og:type\": \"website\",\n \"og:image:width\": \"512\",\n \"og:site_name\": \"ChatGPT\",\n \"og:title\": \"ChatGPT - MetaGPT\",\n \"og:image:height\": \"512\",\n \"title\": \"ChatGPT - MetaGPT\",\n \"og:description\": \"Crafts specialized prompts for diverse GPT applications\",\n \"next-head-count\": \"21\",\n \"viewport\": \"width=device-width, initial-scale=1\",\n \"react-scroll-to-bottom:version\": \"4.2.0\",\n \"og:url\": \"/g/g-gHceUPFhE-metagpt\"\n }\n ],\n \"cse_image\": [\n {\n \"src\": \"https://files.oaiusercontent.com/file-pZO1spqW9XBbl6yhFEVA1xni?se=2123-10-18T23%3A51%3A44Z&sp=r&sv=2021-08-06&sr=b&rscc=max-age%3D31536000%2C%20immutable&rscd=attachment%3B%20filename%3Df77c7fb5-1ba1-487b-b610-19db286e62ab.png&sig=nPfDFuFwLLYoWGUotoX8wZ7mbXNRwg2wcIyXGpE19k0%3D\"\n }\n ]\n }\n },\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"pip - Issue installing metagpt on Python 3.11 on Windows - Stack ...\",\n \"htmlTitle\": \"pip - Issue installing \\u003cb\\u003emetagpt\\u003c/b\\u003e on Python 3.11 on Windows - Stack ...\",\n \"link\": \"https://stackoverflow.com/questions/76871577/issue-installing-metagpt-on-python-3-11-on-windows\",\n \"displayLink\": \"stackoverflow.com\",\n \"snippet\": \"Aug 9, 2023 ... 1 Answer 1 · try to delete the file 'metagpt-0.1-py3.11.egg', and try again. · if still not work , you can use pip install -r requirements.txt ...\",\n \"htmlSnippet\": \"Aug 9, 2023 \\u003cb\\u003e...\\u003c/b\\u003e 1 Answer 1 · try to delete the file '\\u003cb\\u003emetagpt\\u003c/b\\u003e-0.1-py3.11.egg', and try again. · if still not work , you can use pip install -r requirements.txt ...\",\n \"cacheId\": \"rE7h8ENZAfsJ\",\n \"formattedUrl\": \"https://stackoverflow.com/.../issue-installing-metagpt-on-python-3-11-on-w...\",\n \"htmlFormattedUrl\": \"https://stackoverflow.com/.../issue-installing-\\u003cb\\u003emetagpt\\u003c/b\\u003e-on-python-3-11-on-w...\",\n \"pagemap\": {\n \"cse_thumbnail\": [\n {\n \"src\": \"https://encrypted-tbn2.gstatic.com/images?q=tbn:ANd9GcQYl7zuT3cw_BBRAyhdQEbQuBgqdNHXKHIYKL8S8ly8x9L_XA9sdwSmiHs\",\n \"width\": \"225\",\n \"height\": \"225\"\n }\n ],\n \"qapage\": [\n {\n \"image\": \"https://cdn.sstatic.net/Sites/stackoverflow/Img/apple-touch-icon@2.png?v=73d79a89bded\",\n \"primaryimageofpage\": \"https://cdn.sstatic.net/Sites/stackoverflow/Img/apple-touch-icon@2.png?v=73d79a89bded\",\n \"name\": \"Issue installing metagpt on Python 3.11 on Windows\",\n \"description\": \"I receives this error when trying to install metagpt packages: [WinError 32] The process cannot access the file because it is being used by another process: 'c:\\\\\\\\users\\\\\\\\anthony phan\\\\\\\\appdata\\\\\\\\local\\\\\\\\\"\n }\n ],\n \"question\": [\n {\n \"image\": \"https://cdn.sstatic.net/Sites/stackoverflow/Img/apple-touch-icon.png?v=c78bd457575a\",\n \"upvotecount\": \"1\",\n \"answercount\": \"1\",\n \"name\": \"Issue installing metagpt on Python 3.11 on Windows\",\n \"datecreated\": \"2023-08-09T22:10:59\",\n \"text\": \"I receives this error when trying to install metagpt packages: [WinError 32] The process cannot access the file because it is being used by another process: 'c:\\\\\\\\users\\\\\\\\anthony phan\\\\\\\\appdata\\\\\\\\local...\",\n \"url\": \"Share\"\n }\n ],\n \"answer\": [\n {\n \"upvotecount\": \"0\",\n \"text\": \"try to delete the file 'metagpt-0.1-py3.11.egg', and try again. if still not work , you can use pip install -r requirements.txt instead of python setup.py\",\n \"datecreated\": \"2023-08-30T02:04:27\",\n \"url\": \"Share\"\n }\n ],\n \"person\": [\n {\n \"name\": \"Anthony Q Phan\"\n },\n {\n \"name\": \"D yesfir\"\n }\n ],\n \"metatags\": [\n {\n \"og:image\": \"https://cdn.sstatic.net/Sites/stackoverflow/Img/apple-touch-icon@2.png?v=73d79a89bded\",\n \"og:type\": \"website\",\n \"twitter:card\": \"summary\",\n \"twitter:title\": \"Issue installing metagpt on Python 3.11 on Windows\",\n \"og:site_name\": \"Stack Overflow\",\n \"twitter:domain\": \"stackoverflow.com\",\n \"viewport\": \"width=device-width, height=device-height, initial-scale=1.0, minimum-scale=1.0\",\n \"twitter:description\": \"I receives this error when trying to install metagpt packages:\\n[WinError 32] The process cannot access the file because it is being used by another process: 'c:\\\\\\\\users\\\\\\\\anthony phan\\\\\\\\appdata\\\\\\\\local\\\\\\\\\",\n \"og:url\": \"https://stackoverflow.com/questions/76871577/issue-installing-metagpt-on-python-3-11-on-windows\"\n }\n ],\n \"cse_image\": [\n {\n \"src\": \"https://cdn.sstatic.net/Sites/stackoverflow/Img/apple-touch-icon@2.png?v=73d79a89bded\"\n }\n ]\n }\n }\n ]\n}\n", + "httplib2-GET-https://customsearch.googleapis.com/customsearch/v1-{\"params\": {\"q\": \"metagpt\", \"num\": \"6\", \"cx\": \"mock-google-cse\", \"key\": \"mock-google-key\", \"alt\": \"json\"}}": "{\n \"kind\": \"customsearch#search\",\n \"url\": {\n \"type\": \"application/json\",\n \"template\": \"https://www.googleapis.com/customsearch/v1?q={searchTerms}&num={count?}&start={startIndex?}&lr={language?}&safe={safe?}&cx={cx?}&sort={sort?}&filter={filter?}&gl={gl?}&cr={cr?}&googlehost={googleHost?}&c2coff={disableCnTwTranslation?}&hq={hq?}&hl={hl?}&siteSearch={siteSearch?}&siteSearchFilter={siteSearchFilter?}&exactTerms={exactTerms?}&excludeTerms={excludeTerms?}&linkSite={linkSite?}&orTerms={orTerms?}&dateRestrict={dateRestrict?}&lowRange={lowRange?}&highRange={highRange?}&searchType={searchType}&fileType={fileType?}&rights={rights?}&imgSize={imgSize?}&imgType={imgType?}&imgColorType={imgColorType?}&imgDominantColor={imgDominantColor?}&alt=json\"\n },\n \"queries\": {\n \"request\": [\n {\n \"title\": \"Google Custom Search - metagpt\",\n \"totalResults\": \"85300\",\n \"searchTerms\": \"metagpt\",\n \"count\": 6,\n \"startIndex\": 1,\n \"inputEncoding\": \"utf8\",\n \"outputEncoding\": \"utf8\",\n \"safe\": \"off\",\n \"cx\": \"mock-google-cse\"\n }\n ],\n \"nextPage\": [\n {\n \"title\": \"Google Custom Search - metagpt\",\n \"totalResults\": \"85300\",\n \"searchTerms\": \"metagpt\",\n \"count\": 6,\n \"startIndex\": 7,\n \"inputEncoding\": \"utf8\",\n \"outputEncoding\": \"utf8\",\n \"safe\": \"off\",\n \"cx\": \"mock-google-cse\"\n }\n ]\n },\n \"context\": {\n \"title\": \"metagpt1\"\n },\n \"searchInformation\": {\n \"searchTime\": 0.193417,\n \"formattedSearchTime\": \"0.19\",\n \"totalResults\": \"85300\",\n \"formattedTotalResults\": \"85,300\"\n },\n \"items\": [\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"geekan/MetaGPT: The Multi-Agent Framework: Given one ... - GitHub\",\n \"htmlTitle\": \"geekan/MetaGPT: The Multi-Agent Framework: Given one ... - GitHub\",\n \"link\": \"https://github.com/geekan/MetaGPT\",\n \"displayLink\": \"github.com\",\n \"snippet\": \"The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo - GitHub - geekan/MetaGPT: The Multi-Agent Framework: Given one ...\",\n \"htmlSnippet\": \"The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo - GitHub - geekan/\\u003cb\\u003eMetaGPT\\u003c/b\\u003e: The Multi-Agent Framework: Given one ...\",\n \"cacheId\": \"gsshb0APPNgJ\",\n \"formattedUrl\": \"https://github.com/geekan/MetaGPT\",\n \"htmlFormattedUrl\": \"https://github.com/geekan/\\u003cb\\u003eMetaGPT\\u003c/b\\u003e\",\n \"pagemap\": {\n \"cse_thumbnail\": [\n {\n \"src\": \"https://encrypted-tbn1.gstatic.com/images?q=tbn:ANd9GcRuD8YUvRcltmdoxKyuIbt8UZhg3LE5mwNX7KPXDB15YIJRKdT2m5JiweuS\",\n \"width\": \"318\",\n \"height\": \"159\"\n }\n ],\n \"softwaresourcecode\": [\n {\n \"author\": \"geekan\",\n \"name\": \"MetaGPT\",\n \"text\": \"MetaGPT: The Multi-Agent Framework Assign different roles to GPTs to form a collaborative software entity for complex tasks. MetaGPT takes a one line requirement as input and outputs user stories...\"\n }\n ],\n \"metatags\": [\n {\n \"octolytics-url\": \"https://collector.github.com/github/collect\",\n \"apple-itunes-app\": \"app-id=1477376905, app-argument=https://github.com/geekan/MetaGPT\",\n \"og:image\": \"https://opengraph.githubassets.com/6178eb2aa6711c676eafc956e52345e71225c58cd0a666b54871171e847c0905/geekan/MetaGPT\",\n \"twitter:card\": \"summary_large_image\",\n \"og:image:width\": \"1200\",\n \"theme-color\": \"#1e2327\",\n \"og:site_name\": \"GitHub\",\n \"hovercard-subject-tag\": \"repository:660551251\",\n \"turbo-body-classes\": \"logged-out env-production page-responsive\",\n \"html-safe-nonce\": \"a6964edcf12c9ea83de0bf16db8105c60333287597018548250a0fa92b93d3f9\",\n \"expected-hostname\": \"github.com\",\n \"og:description\": \"🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo - GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Task...\",\n \"browser-errors-url\": \"https://api.github.com/_private/browser/errors\",\n \"octolytics-dimension-user_login\": \"geekan\",\n \"hostname\": \"github.com\",\n \"twitter:site\": \"@github\",\n \"browser-stats-url\": \"https://api.github.com/_private/browser/stats\",\n \"route-pattern\": \"/:user_id/:repository\",\n \"visitor-payload\": \"eyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJBNjIxOjk2OUU6OTZERjlEQzpEM0UxM0RFOjY1QTNBQjU0IiwidmlzaXRvcl9pZCI6IjU2ODA2NDI2MDQ0ODY5MzA3NyIsInJlZ2lvbl9lZGdlIjoiaWFkIiwicmVnaW9uX3JlbmRlciI6ImlhZCJ9\",\n \"github-keyboard-shortcuts\": \"repository\",\n \"octolytics-dimension-repository_id\": \"660551251\",\n \"octolytics-dimension-repository_network_root_nwo\": \"geekan/MetaGPT\",\n \"twitter:title\": \"GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo\",\n \"og:image:alt\": \"🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo - GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Task...\",\n \"og:type\": \"object\",\n \"optimizely-datafile\": \"{\\\"accountId\\\": \\\"16737760170\\\", \\\"projectId\\\": \\\"16737760170\\\", \\\"revision\\\": \\\"23\\\", \\\"attributes\\\": [{\\\"id\\\": \\\"16822470375\\\", \\\"key\\\": \\\"user_id\\\"}, {\\\"id\\\": \\\"17143601254\\\", \\\"key\\\": \\\"spammy\\\"}, {\\\"id\\\": \\\"18175660309\\\", \\\"key\\\": \\\"organization_plan\\\"}, {\\\"id\\\": \\\"18813001570\\\", \\\"key\\\": \\\"is_logged_in\\\"}, {\\\"id\\\": \\\"19073851829\\\", \\\"key\\\": \\\"geo\\\"}, {\\\"id\\\": \\\"20175462351\\\", \\\"key\\\": \\\"requestedCurrency\\\"}, {\\\"id\\\": \\\"20785470195\\\", \\\"key\\\": \\\"country_code\\\"}, {\\\"id\\\": \\\"21656311196\\\", \\\"key\\\": \\\"opened_downgrade_dialog\\\"}], \\\"audiences\\\": [{\\\"id\\\": \\\"$opt_dummy_audience\\\", \\\"name\\\": \\\"Optimizely-Generated Audience for Backwards Compatibility\\\", \\\"conditions\\\": \\\"[\\\\\\\"or\\\\\\\", {\\\\\\\"match\\\\\\\": \\\\\\\"exact\\\\\\\", \\\\\\\"name\\\\\\\": \\\\\\\"$opt_dummy_attribute\\\\\\\", \\\\\\\"type\\\\\\\": \\\\\\\"custom_attribute\\\\\\\", \\\\\\\"value\\\\\\\": \\\\\\\"$opt_dummy_value\\\\\\\"}]\\\"}], \\\"version\\\": \\\"4\\\", \\\"events\\\": [{\\\"id\\\": \\\"18188530140\\\", \\\"experimentIds\\\": [], \\\"key\\\": \\\"test_event\\\"}], \\\"integrations\\\": [], \\\"anonymizeIP\\\": true, \\\"botFiltering\\\": false, \\\"typedAudiences\\\": [], \\\"variables\\\": [], \\\"environmentKey\\\": \\\"production\\\", \\\"sdkKey\\\": \\\"UpVyJZaLVEGwJPQWf5pAD\\\", \\\"featureFlags\\\": [], \\\"rollouts\\\": [],\",\n \"og:title\": \"GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo\",\n \"visitor-hmac\": \"471691c5f7e3204061bb09c630c440708f5c08a2824d60b0f28eea873d474cd7\",\n \"og:image:height\": \"600\",\n \"turbo-cache-control\": \"no-preview\",\n \"request-id\": \"A621:969E:96DF9DC:D3E13DE:65A3AB54\",\n \"analytics-location\": \"/\\u003cuser-name\\u003e/\\u003crepo-name\\u003e\",\n \"color-scheme\": \"light dark\",\n \"octolytics-dimension-repository_is_fork\": \"false\",\n \"go-import\": \"github.com/geekan/MetaGPT git https://github.com/geekan/MetaGPT.git\",\n \"browser-optimizely-client-errors-url\": \"https://api.github.com/_private/browser/optimizely_client/errors\",\n \"twitter:image:src\": \"https://opengraph.githubassets.com/6178eb2aa6711c676eafc956e52345e71225c58cd0a666b54871171e847c0905/geekan/MetaGPT\",\n \"octolytics-dimension-user_id\": \"2707039\",\n \"octolytics-dimension-repository_public\": \"true\",\n \"fb:app_id\": \"1401488693436528\",\n \"octolytics-dimension-repository_network_root_id\": \"660551251\",\n \"octolytics-dimension-repository_nwo\": \"geekan/MetaGPT\",\n \"viewport\": \"width=device-width\",\n \"twitter:description\": \"🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo - GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Task...\",\n \"current-catalog-service-hash\": \"82c569b93da5c18ed649ebd4c2c79437db4611a6a1373e805a3cb001c64130b7\",\n \"og:url\": \"https://github.com/geekan/MetaGPT\"\n }\n ],\n \"cse_image\": [\n {\n \"src\": \"https://opengraph.githubassets.com/6178eb2aa6711c676eafc956e52345e71225c58cd0a666b54871171e847c0905/geekan/MetaGPT\"\n }\n ]\n }\n },\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"[2308.00352] MetaGPT: Meta Programming for A Multi-Agent ...\",\n \"htmlTitle\": \"[2308.00352] \\u003cb\\u003eMetaGPT\\u003c/b\\u003e: Meta Programming for A Multi-Agent ...\",\n \"link\": \"https://arxiv.org/abs/2308.00352\",\n \"displayLink\": \"arxiv.org\",\n \"snippet\": \"Aug 1, 2023 ... Computer Science \\u003e Artificial Intelligence · Title:MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework · Bibliographic and ...\",\n \"htmlSnippet\": \"Aug 1, 2023 \\u003cb\\u003e...\\u003c/b\\u003e Computer Science > Artificial Intelligence · Title:\\u003cb\\u003eMetaGPT\\u003c/b\\u003e: Meta Programming for A Multi-Agent Collaborative Framework · Bibliographic and ...\",\n \"cacheId\": \"8_tddNY0jEYJ\",\n \"formattedUrl\": \"https://arxiv.org/abs/2308.00352\",\n \"htmlFormattedUrl\": \"https://arxiv.org/abs/2308.00352\",\n \"pagemap\": {\n \"cse_thumbnail\": [\n {\n \"src\": \"https://encrypted-tbn3.gstatic.com/images?q=tbn:ANd9GcStsc5IszP_UC7vkymrk7PhjHGOFQhTh862xtJcQkxDem2IteJQXpob6_Vb\",\n \"width\": \"336\",\n \"height\": \"150\"\n }\n ],\n \"metatags\": [\n {\n \"og:image\": \"/static/browse/0.3.4/images/arxiv-logo-fb.png\",\n \"theme-color\": \"#ffffff\",\n \"og:image:width\": \"1200\",\n \"twitter:card\": \"summary\",\n \"citation_title\": \"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework\",\n \"og:site_name\": \"arXiv.org\",\n \"citation_date\": \"2023/08/01\",\n \"og:description\": \"Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediate results and reduce errors. MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-base\",\n \"og:image:secure_url\": \"/static/browse/0.3.4/images/arxiv-logo-fb.png\",\n \"twitter:image\": \"https://static.arxiv.org/icons/twitter/arxiv-logo-twitter-square.png\",\n \"citation_arxiv_id\": \"2308.00352\",\n \"citation_online_date\": \"2023/11/06\",\n \"twitter:image:alt\": \"arXiv logo\",\n \"twitter:site\": \"@arxiv\",\n \"citation_pdf_url\": \"http://arxiv.org/pdf/2308.00352.pdf\",\n \"msapplication-tilecolor\": \"#da532c\",\n \"og:type\": \"website\",\n \"og:image:alt\": \"arXiv logo\",\n \"twitter:title\": \"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework\",\n \"og:title\": \"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework\",\n \"citation_abstract\": \"Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediate results and reduce errors. MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-base\",\n \"og:image:height\": \"700\",\n \"citation_author\": \"Hong, Sirui\",\n \"viewport\": \"width=device-width, initial-scale=1\",\n \"twitter:description\": \"Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple...\",\n \"og:url\": \"https://arxiv.org/abs/2308.00352v5\"\n }\n ],\n \"cse_image\": [\n {\n \"src\": \"https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-one-color-white.svg\"\n }\n ]\n }\n },\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"MetaGPT: Complete Guide to the Best AI Agent Available Right Now ...\",\n \"htmlTitle\": \"\\u003cb\\u003eMetaGPT\\u003c/b\\u003e: Complete Guide to the Best AI Agent Available Right Now ...\",\n \"link\": \"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\n \"displayLink\": \"www.unite.ai\",\n \"snippet\": \"Sep 11, 2023 ... The beauty of MetaGPT lies in its structuring. It capitalizes on meta-programming techniques to manipulate, analyze, and transform code in real- ...\",\n \"htmlSnippet\": \"Sep 11, 2023 \\u003cb\\u003e...\\u003c/b\\u003e The beauty of \\u003cb\\u003eMetaGPT\\u003c/b\\u003e lies in its structuring. It capitalizes on meta-programming techniques to manipulate, analyze, and transform code in real- ...\",\n \"cacheId\": \"qkZULzxVHNAJ\",\n \"formattedUrl\": \"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-...\",\n \"htmlFormattedUrl\": \"https://www.unite.ai/\\u003cb\\u003emetagpt\\u003c/b\\u003e-complete-guide-to-the-best-ai-agent-available-...\",\n \"pagemap\": {\n \"cse_thumbnail\": [\n {\n \"src\": \"https://encrypted-tbn2.gstatic.com/images?q=tbn:ANd9GcSVwf1WWLtVpqJCZ1E_t7TrpSZ7nrwsCUWar6x9YzlOsX1aSH7EGHbkIlY\",\n \"width\": \"290\",\n \"height\": \"174\"\n }\n ],\n \"imageobject\": [\n {\n \"width\": \"1000\",\n \"url\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929-1000x600.png\",\n \"height\": \"600\"\n },\n {\n \"url\": \"https://www.unite.ai/wp-content/uploads/2021/03/logoUNITE230X30BLACK-1.svg\"\n }\n ],\n \"person\": [\n {\n \"name\": \"Aayush Mittal\"\n }\n ],\n \"organization\": [\n {\n \"name\": \"Unite.AI\"\n }\n ],\n \"metatags\": [\n {\n \"og:image\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929-1000x600.png\",\n \"twitter:card\": \"summary\",\n \"article:published_time\": \"2023-09-11T18:03:48+00:00\",\n \"og:image:width\": \"1121\",\n \"og:site_name\": \"Unite.AI\",\n \"twitter:url\": \"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\n \"twitter:label1\": \"Written by\",\n \"twitter:label2\": \"Est. reading time\",\n \"og:image:type\": \"image/png\",\n \"msapplication-tileimage\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929.png\",\n \"og:description\": \"Discover why MetaGPT outperforms AutoGPT, BabyAgi, and other AI agents in complex coding tasks. Our in-depth article guides you through the setup process and provides illustrative examples. Build GPT-powered microapps with a single line of prompt\",\n \"twitter:creator\": \"@UniteAI\",\n \"twitter:image\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929-1000x600.png\",\n \"article:publisher\": \"https://www.facebook.com/uniteai\",\n \"twitter:data1\": \"Aayush Mittal\",\n \"og:image:secure_url\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929.png\",\n \"twitter:data2\": \"9 minutes\",\n \"twitter:site\": \"@UniteAI\",\n \"og:video:type\": \"video/mp4\",\n \"uri-translation\": \"on\",\n \"og:type\": \"article\",\n \"twitter:title\": \"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\n \"og:image:alt\": \"MetaGPBassed Illustration of human and machine collaborationT\",\n \"author\": \"Aayush Mittal\",\n \"og:title\": \"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\n \"og:image:height\": \"628\",\n \"og:updated_time\": \"2023-09-11T14:03:48-04:00\",\n \"article:tag\": \"AI AGENTS\",\n \"og:video\": \"https://www.unite.ai/wp-content/uploads/2023/09/ezgif.com-optimize-online-video-cutter.com_.mp4\",\n \"viewport\": \"width=device-width,initial-scale=1.0,user-scalable=yes\",\n \"og:locale\": \"en_US\",\n \"og:rich_attachment\": \"1\",\n \"og:url\": \"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\"\n }\n ],\n \"cse_image\": [\n {\n \"src\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929-1000x600.png\"\n }\n ],\n \"blogposting\": [\n {\n \"image\": \"https://www.unite.ai/wp-content/uploads/2023/09/Heisenbergforlife_Center_the_scene_in_zoomed_scope_around_a_hum_7f069632-eda5-4edd-858b-cb44fec82929.png\",\n \"datemodified\": \"2023-09-11T18:03:48+00:00\",\n \"author\": \"Aayush Mittal\",\n \"name\": \"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\n \"description\": \"With Large Language Models (LLMs) like ChatGPT, OpenAI has witnessed a surge in enterprise and user adoption, currently raking in around $80 million in monthly revenue. According to a recent...\",\n \"headline\": \"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\n \"datepublished\": \"2023-09-11\"\n }\n ],\n \"newsarticle\": [\n {\n \"datemodified\": \"2023-09-11\",\n \"keywords\": \"AI AGENTSAutoGPTDockergenerative aiLLMMetaGPTnlpPROMPT ENGINEERINGpython\",\n \"headline\": \"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\n \"datepublished\": \"2023-09-11\"\n }\n ]\n }\n },\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"Thoughts on MetaGPT : r/ProductManagement\",\n \"htmlTitle\": \"Thoughts on \\u003cb\\u003eMetaGPT\\u003c/b\\u003e : r/ProductManagement\",\n \"link\": \"https://www.reddit.com/r/ProductManagement/comments/163vekc/thoughts_on_metagpt/\",\n \"displayLink\": \"www.reddit.com\",\n \"snippet\": \"Aug 28, 2023 ... Thoughts on MetaGPT. YT shorts - a quick summaryExplainer YT video - maynot be the best, but beginner friendly. ... PS: feel free to link more ...\",\n \"htmlSnippet\": \"Aug 28, 2023 \\u003cb\\u003e...\\u003c/b\\u003e Thoughts on \\u003cb\\u003eMetaGPT\\u003c/b\\u003e. YT shorts - a quick summaryExplainer YT video - maynot be the best, but beginner friendly. ... PS: feel free to link more ...\",\n \"cacheId\": \"fDkEZ_skdhcJ\",\n \"formattedUrl\": \"https://www.reddit.com/r/ProductManagement/.../thoughts_on_metagpt/\",\n \"htmlFormattedUrl\": \"https://www.reddit.com/r/ProductManagement/.../thoughts_on_\\u003cb\\u003emetagpt\\u003c/b\\u003e/\",\n \"pagemap\": {\n \"cse_thumbnail\": [\n {\n \"src\": \"https://encrypted-tbn2.gstatic.com/images?q=tbn:ANd9GcSnWudLgGG_2ao_7EWw3EW58JBUQkJ1m4LOHzyiajVHq10p0_TNAeCRlik\",\n \"width\": \"259\",\n \"height\": \"194\"\n }\n ],\n \"metatags\": [\n {\n \"og:image\": \"https://share.redd.it/preview/post/163vekc\",\n \"theme-color\": \"#000000\",\n \"og:image:width\": \"1200\",\n \"og:type\": \"website\",\n \"og:image:alt\": \"An image containing a preview of the post\",\n \"twitter:card\": \"summary_large_image\",\n \"twitter:title\": \"r/ProductManagement on Reddit: Thoughts on MetaGPT\",\n \"og:site_name\": \"Reddit\",\n \"og:title\": \"r/ProductManagement on Reddit: Thoughts on MetaGPT\",\n \"og:image:height\": \"630\",\n \"msapplication-navbutton-color\": \"#000000\",\n \"og:description\": \"Posted by u/CheraCholan - No votes and 4 comments\",\n \"twitter:image\": \"https://share.redd.it/preview/post/163vekc\",\n \"apple-mobile-web-app-status-bar-style\": \"black\",\n \"twitter:site\": \"@reddit\",\n \"viewport\": \"width=device-width, initial-scale=1, viewport-fit=cover\",\n \"apple-mobile-web-app-capable\": \"yes\",\n \"og:ttl\": \"600\",\n \"og:url\": \"https://www.reddit.com/r/ProductManagement/comments/163vekc/thoughts_on_metagpt/\"\n }\n ],\n \"cse_image\": [\n {\n \"src\": \"https://external-preview.redd.it/thoughts-on-metagpt-v0-VQP3cNl_-L2zHMe4QWMy1GTBsiLHKNj0lg-u_o_nZug.jpg?auto=webp&s=03900a2b49a801e7d769a0ae8d2ec7a05011c1fc\"\n }\n ]\n }\n },\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"MetaGPT: Meta Programming for Multi-Agent Collaborative ...\",\n \"htmlTitle\": \"\\u003cb\\u003eMetaGPT\\u003c/b\\u003e: Meta Programming for Multi-Agent Collaborative ...\",\n \"link\": \"https://news.ycombinator.com/item?id=37076125\",\n \"displayLink\": \"news.ycombinator.com\",\n \"snippet\": \"You can use multiple agents, or split a lot of information across multiple requests to one agent. The result is the same. Some problems require a full ...\",\n \"htmlSnippet\": \"You can use multiple agents, or split a lot of information across multiple requests to one agent. The result is the same. Some problems require a full ...\",\n \"cacheId\": \"PvjWUfqo0GAJ\",\n \"formattedUrl\": \"https://news.ycombinator.com/item?id=37076125\",\n \"htmlFormattedUrl\": \"https://news.ycombinator.com/item?id=37076125\",\n \"pagemap\": {\n \"metatags\": [\n {\n \"referrer\": \"origin\",\n \"viewport\": \"width=device-width, initial-scale=1.0\"\n }\n ]\n }\n },\n {\n \"kind\": \"customsearch#result\",\n \"title\": \"MetaGPT: a Multi-Agent Framework to Automate Your Software ...\",\n \"htmlTitle\": \"\\u003cb\\u003eMetaGPT\\u003c/b\\u003e: a Multi-Agent Framework to Automate Your Software ...\",\n \"link\": \"https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-to-automate-your-software-company-4b6ae747cc36\",\n \"displayLink\": \"medium.datadriveninvestor.com\",\n \"snippet\": \"MetaGPT is about to reach 10000 stars on Github. It's a Multi-Agent Framework that can behave as an engineer, product manager, architect, project managers.\",\n \"htmlSnippet\": \"\\u003cb\\u003eMetaGPT\\u003c/b\\u003e is about to reach 10000 stars on Github. It's a Multi-Agent Framework that can behave as an engineer, product manager, architect, project managers.\",\n \"cacheId\": \"qWqvRF7SoGsJ\",\n \"formattedUrl\": \"https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-t...\",\n \"htmlFormattedUrl\": \"https://medium.datadriveninvestor.com/\\u003cb\\u003emetagpt\\u003c/b\\u003e-a-multi-agent-framework-t...\",\n \"pagemap\": {\n \"cse_thumbnail\": [\n {\n \"src\": \"https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRKDyUf8JumEvosQ1ZmxQ1dGmOGIx1jd4bvnICexOb2jFmKZHKagMGoQ0xI\",\n \"width\": \"242\",\n \"height\": \"209\"\n }\n ],\n \"metatags\": [\n {\n \"og:image\": \"https://miro.medium.com/v2/da:true/resize:fit:1200/0*g2b2hbP8HykGIIN3\",\n \"twitter:app:url:iphone\": \"medium://p/4b6ae747cc36\",\n \"theme-color\": \"#000000\",\n \"article:published_time\": \"2023-09-05T05:20:30.732Z\",\n \"twitter:card\": \"summary_large_image\",\n \"og:site_name\": \"Medium\",\n \"al:android:package\": \"com.medium.reader\",\n \"twitter:label1\": \"Reading time\",\n \"twitter:tile:template:testing\": \"2\",\n \"twitter:app:id:iphone\": \"828256236\",\n \"title\": \"MetaGPT: a Multi-Agent Framework to Automate Your Software Company | by Peter Xing | DataDrivenInvestor\",\n \"al:ios:url\": \"medium://p/4b6ae747cc36\",\n \"og:description\": \"MetaGPT is about to reach 10,000 stars on Github. It’s a Multi-Agent Framework that can behave as an engineer, product manager, architect…\",\n \"twitter:creator\": \"@peterxing\",\n \"al:ios:app_store_id\": \"828256236\",\n \"twitter:data1\": \"2 min read\",\n \"twitter:site\": \"@DDInvestorHQ\",\n \"twitter:tile:info1:text\": \"Peter Xing\",\n \"twitter:tile:info1:icon\": \"Person\",\n \"og:type\": \"article\",\n \"twitter:title\": \"MetaGPT: a Multi-Agent Framework to Automate Your Software Company\",\n \"al:ios:app_name\": \"Medium\",\n \"twitter:cta\": \"Read on Medium\",\n \"author\": \"Peter Xing\",\n \"og:title\": \"MetaGPT: a Multi-Agent Framework to Automate Your Software Company\",\n \"al:web:url\": \"https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-to-automate-your-software-company-4b6ae747cc36\",\n \"article:author\": \"https://medium.com/@peterxing\",\n \"twitter:tile:info2:text\": \"Sep 4, 2023\",\n \"twitter:image:src\": \"https://miro.medium.com/v2/da:true/resize:fit:1200/0*g2b2hbP8HykGIIN3\",\n \"al:android:url\": \"medium://p/4b6ae747cc36\",\n \"referrer\": \"unsafe-url\",\n \"fb:app_id\": \"542599432471018\",\n \"viewport\": \"width=device-width,minimum-scale=1,initial-scale=1,maximum-scale=1\",\n \"twitter:tile:info2:icon\": \"Calendar\",\n \"twitter:description\": \"MetaGPT is about to reach 10,000 stars on Github. It’s a Multi-Agent Framework that can behave as an engineer, product manager, architect…\",\n \"twitter:tile:image\": \"https://miro.medium.com/v2/da:true/resize:fit:1200/0*g2b2hbP8HykGIIN3\",\n \"og:url\": \"https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-to-automate-your-software-company-4b6ae747cc36\",\n \"twitter:app:name:iphone\": \"Medium\",\n \"al:android:app_name\": \"Medium\"\n }\n ],\n \"cse_image\": [\n {\n \"src\": \"https://miro.medium.com/v2/da:true/resize:fit:1200/0*g2b2hbP8HykGIIN3\"\n }\n ]\n }\n }\n ]\n}\n", + "aiohttp-post-https://google.serper.dev/search-{\"data\": \"[{\\\"num\\\": 8, \\\"page\\\": 1, \\\"q\\\": \\\"metagpt\\\"}]\", \"headers\": {\"Content-Type\": \"application/json\", \"X-API-KEY\": \"mock-serper-key\"}}": [ + { + "searchParameters": { + "q": "metagpt", + "num": 8, + "page": 1, + "type": "search", + "engine": "google" + }, + "organic": [ + { + "title": "geekan/MetaGPT: The Multi-Agent Framework: Given one ... - GitHub", + "link": "https://github.com/geekan/MetaGPT", + "snippet": "MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc.", + "sitelinks": [ + { + "title": "Roadmap", + "link": "https://github.com/geekan/MetaGPT/blob/main/docs/ROADMAP.md" + }, + { + "title": "README.md", + "link": "https://github.com/geekan/MetaGPT/blob/main/README.md" + }, + { + "title": "Issues 161", + "link": "https://github.com/geekan/MetaGPT/issues" + }, + { + "title": "Actions", + "link": "https://github.com/geekan/MetaGPT/actions" + } + ], + "position": 1 + }, + { + "title": "[2308.00352] MetaGPT: Meta Programming for A Multi-Agent ... - arXiv", + "link": "https://arxiv.org/abs/2308.00352", + "snippet": "Abstract:Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs).", + "date": "Aug 1, 2023", + "position": 2 + }, + { + "title": "MetaGPT: a Multi-Agent Framework to Automate Your Software ...", + "link": "https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-to-automate-your-software-company-4b6ae747cc36", + "snippet": "MetaGPT is about to reach 10000 stars on Github. It's a Multi-Agent Framework that can behave as an engineer, product manager, architect, project managers.", + "position": 3 + }, + { + "title": "MetaGPT HUGE Update: Autonomous AI Agents with Incremental ...", + "link": "https://www.youtube.com/watch?v=Xyws6iI-eH8", + "snippet": "In this video, we unravel the magic at the core of MetaGPT, exploring its multi-agent framework ...", + "date": "Dec 23, 2023", + "attributes": { + "Duration": "11:38", + "Posted": "Dec 23, 2023" + }, + "imageUrl": "https://i.ytimg.com/vi/Xyws6iI-eH8/default.jpg?sqp=-oaymwEECHgQQw&rs=AMzJL3k9VHKSi-z-si4PJd1tNv8Itm4h5g", + "position": 4 + }, + { + "title": "MetaGPT - Apps on Google Play", + "link": "https://play.google.com/store/apps/details?id=com.metagpt.app&hl=en&gl=US", + "snippet": "Real-time crypto monitor.Track prices, set alerts, seize opportunities instantly.", + "date": "Jan 1, 2024", + "position": 5 + }, + { + "title": "MetaGPT | Discover AI use cases - GPT-3 Demo", + "link": "https://gpt3demo.com/apps/metagpt", + "snippet": "Assign different roles to GPTs to form a collaborative software entity for complex tasks. MetaGPT takes a one-line requirement as input and outputs user ...", + "position": 6 + }, + { + "title": "MetaGPT: AI-Powered Web Development That Changes the Game", + "link": "https://www.analyticsvidhya.com/blog/2024/01/meet-metagpt-the-chatgpt-powered-ai-assistant-that-turns-text-into-web-apps/", + "snippet": "MetaGPT is an AI assistant that leverages the power of GPT-4, a state-of-the-art language model developed by OpenAI. ChatGPT is trained on vast ...", + "date": "Jan 4, 2024", + "position": 7 + }, + { + "title": "MetaGPT: Complete Guide to the Best AI Agent Available Right Now", + "link": "https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/", + "snippet": "Discover why MetaGPT outperforms AutoGPT, BabyAgi, and other AI agents in complex coding tasks. Our in-depth article guides you through the ...", + "date": "Sep 11, 2023", + "position": 8 + } + ], + "relatedSearches": [ + { + "query": "MetaGPT online" + }, + { + "query": "Metagpt download" + }, + { + "query": "MetaGPT paper" + }, + { + "query": "Metagpt app" + }, + { + "query": "Metagpt github" + }, + { + "query": "MetaGPT huggingface" + }, + { + "query": "MetaGPT review" + }, + { + "query": "MetaGPT AI" + } + ] + } + ], + "aiohttp-post-https://google.serper.dev/search-{\"data\": \"[{\\\"num\\\": 6, \\\"page\\\": 1, \\\"q\\\": \\\"metagpt\\\"}]\", \"headers\": {\"Content-Type\": \"application/json\", \"X-API-KEY\": \"mock-serper-key\"}}": [ + { + "searchParameters": { + "q": "metagpt", + "num": 6, + "page": 1, + "type": "search", + "engine": "google" + }, + "organic": [ + { + "title": "geekan/MetaGPT: The Multi-Agent Framework: Given one ... - GitHub", + "link": "https://github.com/geekan/MetaGPT", + "snippet": "MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc.", + "sitelinks": [ + { + "title": "Roadmap", + "link": "https://github.com/geekan/MetaGPT/blob/main/docs/ROADMAP.md" + }, + { + "title": "README.md", + "link": "https://github.com/geekan/MetaGPT/blob/main/README.md" + }, + { + "title": "Issues 161", + "link": "https://github.com/geekan/MetaGPT/issues" + }, + { + "title": "Actions", + "link": "https://github.com/geekan/MetaGPT/actions" + } + ], + "position": 1 + }, + { + "title": "[2308.00352] MetaGPT: Meta Programming for A Multi-Agent ... - arXiv", + "link": "https://arxiv.org/abs/2308.00352", + "snippet": "Abstract:Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs).", + "date": "Aug 1, 2023", + "position": 2 + }, + { + "title": "MetaGPT: a Multi-Agent Framework to Automate Your Software ...", + "link": "https://medium.datadriveninvestor.com/metagpt-a-multi-agent-framework-to-automate-your-software-company-4b6ae747cc36", + "snippet": "MetaGPT is about to reach 10000 stars on Github. It's a Multi-Agent Framework that can behave as an engineer, product manager, architect, project managers.", + "position": 3 + }, + { + "title": "MetaGPT HUGE Update: Autonomous AI Agents with Incremental ...", + "link": "https://www.youtube.com/watch?v=Xyws6iI-eH8", + "snippet": "In this video, we unravel the magic at the core of MetaGPT, exploring its multi-agent framework ...", + "date": "Dec 23, 2023", + "attributes": { + "Duration": "11:38", + "Posted": "Dec 23, 2023" + }, + "imageUrl": "https://i.ytimg.com/vi/Xyws6iI-eH8/default.jpg?sqp=-oaymwEECHgQQw&rs=AMzJL3k9VHKSi-z-si4PJd1tNv8Itm4h5g", + "position": 4 + }, + { + "title": "MetaGPT - Apps on Google Play", + "link": "https://play.google.com/store/apps/details?id=com.metagpt.app&hl=en&gl=US", + "snippet": "Real-time crypto monitor.Track prices, set alerts, seize opportunities instantly.", + "date": "Jan 1, 2024", + "position": 5 + }, + { + "title": "MetaGPT: AI-Powered Web Development That Changes the Game", + "link": "https://www.analyticsvidhya.com/blog/2024/01/meet-metagpt-the-chatgpt-powered-ai-assistant-that-turns-text-into-web-apps/", + "snippet": "MetaGPT is an AI assistant that leverages the power of GPT-4, a state-of-the-art language model developed by OpenAI. ChatGPT is trained on vast ...", + "date": "Jan 4, 2024", + "position": 6 + } + ], + "relatedSearches": [ + { + "query": "MetaGPT online" + }, + { + "query": "MetaGPT paper" + }, + { + "query": "Metagpt review" + }, + { + "query": "Metagpt download" + }, + { + "query": "Metagpt github" + }, + { + "query": "MetaGPT AI" + }, + { + "query": "MetaGPT huggingface" + }, + { + "query": "Metagpt OpenAI" + } + ] + } + ], + "curl-cffi-POST-https://duckduckgo.com-{\"data\": {\"q\": \"metagpt\"}}": "metagpt at DuckDuckGo
", + "curl-cffi-GET-https://links.duckduckgo.com/d.js-{\"params\": {\"bing_market\": \"wt-WT\", \"df\": null, \"ex\": \"-1\", \"kl\": \"wt-wt\", \"l\": \"wt-wt\", \"q\": \"metagpt\", \"s\": \"0\", \"sp\": \"0\", \"vqd\": \"4-118631859838297093459588814466521506726\"}}": "if (DDG.deep && DDG.deep.setUpstream) DDG.deep.setUpstream(\"bingv7aa\");DDG.deep.bn={'ivc':1};if (DDG.pageLayout) DDG.pageLayout.load('a',[], {\"page_load_url\":\"https://duckduckgo.com/y.js?iurl=%7B2%7DIG%3DFD8EFA3AD04A446FA24ACF32036DB0FF%26CID%3D3E2A18C583DE6B6F14A00CC382616A60%26Type%3DEvent.CPT%26DATA%3D0\"});DDG.deep.signalSummary = \"retail:h\";DDG.inject('DDG.Data.languages.resultLanguages', {\"en\":[\"https://github.com/geekan/MetaGPT\",\"https://docs.deepwisdom.ai/\",\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"https://docs.deepwisdom.ai/main/en/guide/get_started/introduction.html\",\"https://arxiv.org/abs/2308.00352\",\"https://github.com/geekan/MetaGPT/blob/main/README.md\",\"https://interestingengineering.com/innovation/metagpt-create-apps-text-prompts\",\"https://aibusiness.com/nlp/metagpt-text-to-app-ai-simplifies-web-dev\",\"https://github.com/PlaiD3/MetaGPT/blob/main/README.md\",\"https://www.youtube.com/watch?v=wpgC5fmtU70\",\"https://www.tomsguide.com/news/ai-tool-uses-chatgpt-to-build-you-a-website-in-30-minutes-and-we-tried-it\",\"https://www.kdnuggets.com/meet-metagpt-the-chatgptpowered-ai-assistant-that-turns-text-into-web-apps\",\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"https://www.marktechpost.com/2023/08/09/meet-metagpt-the-open-source-ai-framework-that-transforms-gpts-into-engineers-architects-and-managers/\",\"https://medium.com/gta-generative-tech-advances/metagpt-an-interesting-approach-to-multi-agent-collaboration-5ace263c4fd8\",\"https://www.youtube.com/watch?v=nqZlTV_L6Ao\",\"https://medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\",\"https://medium.com/@smraiyyan/metagpt-unleashed-crafting-your-virtual-software-company-from-scratch-6ea60cd70da1\",\"https://www.almabetter.com/bytes/articles/metagpt\",\"https://geekflare.com/metagpt-multi-agent-framework/\",\"https://analyticsindiamag.com/metagpt-realising-the-gpt-4-dream/\",\"https://medium.com/technology-hits/autogpt-langchain-deep-lake-metagpt-a-revolutionary-framework-for-building-advanced-ai-e2c579d86494\",\"https://generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\",\"https://www.msn.com/en-us/news/technology/generative-ai-apis-and-chatgpt-alternatives-for-developers-to-consider/ar-AA1ltwXb\",\"https://www.theguardian.com/technology/2024/jan/08/ai-tools-chatgpt-copyrighted-material-openai\",\"https://www.forbes.com/sites/katiejennings/2024/01/05/health-ai-startup-nabla-was-built-on-gpt-4-now-its-abandoning-openai-for-open-source/\",\"https://www.technologyreview.com/2024/01/04/1086046/whats-next-for-ai-in-2024/\"],\"zh-CN\":[\"https://blog.csdn.net/Attitude93/article/details/135550499\",\"https://zhuanlan.zhihu.com/p/677608276\"]});DDG.deep.pageLayoutSummary = \"w29v1r1\";DDG.inject('DDG.Data.languages.adLanguages', {});if (DDG.pageLayout) DDG.pageLayout.load('d',[{\"a\":\"geekan/MetaGPT. This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository. About. \\ud83c\\udf1f The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo deepwisdom.ai/ Topics. agent multi-agent gpt hacktoberfest llm metagpt Resources. Readme\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT\",\"d\":\"github.com/geekan/MetaGPT\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework - GitHub\",\"u\":\"https://github.com/geekan/MetaGPT\"},{\"a\":\"MetaGPT. The Multi-Agent Framework. Assign different roles to GPTs to form a collaborative software entity for complex tasks. Get Started. View on Github. Agents. Explore agent creation, configuration, and management, including algorithms and techniques. Demos.\",\"ae\":null,\"c\":\"https://docs.deepwisdom.ai/\",\"d\":\"docs.deepwisdom.ai\",\"da\":\"\",\"h\":0,\"i\":\"docs.deepwisdom.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT | MetaGPT\",\"u\":\"https://docs.deepwisdom.ai/\"},{\"a\":\"MetaGPT is a Multi-agent system that utilizes Large Language models and Standardized Operating Procedures to generate code in real-time. It outperforms other AI agents in code generation, collaboration, and code review. Learn how to install and use MetaGPT with examples and benchmarks.\",\"ae\":null,\"c\":\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"d\":\"www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"da\":\"\",\"e\":\"2023-09-11T00:00:00.0000000\",\"h\":0,\"i\":\"www.unite.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\"u\":\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\"},{\"a\":\"Internally, MetaGPT includes product managers / architects / project managers / engineers. It provides the entire process of a software company along with carefully orchestrated SOPs. Code = SOP (Team) is the core philosophy. We materialize SOP and apply it to teams composed of LLMs. Software Company Multi-Role Schematic.\",\"ae\":null,\"c\":\"https://docs.deepwisdom.ai/main/en/guide/get_started/introduction.html\",\"d\":\"docs.deepwisdom.ai/main/en/guide/get_started/introduction.html\",\"da\":\"\",\"h\":0,\"i\":\"docs.deepwisdom.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework | MetaGPT\",\"u\":\"https://docs.deepwisdom.ai/main/en/guide/get_started/introduction.html\"},{\"a\":\"MetaGPT is a novel method that uses human workflows to improve the performance of LLM-based multi-agent systems. It encodes SOPs into prompt sequences and assigns roles to agents to break down complex tasks into subtasks.\",\"ae\":null,\"b\":\"arx\\tarXiv.org\\tarxiv.org\",\"c\":\"https://arxiv.org/abs/2308.00352\",\"d\":\"arxiv.org/abs/2308.00352\",\"da\":\"translations\",\"e\":\"2023-08-01T00:00:00.0000000\",\"h\":0,\"i\":\"arxiv.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework\",\"u\":\"https://arxiv.org/abs/2308.00352\"},{\"a\":\"MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc. \n Internally, MetaGPT includes product managers / architects / project managers / engineers.\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT/blob/main/README.md\",\"d\":\"github.com/geekan/MetaGPT/blob/main/README.md\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework - GitHub\",\"u\":\"https://github.com/geekan/MetaGPT/blob/main/README.md\"},{\"a\":\"MetaGPT is a tool that lets you build websites, apps, and more using only text-based prompts powered by ChatGPT, an AI chatbot that can write code and improve it. You can create one app for free or subscribe for unlimited apps with MetaGPT.\",\"ae\":null,\"c\":\"https://interestingengineering.com/innovation/metagpt-create-apps-text-prompts\",\"d\":\"interestingengineering.com/innovation/metagpt-create-apps-text-prompts\",\"da\":\"\",\"e\":\"2023-05-08T12:57:00.0000000\",\"h\":0,\"i\":\"interestingengineering.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Create web-based apps with only text prompts\",\"u\":\"https://interestingengineering.com/innovation/metagpt-create-apps-text-prompts\"},{\"a\":\"MetaGPT is a new text-to-app generator that can create web apps from text descriptions. It uses ChatGPT's API and is free to use for commercial purposes. You can build microapps for various tasks or platforms, such as Facebook Messenger, Trello, or Microsoft Word.\",\"ae\":null,\"c\":\"https://aibusiness.com/nlp/metagpt-text-to-app-ai-simplifies-web-dev\",\"d\":\"aibusiness.com/nlp/metagpt-text-to-app-ai-simplifies-web-dev\",\"da\":\"\",\"e\":\"2023-08-07T00:00:00.0000000\",\"h\":0,\"i\":\"aibusiness.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Text-To-App AI Simplifies Web Dev\",\"u\":\"https://aibusiness.com/nlp/metagpt-text-to-app-ai-simplifies-web-dev\"},{\"a\":\"MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc. \n; Internally, MetaGPT includes product managers / architects / project managers / engineers. It provides the entire process of a software company along with carefully orchestrated SOPs.\n \n\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/PlaiD3/MetaGPT/blob/main/README.md\",\"d\":\"github.com/PlaiD3/MetaGPT/blob/main/README.md\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Multi-Agent Meta Programming Framework - GitHub\",\"u\":\"https://github.com/PlaiD3/MetaGPT/blob/main/README.md\"},{\"a\":\"MetaGPT is a powerful no-code solution for app building that allows users to create web apps without any prerequisites of coding or technical experience. It ...\",\"ae\":null,\"b\":\"yt\\tYouTube\\twww.youtube.com\",\"c\":\"https://www.youtube.com/watch?v=wpgC5fmtU70\",\"d\":\"www.youtube.com/watch?v=wpgC5fmtU70\",\"da\":\"mlb_games,nba_games,ncaafb_games,ncaamb_games,nfl_games,nhl_games,soccer_games,translations,videos,wheretowatch\",\"h\":0,\"i\":\"www.youtube.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Meet MetaGPT A GPT-4-powered Application That Can Create ... - YouTube\",\"u\":\"https://www.youtube.com/watch?v=wpgC5fmtU70\"},{\"a\":\"Developed by New York-based company WhimsyWorks, MetaGPT offers users a no-code solution to turn their idea into a website or online app using AI. If you've recently used an AI chatbot, the ...\",\"ae\":null,\"c\":\"https://www.tomsguide.com/news/ai-tool-uses-chatgpt-to-build-you-a-website-in-30-minutes-and-we-tried-it\",\"d\":\"www.tomsguide.com/news/ai-tool-uses-chatgpt-to-build-you-a-website-in-30-minutes-and-we-tried-it\",\"da\":\"translations\",\"e\":\"2023-05-10T00:00:00.0000000\",\"h\":0,\"i\":\"www.tomsguide.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"AI tool uses ChatGPT to build you an app in 30 minutes - Tom's Guide\",\"u\":\"https://www.tomsguide.com/news/ai-tool-uses-chatgpt-to-build-you-a-website-in-30-minutes-and-we-tried-it\"},{\"a\":\"MetaGPT is a tool that lets you create no-code web applications using natural language. You can type in a text prompt and get a functional web app in seconds, using the power of GPT-4 and the Code Interpreter. Learn how to use MetaGPT for data science, analytics, and more.\",\"ae\":null,\"c\":\"https://www.kdnuggets.com/meet-metagpt-the-chatgptpowered-ai-assistant-that-turns-text-into-web-apps\",\"d\":\"www.kdnuggets.com/meet-metagpt-the-chatgptpowered-ai-assistant-that-turns-text-into-web-apps\",\"da\":\"\",\"e\":\"2023-09-08T00:00:00.0000000\",\"h\":0,\"i\":\"www.kdnuggets.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Meet MetaGPT: The ChatGPT-Powered AI Assistant That Turns Text Into Web ...\",\"u\":\"https://www.kdnuggets.com/meet-metagpt-the-chatgptpowered-ai-assistant-that-turns-text-into-web-apps\"},{\"a\":\"MetaGPT is a multi-agent system that uses large language models to perform complex tasks. It can understand, generate, and interact with natural language input and output. Learn about its features, capabilities, applications, and advantages in this complete guide.\",\"ae\":null,\"c\":\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"d\":\"www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"da\":\"\",\"e\":\"2023-12-13T00:00:00.0000000\",\"h\":0,\"i\":\"www.straight.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"A Complete Guide to MetaGPT: The Best AI Agent Available Now\",\"u\":\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\"},{\"a\":\"MetaGPT is an open-source AI framework that transforms GPTs into engineers, architects, and managers by using role-based action specifications and SOPs. It can generate high-quality code, design, and documentation for software engineering, data analysis, and game development tasks.\",\"ae\":null,\"c\":\"https://www.marktechpost.com/2023/08/09/meet-metagpt-the-open-source-ai-framework-that-transforms-gpts-into-engineers-architects-and-managers/\",\"d\":\"www.marktechpost.com/2023/08/09/meet-metagpt-the-open-source-ai-framework-that-transforms-gpts-into-engineers-architects-and-managers/\",\"da\":\"translations\",\"e\":\"2023-08-09T00:00:00.0000000\",\"h\":0,\"i\":\"www.marktechpost.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Meet MetaGPT: The Open-Source AI Framework That Transforms GPTs into ...\",\"u\":\"https://www.marktechpost.com/2023/08/09/meet-metagpt-the-open-source-ai-framework-that-transforms-gpts-into-engineers-architects-and-managers/\"},{\"a\":\"MetaGPT is the maestro who brings harmony to this chaos. By encoding Standardized Operating Procedures (SOPs) into prompts, MetaGPT ensures structured collaboration akin to a well-rehearsed ...\",\"ae\":null,\"c\":\"https://medium.com/gta-generative-tech-advances/metagpt-an-interesting-approach-to-multi-agent-collaboration-5ace263c4fd8\",\"d\":\"medium.com/gta-generative-tech-advances/metagpt-an-interesting-approach-to-multi-agent-collaboration-5ace263c4fd8\",\"da\":\"\",\"e\":\"2023-08-15T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: An Interesting Approach to Multi-Agent Collaboration\",\"u\":\"https://medium.com/gta-generative-tech-advances/metagpt-an-interesting-approach-to-multi-agent-collaboration-5ace263c4fd8\"},{\"a\":\"Welcome to our video review! \\ud83c\\udfa5 Dive into the world of MetaGPT, a revolutionary project that's redefining the boundaries of AI. \\ud83e\\udd16 Imagine having an entire e...\",\"ae\":null,\"b\":\"yt\\tYouTube\\twww.youtube.com\",\"c\":\"https://www.youtube.com/watch?v=nqZlTV_L6Ao\",\"d\":\"www.youtube.com/watch?v=nqZlTV_L6Ao\",\"da\":\"mlb_games,nba_games,ncaafb_games,ncaamb_games,nfl_games,nhl_games,soccer_games,videos,wheretowatch\",\"e\":\"2023-09-04T00:00:00.0000000\",\"h\":0,\"i\":\"www.youtube.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT Setup: Launch a Startup with One \\ufe0f Prompt! - YouTube\",\"u\":\"https://www.youtube.com/watch?v=nqZlTV_L6Ao\"},{\"a\":\"MetaGPT is a model that uses the power of natural language to create and execute meta programs for multi-agent collaboration. Meta programs are programs that can generate or modify other programs ...\",\"ae\":null,\"c\":\"https://medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\",\"d\":\"medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\",\"da\":\"\",\"e\":\"2023-08-03T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: A Framework for Multi-Agent Meta Programming\",\"u\":\"https://medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\"},{\"a\":\"MetaGPT, available on Github (crossed 13,000 stars), aims to change the way we make software.This exciting tool can take a single line of what you want to do and turn it into many things like user ...\",\"ae\":null,\"c\":\"https://medium.com/@smraiyyan/metagpt-unleashed-crafting-your-virtual-software-company-from-scratch-6ea60cd70da1\",\"d\":\"medium.com/@smraiyyan/metagpt-unleashed-crafting-your-virtual-software-company-from-scratch-6ea60cd70da1\",\"da\":\"translations\",\"e\":\"2023-08-07T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT Lets You Create Your Own Virtual Software Company from ... - Medium\",\"u\":\"https://medium.com/@smraiyyan/metagpt-unleashed-crafting-your-virtual-software-company-from-scratch-6ea60cd70da1\"},{\"a\":\"Discover the revolutionary advancements of MetaGPT and its potential impact on the future of AI-powered solutions. Artificial Intelligence has experienced remarkable progress in recent years, with one term in particular capturing the attention of the digital landscape: MetaGPT online. It can also be referred to as one of the ChatGPT alternatives.In an increasingly competitive environment ...\",\"ae\":null,\"c\":\"https://www.almabetter.com/bytes/articles/metagpt\",\"d\":\"www.almabetter.com/bytes/articles/metagpt\",\"da\":\"\",\"e\":\"2023-08-28T00:00:00.0000000\",\"h\":0,\"i\":\"www.almabetter.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Future of Multi-Agent Collaboration in AI\",\"u\":\"https://www.almabetter.com/bytes/articles/metagpt\"},{\"a\":\"MetaGPT is a framework that uses different GPTs to generate APIs, user stories, data structures, and more. It can automate software development tasks, enhance existing programs, and collaborate with other agents. Learn how to get started, use cases, advantages, and alternatives of MetaGPT.\",\"ae\":null,\"c\":\"https://geekflare.com/metagpt-multi-agent-framework/\",\"d\":\"geekflare.com/metagpt-multi-agent-framework/\",\"da\":\"\",\"e\":\"2023-09-18T00:00:00.0000000\",\"h\":0,\"i\":\"geekflare.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Is This the Best Multi-Agent Framework Yet? - Geekflare\",\"u\":\"https://geekflare.com/metagpt-multi-agent-framework/\"},{\"a\":\"MetaGPT is a web app that allows users to build web applications using natural language prompts and ChatGPT, a multimodal language model. The service has been used to create dashboards, code-based visualisations, and even a marriage proposal, showing the potential of GPT-4 and its plugins.\",\"ae\":null,\"c\":\"https://analyticsindiamag.com/metagpt-realising-the-gpt-4-dream/\",\"d\":\"analyticsindiamag.com/metagpt-realising-the-gpt-4-dream/\",\"da\":\"\",\"e\":\"2023-04-26T00:00:00.0000000\",\"h\":0,\"i\":\"analyticsindiamag.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT \\u2014 Realising the GPT-4 Dream - Analytics India Magazine\",\"u\":\"https://analyticsindiamag.com/metagpt-realising-the-gpt-4-dream/\"},{\"a\":\"MetaGPT, or multimodal Generative Pretrained Transformers, represents a significant leap in the evolution of artificial intelligence. This new generation of AI models is capable of understanding ...\",\"ae\":null,\"c\":\"https://medium.com/technology-hits/autogpt-langchain-deep-lake-metagpt-a-revolutionary-framework-for-building-advanced-ai-e2c579d86494\",\"d\":\"medium.com/technology-hits/autogpt-langchain-deep-lake-metagpt-a-revolutionary-framework-for-building-advanced-ai-e2c579d86494\",\"da\":\"\",\"e\":\"2023-08-28T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"AutoGPT \\u2014 LangChain \\u2014 Deep Lake \\u2014 MetaGPT: A ... - Medium\",\"u\":\"https://medium.com/technology-hits/autogpt-langchain-deep-lake-metagpt-a-revolutionary-framework-for-building-advanced-ai-e2c579d86494\"},{\"a\":\"Overview of the MetaGPT framework. Presented is a two-layer architectural design: i) the Foundational Components Layer, which is essential for agent operations and system-wide communication, and ii) the Collaboration Layer, which facilitates agent coordination through key mechanisms such as knowledge sharing and workflow encapsulation.\",\"ae\":null,\"c\":\"https://generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\",\"d\":\"generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\",\"da\":\"translations\",\"e\":\"2023-08-14T00:00:00.0000000\",\"h\":0,\"i\":\"generativeai.pub\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Analyzing an exciting Generative AI research called MetaGPT.\",\"u\":\"https://generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\"},{\"a\":\"MetaGPT\\u5c06\\u4f1a\\u6309\\u7167\\u4e0b\\u8ff0\\u4f18\\u5148\\u7ea7\\u6765\\u8bfb\\u53d6\\u4f60\\u7684\\u914d\\u7f6e\\uff1aconfig/key.yaml > config/config.yaml > environment variable. \\u6211\\u8fd9\\u91cc\\u4f7f\\u7528\\u73af\\u5883\\u53d8\\u91cf\\u7684\\u65b9\\u5f0f\\u3002. \\uff081\\uff09\\u521b\\u5efa\\u4e00\\u4e2a\\u5de5\\u7a0b\\u76ee\\u5f55 MyMetaGPT\\uff0c\\u7528VSCode\\u6253\\u5f00. \\uff082\\uff09\\u65b0\\u5efa\\u4e00\\u4e2a.env\\u6587\\u4ef6\\uff0c\\u5c06\\u4ee5\\u4e0a\\u914d\\u7f6e\\u586b\\u52a0\\u5230\\u8be5\\u6587\\u4ef6\\u4e2d. \\u5728Python\\u6587\\u4ef6\\uff08MetaGPT_test.py\\uff09\\u4e2d\\u5c06\\u8be5.env\\u6587\\u4ef6 ...\",\"ae\":null,\"c\":\"https://blog.csdn.net/Attitude93/article/details/135550499\",\"d\":\"blog.csdn.net/Attitude93/article/details/135550499\",\"da\":\"translations\",\"e\":\"2024-01-13T00:00:00.0000000\",\"h\":0,\"i\":\"blog.csdn.net\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"AI Agent\\u7cfb\\u5217\\u3011\\u3010MetaGPT\\u30110. \\u4f60\\u7684\\u7b2c\\u4e00\\u4e2aMetaGPT\\u7a0b\\u5e8f - CSDN\\u535a\\u5ba2\",\"u\":\"https://blog.csdn.net/Attitude93/article/details/135550499\"},{\"a\":\"Here are nine of the best ChatGPT alternatives and generative AI APIs for developers that are worth checking out. 1. Meta: Llama2. do is download and install Llama 2 locally. Related video: How AI ...\",\"ae\":null,\"c\":\"https://www.msn.com/en-us/news/technology/generative-ai-apis-and-chatgpt-alternatives-for-developers-to-consider/ar-AA1ltwXb\",\"d\":\"www.msn.com/en-us/news/technology/generative-ai-apis-and-chatgpt-alternatives-for-developers-to-consider/ar-AA1ltwXb\",\"da\":\"news\",\"e\":\"2023-12-13T00:00:00.0000000\",\"h\":0,\"i\":\"www.msn.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Generative AI APIs and ChatGPT Alternatives for Developers to ... - MSN\",\"u\":\"https://www.msn.com/en-us/news/technology/generative-ai-apis-and-chatgpt-alternatives-for-developers-to-consider/ar-AA1ltwXb\"},{\"a\":\"Pressure grows on artificial intelligence firms over the content used to train their products\",\"ae\":null,\"c\":\"https://www.theguardian.com/technology/2024/jan/08/ai-tools-chatgpt-copyrighted-material-openai\",\"d\":\"www.theguardian.com/technology/2024/jan/08/ai-tools-chatgpt-copyrighted-material-openai\",\"da\":\"news,translations\",\"e\":\"2024-01-08T07:15:00.0000000\",\"h\":0,\"i\":\"www.theguardian.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"'Impossible' to create AI tools like ChatGPT without copyrighted ...\",\"u\":\"https://www.theguardian.com/technology/2024/jan/08/ai-tools-chatgpt-copyrighted-material-openai\"},{\"a\":\"The Paris-based startup has raised $24 million at a $180 million valuation to shift its doctor note-taking software towards the open source AI models championed by Meta AI chief Yann Lecun, one of ...\",\"ae\":null,\"c\":\"https://www.forbes.com/sites/katiejennings/2024/01/05/health-ai-startup-nabla-was-built-on-gpt-4-now-its-abandoning-openai-for-open-source/\",\"d\":\"www.forbes.com/sites/katiejennings/2024/01/05/health-ai-startup-nabla-was-built-on-gpt-4-now-its-abandoning-openai-for-open-source/\",\"da\":\"news,translations\",\"e\":\"2024-01-05T11:00:00.0000000\",\"h\":0,\"i\":\"www.forbes.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Health AI Startup Nabla Was Built On GPT-4. Now, It's ... - Forbes\",\"u\":\"https://www.forbes.com/sites/katiejennings/2024/01/05/health-ai-startup-nabla-was-built-on-gpt-4-now-its-abandoning-openai-for-open-source/\"},{\"a\":\"\\u57282023\\u5e7412\\u670819\\u65e5\\u65f6\\uff0c\\u542c\\u4e86\\u6797\\u4e49\\u7ae0\\u8001\\u5e08\\u5173\\u4e8e"\\u57fa\\u4e8eMetaGPT\\u8fdb\\u884c\\u667a\\u80fd\\u4f53\\u5f00\\u53d1"\\u7684\\u8bb2\\u5ea7\\uff1a \\u89c9\\u5f97\\u65b0\\u5947\\u6709\\u8da3\\uff0c\\u5982\\u679c\\u80fd\\u8fd9\\u6837\\u5728\\u5de5\\u4f5c\\u751f\\u6d3b\\u4e2d\\u5b8c\\u6210\\u81ea\\u5df1\\u7684\\u4efb\\u52a1\\uff0c\\u90a3\\u7b80\\u76f4\\u662f\\u4e8b\\u534a\\u529f\\u500d\\u3002\\u4e8e\\u662f\\u8fd9\\u4e24\\u5929\\u53c8\\u5b66\\u4e60\\u4e86\\u300aMetaGPT\\u667a\\u80fd\\u4f53\\u5f00\\u53d1\\u5165\\u95e8\\u300b\\u6559\\u2026\",\"ae\":null,\"c\":\"https://zhuanlan.zhihu.com/p/677608276\",\"d\":\"zhuanlan.zhihu.com/p/677608276\",\"da\":\"translations\",\"e\":\"2024-01-12T00:00:00.0000000\",\"h\":0,\"i\":\"zhuanlan.zhihu.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"\\u5b66\\u4e60\\u7b14\\u8bb0-\\u300aMetaGPT\\u667a\\u80fd\\u4f53\\u5f00\\u53d1\\u5165\\u95e8\\u300b\\u6559\\u7a0b - \\u77e5\\u4e4e\",\"u\":\"https://zhuanlan.zhihu.com/p/677608276\"},{\"a\":\"In 2024, generative AI might actually become useful for the regular, non-tech person, and we are going to see more people tinkering with a million little AI models. State-of-the-art AI models ...\",\"ae\":null,\"c\":\"https://www.technologyreview.com/2024/01/04/1086046/whats-next-for-ai-in-2024/\",\"d\":\"www.technologyreview.com/2024/01/04/1086046/whats-next-for-ai-in-2024/\",\"da\":\"translations\",\"e\":\"2024-01-04T09:14:17.0000000\",\"h\":0,\"i\":\"www.technologyreview.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What's next for AI in 2024 | MIT Technology Review\",\"u\":\"https://www.technologyreview.com/2024/01/04/1086046/whats-next-for-ai-in-2024/\"},{\"n\":\"/d.js?q=metagpt&kl=wt-wt&l=wt-wt&p=&s=29&ex=-1&ct=US&sp=0&vqd=4-118631859838297093459588814466521506726\"}]);DDG.duckbar.load('images');DDG.duckbar.load('news');DDG.duckbar.load('videos', {\"ads\":[],\"query\":\"metagpt\",\"queryEncoded\":\"metagpt\",\"response_type\":\"places\",\"results\":[{\"content\":\"https://www.youtube.com/watch?v=uT75J_KG_aY\",\"description\":\"In this video, we review MetaGPT, a new project that aims to recreate an entire engineering organization using AI. MetaGPT is a CEO, Product Manager, Architect, Project Manager, Engineering, and QA. Write a simple prompt, and you get everything from the requirements to the PRDs to the code and tests. How To Find Me: Become a Patron \\ud83d\\udd25 - https ...\",\"duration\":\"6:36\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/uT75J_KG_aY?autoplay=1\",\"image_token\":\"57974159b78b309485721c0bce280219d9927e071e542a34777864767d6cb8d4\",\"images\":{\"large\":\"https://tse3.mm.bing.net/th?id=OVP.BbSKV8N1vyYv-3m8vyuCoQEsDh&pid=Api\",\"medium\":\"https://tse3.mm.bing.net/th?id=OVP.BbSKV8N1vyYv-3m8vyuCoQEsDh&pid=Api\",\"motion\":\"https://tse3.mm.bing.net/th?id=OM1.bsXxoMoJ9ZWQBw&pid=Api\",\"small\":\"https://tse3.mm.bing.net/th?id=OVP.BbSKV8N1vyYv-3m8vyuCoQEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-08-14T14:09:10.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":75408},\"title\":\"How To Install MetaGPT - Build A Startup With One Prompt!!\",\"uploader\":\"Matthew Berman\"},{\"content\":\"https://www.youtube.com/watch?v=pJwR5pv0_gs\",\"description\":\"Multi agent framework tutorial of MetaGPT & chatDev; Check the Hubspot x Jasper research of Using Generative AI to Scale Your Content Operations: https://offers.hubspot.com/generative-ai-for-content-operations?utm_source=youtube&utm_medium=social&utm_campaign=CR0087Sep2023_AIJason/partner_youtube \\ud83d\\udd17 Links - Follow me on twitter: https ...\",\"duration\":\"13:41\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/pJwR5pv0_gs?autoplay=1\",\"image_token\":\"18ac54a8e5144c74f2010219781c47c295099a6eed7479645733832910d19aec\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.LJ0SK8DLWjCcwVVh-PEcOwHgFo&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.LJ0SK8DLWjCcwVVh-PEcOwHgFo&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM2.PxMMOsse4Yi_FQ&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.LJ0SK8DLWjCcwVVh-PEcOwHgFo&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-09-08T11:36:03.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":167793},\"title\":\"Build AI agent workforce - Multi agent framework with MetaGPT & chatDev\",\"uploader\":\"AI Jason\"},{\"content\":\"https://www.youtube.com/watch?v=q16Gi9pTG_M\",\"description\":\"In this captivating video, we explore the core concept of MetaGPT, which centers on task distribution and coordination among individual GPT agents. Each agent is bestowed with specific roles that capitalize on their unique strengths and expertise. Imagine one GPT excelling in natural language understanding, while another showcases prowess in ...\",\"duration\":\"14:56\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/q16Gi9pTG_M?autoplay=1\",\"image_token\":\"bee3657ef83c9da2bc4ccfea770244e18958f5789a39d0136c3a049cc22a0e54\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.eiPUmQWRU1sE-01-x5Kn7gEsDh&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.eiPUmQWRU1sE-01-x5Kn7gEsDh&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM2.eWDmjf8nvrSrhw&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.eiPUmQWRU1sE-01-x5Kn7gEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-07-25T00:37:40.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":14365},\"title\":\"MetaGPT: Deploy POWERFUL Autonomous Ai Agents BETTER Than SUPERAGI! (Installation Tutorial)\",\"uploader\":\"WorldofAI\"},{\"content\":\"https://www.youtube.com/watch?v=nqZlTV_L6Ao\",\"description\":\"Welcome to our video review! \\ud83c\\udfa5 Dive into the world of MetaGPT, a revolutionary project that's redefining the boundaries of AI. \\ud83e\\udd16 Imagine having an entire engineering team - from CEO to QA - compacted into one AI system. Just input a prompt, and voila! You're handed everything from requirements, PRDs, to the actual code and tests. Let ...\",\"duration\":\"14:15\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/nqZlTV_L6Ao?autoplay=1\",\"image_token\":\"9d13b27084400da23ef8d8567bd6b5c8a3758d4129f2b28c3619c0e2e1ba8276\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.VBEy5DF-0BQshjEkqA9T0wHgFo&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.VBEy5DF-0BQshjEkqA9T0wHgFo&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM2.N7S3-wAngkj7VA&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.VBEy5DF-0BQshjEkqA9T0wHgFo&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-09-04T11:45:06.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":23248},\"title\":\"\\ud83d\\ude80 MetaGPT Setup: Launch a Startup with One \\u270d\\ufe0f Prompt!\",\"uploader\":\"Prompt Engineering\"},{\"content\":\"https://www.youtube.com/watch?v=VxhPcnsA7KA\",\"description\":\"Meet MetaGPT, MetaGPT is a complete Software Engineering organization at your disposal. MetaGPT employees autonomous AI agents specializing in the roles found in real Software Development companies. Deploying Autonomous GPT AI Product Managers, Architects, Project Managers and Engineers your software is developed for you and Documented! This ...\",\"duration\":\"8:49\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/VxhPcnsA7KA?autoplay=1\",\"image_token\":\"c56ab50565d7135c0d45f37ea4b70f565eced03024b608392498704c54b0fe66\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.RTXFEZ-JNqeIG3Bfi8B3UQEsDh&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.RTXFEZ-JNqeIG3Bfi8B3UQEsDh&pid=Api\",\"motion\":\"https://tse1.mm.bing.net/th?id=OM2.219b44Lsywj5Bg&pid=Api\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.RTXFEZ-JNqeIG3Bfi8B3UQEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-08-21T00:25:20.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":6190},\"title\":\"How To Install MetaGPT - Your own AI Software Company, Create Programs With a single Prompt!\",\"uploader\":\"StuffAboutStuff\"},{\"content\":\"https://www.youtube.com/watch?v=Xyws6iI-eH8\",\"description\":\"In this video, we unravel the magic at the core of MetaGPT, exploring its multi-agent framework and the groundbreaking December 15 update (v0.5.0) that introduced incremental development. Join us on this journey of innovation and efficiency in AI! \\ud83d\\udd25 Become a Patron (Private Discord): https://patreon.com/WorldofAi \\u2615 To help and Support me ...\",\"duration\":\"11:38\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/Xyws6iI-eH8?autoplay=1\",\"image_token\":\"db0651076b86c15566c0f032ab3e035fa65863cdf0b3bf46a18d10201bad1bab\",\"images\":{\"large\":\"https://tse3.mm.bing.net/th?id=OVP.X0OdKOGTJgwUw3Op_rmcewEsDh&pid=Api\",\"medium\":\"https://tse3.mm.bing.net/th?id=OVP.X0OdKOGTJgwUw3Op_rmcewEsDh&pid=Api\",\"motion\":\"https://tse3.mm.bing.net/th?id=OM2.-Hw5pO2PnG7h1g&pid=Api\",\"small\":\"https://tse3.mm.bing.net/th?id=OVP.X0OdKOGTJgwUw3Op_rmcewEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-12-23T21:22:36.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":7003},\"title\":\"MetaGPT HUGE Update: Autonomous AI Agents with Incremental Memory!\",\"uploader\":\"WorldofAI\"},{\"content\":\"https://www.youtube.com/watch?v=T_wBUpzxxPY\",\"description\":\"In this video i talk about this awesome project called MetaGPT in my video. Now, MetaGPT is like an all-in-one AI powerhouse. It can do everything from being a CEO to a QA tester for an engineering organization. And the cool thing is, you just give it a simple prompt, and it spits out everything you need - requirements, PRDs, code, and tests ...\",\"duration\":\"4:00\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/T_wBUpzxxPY?autoplay=1\",\"image_token\":\"ef14791d7faff848cb15177567e9f4f9c04ccae4fafc7ef7386e69df3a012010\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.EWCOFStB_tQza4SLrUA0AAEsDh&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.EWCOFStB_tQza4SLrUA0AAEsDh&pid=Api\",\"motion\":\"https://tse1.mm.bing.net/th?id=OM1.itG5pHJg6MKYzg_1696190983&pid=Api\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.EWCOFStB_tQza4SLrUA0AAEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-09-11T10:41:22.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":368},\"title\":\"MetaGPT Installation Guide: From Setup to Startup With One Prompt!\",\"uploader\":\"Py Man\"},{\"content\":\"https://www.youtube.com/watch?v=EgipcKPhqME\",\"description\":\"In this video I provide a great demo and overview of a project called MetaGPT. Have you ever wondered if each person in a development project (such as the project manager, developers, architects, QA testers, etc.) were all AI's and how they'd behave? MetaGPT is doing just that. Not only are all the docs, designs, and tasks delivered, but also a ...\",\"duration\":\"7:35\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/EgipcKPhqME?autoplay=1\",\"image_token\":\"624d4ccdb6d1605da1e388e85c9124957bcba9c70a11a575e751ba6fc09bc5f8\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.hG0c3nw7X-uz0gzUjnOVNwEsDh&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.hG0c3nw7X-uz0gzUjnOVNwEsDh&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM1.8F2lEMy1JlCKsQ_1698986522&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.hG0c3nw7X-uz0gzUjnOVNwEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-09-24T08:00:11.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":1587},\"title\":\"MetaGPT Tutorial | It builds an entire project (with working source code) with just one prompt!!\",\"uploader\":\"CraceCasts\"},{\"content\":\"https://www.youtube.com/watch?v=YtxMderNrzU\",\"description\":\"Subscribe to my Newsletter (My AI updates and news clearly explained): https://louisbouchard.substack.com/ References: Read the full article: https://www.louisbouchard.ai/metagpt/ Hong et al., 2023: MetaGPT, https://arxiv.org/pdf/2308.00352.pdf Code: https://github.com/geekan/MetaGPT/blob/main/README.md Twitter: https://twitter.com/Whats_AI ...\",\"duration\":\"7:38\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/YtxMderNrzU?autoplay=1\",\"image_token\":\"2e0774ace2e34bbe23ece04e80b7bb2ee976fd8ef7f53001e8f8b137763561dc\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.HP81CZ34ap22GZZG2l024QHgFo&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.HP81CZ34ap22GZZG2l024QHgFo&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM2.xArTjo5bOxSBhg&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.HP81CZ34ap22GZZG2l024QHgFo&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-08-27T15:05:12.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":9594},\"title\":\"MetaGPT: Redefining Multi-Agent Collaboration for Complex Tasks\",\"uploader\":\"What's AI by Louis Bouchard\"},{\"content\":\"https://www.youtube.com/watch?v=geLX30qax8Q\",\"description\":\"Dive into the world of autonomous agent swarms with our comprehensive Autonomous Agent Swarms Totorial! \\ud83c\\udf1f Whether you're a beginner or an AI enthusiast, this video will guide you through the fascinating process of creating and managing intelligent agent swarms using LangChain. Learn how to harness the power of collaborative AI agents for ...\",\"duration\":\"47:02\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/geLX30qax8Q?autoplay=1\",\"image_token\":\"9e9f6de14802f66e1364f3ef0c9a7973fcfab471dff810a91595a2ea60242256\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.0DNi9RS5yLCZHu9MXx5lQAEsDh&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.0DNi9RS5yLCZHu9MXx5lQAEsDh&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM.u64mpOw5ZNaPbg_1704713419&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.0DNi9RS5yLCZHu9MXx5lQAEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-11-12T00:29:27.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":12461},\"title\":\"Autonomous AI Agent Swarms | COMPLETE Tutorial\",\"uploader\":\"AspnAI\"}],\"vqd\":{\"metagpt\":\"4-118631859838297093459588814466521506726\"}});DDG.duckbar.loadModule('related_searches', {\"ads\":[],\"query\":\"metagpt\",\"queryEncoded\":\"metagpt\",\"response_type\":\"places\",\"results\":[{\"display_text\":\"metagpt sign in\",\"text\":\"metagpt sign in\",\"web_search_url\":\"?q=metagpt%20sign%20in\"},{\"display_text\":\"metagpt download\",\"text\":\"metagpt download\",\"web_search_url\":\"?q=metagpt%20download\"},{\"display_text\":\"metagpt vs autogpt\",\"text\":\"metagpt vs autogpt\",\"web_search_url\":\"?q=metagpt%20vs%20autogpt\"},{\"display_text\":\"metagpt examples\",\"text\":\"metagpt examples\",\"web_search_url\":\"?q=metagpt%20examples\"},{\"display_text\":\"metagpt windows\",\"text\":\"metagpt windows\",\"web_search_url\":\"?q=metagpt%20windows\"},{\"display_text\":\"metagpt arxiv\",\"text\":\"metagpt arxiv\",\"web_search_url\":\"?q=metagpt%20arxiv\"},{\"display_text\":\"tell me what is metagpt\",\"text\":\"tell me what is metagpt\",\"web_search_url\":\"?q=tell%20me%20what%20is%20metagpt\"},{\"display_text\":\"metagpt pdf\",\"text\":\"metagpt pdf\",\"web_search_url\":\"?q=metagpt%20pdf\"}],\"vqd\":{\"metagpt\":\"4-118631859838297093459588814466521506726\"}});if (DDG.pageLayout) DDG.pageLayout.initialize({\"mainline\":{\"items\":[[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"videos\"],[\"related_searches\"]]}}, { start: 0 });DDG.deep.emit(\"load:completed\");", + "curl-cffi-POST-https://duckduckgo.com-{\"data\": {\"q\": \"llm\"}}": "llm at DuckDuckGo
", + "curl-cffi-GET-https://links.duckduckgo.com/d.js-{\"params\": {\"bing_market\": \"wt-WT\", \"df\": null, \"ex\": \"-1\", \"kl\": \"wt-wt\", \"l\": \"wt-wt\", \"q\": \"llm\", \"s\": \"0\", \"sp\": \"0\", \"vqd\": \"4-36212277936736004277629252433802891730\"}}": "if (DDG.deep && DDG.deep.setUpstream) DDG.deep.setUpstream(\"bingv7aa\");DDG.deep.bn={'ivc':1};if (DDG.pageLayout) DDG.pageLayout.load('a',[{\"a\":\"\\u6d77\\u5916\\u30c8\\u30c3\\u30d7\\u6821\\u307810,000\\u4eba\\u4ee5\\u4e0a\\u306e\\u5408\\u683c\\u5b9f\\u7e3e!\\u307e\\u305a\\u306f\\u7121\\u6599\\u500b\\u5225\\u76f8\\u8ac7\\u3001\\u7121\\u6599\\u30a4\\u30d9\\u30f3\\u30c8\\u3078. \\u9078\\u3079\\u308b\\u5b66\\u7fd2\\u5f62\\u614b\\u3001\\u53d7\\u8b1b\\u671f\\u95933\\u5e74\\u3001\\u518d\\u53d7\\u8b1b\\u7121\\u6599\\u306e\\u30a2\\u30b4\\u30b9\\u3067\\u30b0\\u30ed\\u30fc\\u30d0\\u30eb\\u30ec\\u30d9\\u30eb\\u306e\\u30ad\\u30e3\\u30ea\\u30a2\\u3092\\u76ee\\u6307\\u305b!\",\"adext\":{\"callout\":{\"t\":\"\\u304d\\u3081\\u306e\\u7d30\\u304b\\u3044\\u6307\\u5c0e \\u00b7 \\u7d4c\\u9a13\\u3068\\u60c5\\u71b1\\u306b\\u3042\\u3075\\u308c\\u308b\\u8b1b\\u5e2b \\u00b7 \\u77ed\\u671f\\u9593\\u30b9\\u30b3\\u30a2UP\\u6cd5\\u3092\\u63d0\\u4f9b \\u00b7 \\u5c11\\u4eba\\u6570\\u306e\\u5b9f\\u8df5\\u6f14\\u7fd2\",\"tid\":\"4\"},\"filterlinks\":{\"l\":[],\"tid\":\"\"},\"sitelinks\":{\"l\":[{\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=agos.co.jp&ad_provider=bingv7aa&ad_type=txad&eddgt=obP7zXz7zpZHDybCoDxesg%3D%3D&rut=0775aea54a76bdc651a07b5b6d9bb0b5a3312b830116a0a5705f920eadce0a8d&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8YtC6eTayvxICgO_74gaNxDVUCUx3MSqhDzr%2DQGWoWU46I_SK7hUYitxw1bDkwu51N4R%2Dy2n%2DF_Z3diiXwWhVMScvGQLYOHkpzJlogFXTiR4vkRTEI6CXepxoBdTo7ZRbEHQEhLvaxEQc7HHcGBfvrIhV5UmO4EI5CnyEEmhFkhykgShvntmZi4sK2RdNtojVZjcZh_jLwFJhGr6O4xBoHNjWmJk%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuYWdvcy5jby5qcCUyZmluZm9ybWF0aW9uJTJmc291ZGFuLmh0bWwlM2Z1dG1fc291cmNlJTNkYmluZyVjMiVhMCUyNnV0bV9tZWRpdW0lM2RjcGMlMjZ1dG1fY2FtcGFpZ24lM2Rub3Rfc3l1eW91JTI2bXNjbGtpZCUzZDkxNjNmMTQ2ZjQwNTFlNjEwNzdkOTRlNTA5ZTljNTQyJTI2dXRtX3Rlcm0lM2RMTE0lMjZ1dG1fY29udGVudCUzZEtXRF9BTExfQUxfKExMTSk%26rlid%3D9163f146f4051e61077d94e509e9c542&vqd=4-301837748834523973528319863104123825131&iurl=%7B1%7DIG%3D6793BB4EFA564D10A45BB0C3C75BF04C%26CID%3D342CD9B7486D6452145CCDB1496D6555%26ID%3DDevEx%2C5064.1\",\"text\":\"\\u7121\\u6599\\u500b\\u5225\\u76f8\\u8ac7\"},{\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=agos.co.jp&ad_provider=bingv7aa&ad_type=txad&eddgt=obP7zXz7zpZHDybCoDxesg%3D%3D&rut=bd3f96c640d64876df3ee14fe038b68503cd63d36a1fd092aa33d3e738d4ed8c&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8yHdgbe16wB0x%2DcAPgvHZdDVUCUx70tji1zX3o7kwOuVJH76ae5KWFMlI2xXK47X50C5H7blNCrYkTCjolxW9T95HCiAsMjqqwkdd71fw%2Di12GNjj6a_x8xmsYgUv1SoUaHMS9mJF40HnjMi2osart3afpkZ1yVburNNhgqcOwg%2DXMgDWa%2DLVR%2Dt%2DwG_ZxijIuc87rPnYDGWI6M3y7Us1OIVOMRY%26u%3DaHR0cCUzYSUyZiUyZnd3dy5hZ29zLmNvLmpwJTJmcHJvZ3JhbSUyZiUzZnV0bV9zb3VyY2UlM2RiaW5nJWMyJWEwJTI2dXRtX21lZGl1bSUzZGNwYyUyNnV0bV9jYW1wYWlnbiUzZG5vdF9zeXV5b3UlMjZtc2Nsa2lkJTNkYWJjY2UzN2M4N2RmMTZjNjNiNTE4NmRmN2EzM2RiYzUlMjZ1dG1fdGVybSUzZExMTSUyNnV0bV9jb250ZW50JTNkS1dEX0FMTF9BTF8oTExNKQ%26rlid%3Dabcce37c87df16c63b5186df7a33dbc5&vqd=4-135094424682227864277222089879108223323&iurl=%7B1%7DIG%3D6793BB4EFA564D10A45BB0C3C75BF04C%26CID%3D342CD9B7486D6452145CCDB1496D6555%26ID%3DDevEx%2C5066.1\",\"text\":\"\\u30d7\\u30ed\\u30b0\\u30e9\\u30e0\\u7d39\\u4ecb\"},{\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=agos.co.jp&ad_provider=bingv7aa&ad_type=txad&eddgt=obP7zXz7zpZHDybCoDxesg%3D%3D&rut=2eb357c941584c2d37f902ddd1c08c859ed01f062ab3fb05a001faf0f72e6ba5&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8C54ez8bikjRXEwXnJwi9YDVUCUy8nH9%2DJAueBxXkb0K7ZCNC0iUGDL4ho5%2DSoNtD5viVDKN7ZH22nltAGg05iJ0ZuWgdIts%2DGgXJTkql6SPae7Qmp04T63VKixa%2DGPkNHV0IE2WaD1BTEMUqr91ygKbGPrQddZylBRsNDKI6Ohg5xJwTIHBIZLIc%2D2VktajIGg3mr7TywC9C8C404NhOGDS3izs%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuYWdvcy5jby5qcCUyZm9ubGluZXNlcnZpY2VzJTJmbW9kdWxlcyUyZmFnZW5kYXglMmZpbmRleC5waHAlM2ZvcCUzZGNhbCUyNnV0bV9zb3VyY2UlM2RiaW5nJWMyJWEwJTI2dXRtX21lZGl1bSUzZGNwYyUyNnV0bV9jYW1wYWlnbiUzZG5vdF9zeXV5b3UlMjZtc2Nsa2lkJTNkZjY5ZDIyYjcyNmE1MWRhZDQ0MTg0NzE0ZGI0OTk3MWUlMjZ1dG1fdGVybSUzZExMTSUyNnV0bV9jb250ZW50JTNkS1dEX0FMTF9BTF8oTExNKQ%26rlid%3Df69d22b726a51dad44184714db49971e&vqd=4-128396212371085491387335181864088230840&iurl=%7B1%7DIG%3D6793BB4EFA564D10A45BB0C3C75BF04C%26CID%3D342CD9B7486D6452145CCDB1496D6555%26ID%3DDevEx%2C5068.1\",\"text\":\"\\u7121\\u6599\\u30a4\\u30d9\\u30f3\\u30c8\"},{\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=agos.co.jp&ad_provider=bingv7aa&ad_type=txad&eddgt=obP7zXz7zpZHDybCoDxesg%3D%3D&rut=479b8c8e06853252a860df6f4f7b0021979d4a7d81cfe31b1fa267ba9bfa146b&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8NjJGPM715u8VUlRmw8zHUDVUCUw7uCpgewYW%2DimZqp8QeEMcJSAl25ZE2QP%2De2LLi0zNlmdSsmFlczgatCZw3wHznKksYZxIlU8DyVauuq_BlQ7Y_XHQN5FZwp1JVZ62qIViejaQ8jOUUWe5WlcQ_RlJzztAhEBmbtWJsPAdjkkG2_jriD6uq5jjLVwdj7zJvT%2DPdQaxmcV5d1uLOKlfTWWSqcM%26u%3DaHR0cCUzYSUyZiUyZnd3dy5hZ29zLmNvLmpwJTJmdXNlZnVsJTJmJTNmdXRtX3NvdXJjZSUzZGJpbmclYzIlYTAlMjZ1dG1fbWVkaXVtJTNkY3BjJTI2dXRtX2NhbXBhaWduJTNkbm90X3N5dXlvdSUyNm1zY2xraWQlM2Q0NWViYjRlZWE2M2YxZjk0ZTI1YWQxNGQ1YmQzOTFkNSUyNnV0bV90ZXJtJTNkTExNJTI2dXRtX2NvbnRlbnQlM2RLV0RfQUxMX0FMXyhMTE0p%26rlid%3D45ebb4eea63f1f94e25ad14d5bd391d5&vqd=4-297887522221861120640855135832921374674&iurl=%7B1%7DIG%3D6793BB4EFA564D10A45BB0C3C75BF04C%26CID%3D342CD9B7486D6452145CCDB1496D6555%26ID%3DDevEx%2C5070.1\",\"text\":\"\\u7559\\u5b66\\u304a\\u5f79\\u7acb\\u3061\\u60c5\\u5831\"}],\"tid\":\"9\\t11[10]\\t13[12]\\t15[14]\\t17[16]\",\"type\":\"SiteLink\"},\"smart\":{\"t\":\"\\u30b3\\u30fc\\u30b9: TOEFL(R)TEST\\u5bfe\\u7b56\\u30b3\\u30fc\\u30b9, IELTS\\u8a66\\u9a13\\u5bfe\\u7b56\\u30b3\\u30fc\\u30b9, GMAT(R)\\u8a66\\u9a13\\u5bfe\\u7b56\\u30b3\\u30fc\\u30b9\",\"tid\":\"8\"},\"tid\":\"1\"},\"ae\":{\"callout\":[\"\\u304d\\u3081\\u306e\\u7d30\\u304b\\u3044\\u6307\\u5c0e \\u00b7 \\u7d4c\\u9a13\\u3068\\u60c5\\u71b1\\u306b\\u3042\\u3075\\u308c\\u308b\\u8b1b\\u5e2b \\u00b7 \\u77ed\\u671f\\u9593\\u30b9\\u30b3\\u30a2UP\\u6cd5\\u3092\\u63d0\\u4f9b \\u00b7 \\u5c11\\u4eba\\u6570\\u306e\\u5b9f\\u8df5\\u6f14\\u7fd2\"]},\"c\":\"https://duckduckgo.com/y.js?ad_domain=agos.co.jp&ad_provider=bingv7aa&ad_type=txad&eddgt=obP7zXz7zpZHDybCoDxesg%3D%3D&rut=b63afcc493f34d7a7c7d3518e392551bed85e9ae7571c18b4dc955aaf8259616&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8rhXDjLYuOBw8iJkGNRsNfzVUCUwxbNLujGJigHwGI9U5xO6%2DITqhX%2DRxoJEeElFXLF7C9j%2DxBG6M752LwJ8JIWQMG9aHf9eRSn8J307_mnj%2DzyVlkx3nyY0oZxNIfHP8d_eF8Bl_Gv8mmnjESk_mCDLz9CtFNkGvFdusnGnhhSX20uHcFptCvdD5h78HZ7eC9J8%2DwA%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuYWdvcy5jby5qcCUyZmxhbmQlMmZsbG0lMmYlM2Z1dG1fc291cmNlJTNkYmluZyVjMiVhMCUyNnV0bV9tZWRpdW0lM2RjcGMlMjZ1dG1fY2FtcGFpZ24lM2Rub3Rfc3l1eW91JTI2bXNjbGtpZCUzZDA5ODZlN2Y3OTRiZTE4ZThhNWJjODI1NDY5NTJkZmI1JTI2dXRtX3Rlcm0lM2RMTE0lMjZ1dG1fY29udGVudCUzZEtXRF9BTExfQUxfKExMTSk%26rlid%3D0986e7f794be18e8a5bc82546952dfb5&vqd=4-174227029600136465336090119074482095864&iurl=%7B1%7DIG%3D6793BB4EFA564D10A45BB0C3C75BF04C%26CID%3D342CD9B7486D6452145CCDB1496D6555%26ID%3DDevEx%2C5058.1\",\"d\":\"agos.co.jp\",\"h\":0,\"i\":\"\",\"k\":0,\"m\":0,\"o\":\"\",\"p\":1,\"relevancy\":{\"abstract\":\"%E6%B5%B7%E5%A4%96%E3%83%88%E3%83%83%E3%83%97%E6%A0%A1%E3%81%B810%2C000%E4%BA%BA%E4%BB%A5%E4%B8%8A%E3%81%AE%E5%90%88%E6%A0%BC%E5%AE%9F%E7%B8%BE!%E3%81%BE%E3%81%9A%E3%81%AF%E7%84%A1%E6%96%99%E5%80%8B%E5%88%A5%E7%9B%B8%E8%AB%87%E3%80%81%E7%84%A1%E6%96%99%E3%82%A4%E3%83%99%E3%83%B3%E3%83%88%E3%81%B8.%20%E9%81%B8%E3%81%B9%E3%82%8B%E5%AD%A6%E7%BF%92%E5%BD%A2%E6%85%8B%E3%80%81%E5%8F%97%E8%AC%9B%E6%9C%9F%E9%96%933%E5%B9%B4%E3%80%81%E5%86%8D%E5%8F%97%E8%AC%9B%E7%84%A1%E6%96%99%E3%81%AE%E3%82%A2%E3%82%B4%E3%82%B9%E3%81%A7%E3%82%B0%E3%83%AD%E3%83%BC%E3%83%90%E3%83%AB%E3%83%AC%E3%83%99%E3%83%AB%E3%81%AE%E3%82%AD%E3%83%A3%E3%83%AA%E3%82%A2%E3%82%92%E7%9B%AE%E6%8C%87%E3%81%9B!\",\"adx_name\":\"none\",\"cq_retail\":\"high\",\"is_good_v10\":0,\"q\":\"llm\",\"q_words\":1,\"q_words_fuzzy\":0,\"q_words_in_ad\":\"0\",\"root_domain\":\"agos.co.jp\",\"start\":\"0\",\"title\":\"LLM%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E8%A9%A6%E9%A8%93%E5%AF%BE%E7%AD%96%E3%81%AA%E3%82%89%20%2D%20%E5%85%A8%E5%9B%BD%E3%83%88%E3%83%83%E3%83%97%E3%82%AF%E3%83%A9%E3%82%B9%E3%81%AE%E6%B5%B7%E5%A4%96%E7%95%99%E5%AD%A6%E5%AF%BE%E7%AD%96\"},\"s\":\"bingv7aa\",\"t\":\"LLM\\u306e\\u305f\\u3081\\u306e\\u8a66\\u9a13\\u5bfe\\u7b56\\u306a\\u3089 - \\u5168\\u56fd\\u30c8\\u30c3\\u30d7\\u30af\\u30e9\\u30b9\\u306e\\u6d77\\u5916\\u7559\\u5b66\\u5bfe\\u7b56\",\"tid\":\"1,4,8,9,11[10],13[12],15[14],17[16]\",\"u\":\"https://duckduckgo.com/y.js?ad_domain=agos.co.jp&ad_provider=bingv7aa&ad_type=txad&eddgt=obP7zXz7zpZHDybCoDxesg%3D%3D&rut=b63afcc493f34d7a7c7d3518e392551bed85e9ae7571c18b4dc955aaf8259616&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8rhXDjLYuOBw8iJkGNRsNfzVUCUwxbNLujGJigHwGI9U5xO6%2DITqhX%2DRxoJEeElFXLF7C9j%2DxBG6M752LwJ8JIWQMG9aHf9eRSn8J307_mnj%2DzyVlkx3nyY0oZxNIfHP8d_eF8Bl_Gv8mmnjESk_mCDLz9CtFNkGvFdusnGnhhSX20uHcFptCvdD5h78HZ7eC9J8%2DwA%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuYWdvcy5jby5qcCUyZmxhbmQlMmZsbG0lMmYlM2Z1dG1fc291cmNlJTNkYmluZyVjMiVhMCUyNnV0bV9tZWRpdW0lM2RjcGMlMjZ1dG1fY2FtcGFpZ24lM2Rub3Rfc3l1eW91JTI2bXNjbGtpZCUzZDA5ODZlN2Y3OTRiZTE4ZThhNWJjODI1NDY5NTJkZmI1JTI2dXRtX3Rlcm0lM2RMTE0lMjZ1dG1fY29udGVudCUzZEtXRF9BTExfQUxfKExMTSk%26rlid%3D0986e7f794be18e8a5bc82546952dfb5&vqd=4-174227029600136465336090119074482095864&iurl=%7B1%7DIG%3D6793BB4EFA564D10A45BB0C3C75BF04C%26CID%3D342CD9B7486D6452145CCDB1496D6555%26ID%3DDevEx%2C5058.1\"}], {\"page_load_url\":\"https://duckduckgo.com/y.js?ifu=%7B3%7Dappid%3D055AAD1BA669BEB8B048128DC89A107C678B527B%26rguid%3D413d05f2a7f54c8f8ad4685aa4a1d7d9&iurl=%7B2%7DIG%3D6793BB4EFA564D10A45BB0C3C75BF04C%26CID%3D342CD9B7486D6452145CCDB1496D6555%26Type%3DEvent.CPT%26DATA%3D0\",\"visibility_url\":\"https://duckduckgo.com/y.js?ivu=%7B4%7Dtype%3Dmv%26reqver%3D1.0%26rg%3D413d05f2a7f54c8f8ad4685aa4a1d7d9\"});DDG.duckbar.future_signal_tab({signal:'medium',from:'deep_answer'});DDG.duckbar.add({\"data\":{\"Abstract\":\"A large language model is a language model notable for its ability to achieve general-purpose language understanding and generation. LLMs acquire these abilities by learning statistical relationships from text documents during a computationally intensive self-supervised and semi-supervised training process. LLMs are artificial neural networks following a transformer architecture. They can be used for text generation by taking an input text and repeatedly predicting the next token or word. Up to 2020, fine tuning was the only way a model could be adapted to be able to accomplish specific tasks. Larger sized models, such as GPT-3, however, can be prompt-engineered to achieve similar results. They are thought to acquire knowledge about syntax, semantics and \\\"ontology\\\" inherent in human language corpora, but also inaccuracies and biases present in the corpora.\",\"AbstractSource\":\"Wikipedia\",\"AbstractText\":\"A large language model is a language model notable for its ability to achieve general-purpose language understanding and generation. LLMs acquire these abilities by learning statistical relationships from text documents during a computationally intensive self-supervised and semi-supervised training process. LLMs are artificial neural networks following a transformer architecture. They can be used for text generation by taking an input text and repeatedly predicting the next token or word. Up to 2020, fine tuning was the only way a model could be adapted to be able to accomplish specific tasks. Larger sized models, such as GPT-3, however, can be prompt-engineered to achieve similar results. They are thought to acquire knowledge about syntax, semantics and \\\"ontology\\\" inherent in human language corpora, but also inaccuracies and biases present in the corpora.\",\"AbstractURL\":\"https://en.wikipedia.org/wiki/Large_language_model\",\"Answer\":\"\",\"AnswerType\":\"\",\"Definition\":\"\",\"DefinitionSource\":\"\",\"DefinitionURL\":\"\",\"Entity\":\"\",\"Heading\":\"Large language model\",\"Image\":\"\",\"ImageHeight\":0,\"ImageIsLogo\":0,\"ImageWidth\":0,\"Infobox\":\"\",\"Redirect\":\"\",\"RelatedTopics\":[{\"FirstURL\":\"https://duckduckgo.com/Foundation_models\",\"Icon\":{\"Height\":\"\",\"URL\":\"\",\"Width\":\"\"},\"Result\":\"Foundation models - A foundation model is an AI model that is trained on broad data such that it can be applied across a wide range of use cases.\",\"Text\":\"Foundation models - A foundation model is an AI model that is trained on broad data such that it can be applied across a wide range of use cases.\"},{\"FirstURL\":\"https://duckduckgo.com/Generative_artificial_intelligence\",\"Icon\":{\"Height\":\"\",\"URL\":\"\",\"Width\":\"\"},\"Result\":\"Generative AI - Generative artificial intelligence is artificial intelligence capable of generating text, images, or other media, using generative models. Generative AI models learn the patterns and structure of their input training data and then generate new data that has similar characteristics.\",\"Text\":\"Generative AI - Generative artificial intelligence is artificial intelligence capable of generating text, images, or other media, using generative models. Generative AI models learn the patterns and structure of their input training data and then generate new data that has similar characteristics.\"},{\"FirstURL\":\"https://duckduckgo.com/c/Deep_learning\",\"Icon\":{\"Height\":\"\",\"URL\":\"\",\"Width\":\"\"},\"Result\":\"Deep learning\",\"Text\":\"Deep learning\"},{\"FirstURL\":\"https://duckduckgo.com/c/Natural_language_processing\",\"Icon\":{\"Height\":\"\",\"URL\":\"\",\"Width\":\"\"},\"Result\":\"Natural language processing\",\"Text\":\"Natural language processing\"}],\"Results\":[],\"Type\":\"A\",\"meta\":{\"attribution\":null,\"blockgroup\":null,\"created_date\":null,\"description\":\"Wikipedia\",\"designer\":null,\"dev_date\":null,\"dev_milestone\":\"live\",\"developer\":[{\"name\":\"DDG Team\",\"type\":\"ddg\",\"url\":\"http://www.duckduckhack.com\"}],\"example_query\":\"nikola tesla\",\"id\":\"wikipedia_fathead\",\"is_stackexchange\":null,\"js_callback_name\":\"wikipedia\",\"live_date\":null,\"maintainer\":{\"github\":\"duckduckgo\"},\"name\":\"Wikipedia\",\"perl_module\":\"DDG::Fathead::Wikipedia\",\"producer\":null,\"production_state\":\"online\",\"repo\":\"fathead\",\"signal_from\":\"wikipedia_fathead\",\"src_domain\":\"en.wikipedia.org\",\"src_id\":1,\"src_name\":\"Wikipedia\",\"src_options\":{\"directory\":\"\",\"is_fanon\":0,\"is_mediawiki\":1,\"is_wikipedia\":1,\"language\":\"en\",\"min_abstract_length\":\"20\",\"skip_abstract\":0,\"skip_abstract_paren\":0,\"skip_end\":\"0\",\"skip_icon\":0,\"skip_image_name\":0,\"skip_qr\":\"\",\"source_skip\":\"\",\"src_info\":\"\"},\"src_url\":null,\"status\":\"live\",\"tab\":\"About\",\"topic\":[\"productivity\"],\"unsafe\":0}},\"duckbar_topic\":\"About\",\"from\":\"deep_answer\",\"meta\":{\"attribution\":null,\"blockgroup\":null,\"created_date\":null,\"description\":\"Wikipedia\",\"designer\":null,\"dev_date\":null,\"dev_milestone\":\"live\",\"developer\":[{\"name\":\"DDG Team\",\"type\":\"ddg\",\"url\":\"http://www.duckduckhack.com\"}],\"example_query\":\"nikola tesla\",\"id\":\"wikipedia_fathead\",\"is_stackexchange\":null,\"js_callback_name\":\"wikipedia\",\"live_date\":null,\"maintainer\":{\"github\":\"duckduckgo\"},\"name\":\"Wikipedia\",\"perl_module\":\"DDG::Fathead::Wikipedia\",\"producer\":null,\"production_state\":\"online\",\"repo\":\"fathead\",\"signal_from\":\"wikipedia_fathead\",\"src_domain\":\"en.wikipedia.org\",\"src_id\":1,\"src_name\":\"Wikipedia\",\"src_options\":{\"directory\":\"\",\"is_fanon\":0,\"is_mediawiki\":1,\"is_wikipedia\":1,\"language\":\"en\",\"min_abstract_length\":\"20\",\"skip_abstract\":0,\"skip_abstract_paren\":0,\"skip_end\":\"0\",\"skip_icon\":0,\"skip_image_name\":0,\"skip_qr\":\"\",\"source_skip\":\"\",\"src_info\":\"\"},\"src_url\":null,\"status\":\"live\",\"tab\":\"About\",\"topic\":[\"productivity\"],\"unsafe\":0},\"model\":\"FatheadArticle\",\"pixel_id\":\"wikipedia_fathead_deep\",\"signal\":\"medium\",\"templates\":{\"detail\":\"info_detail\"}});DDG.deep.signalSummary = \"about:m,retail:h\";DDG.inject('DDG.Data.languages.resultLanguages', {\"en\":[\"https://en.wikipedia.org/wiki/Large_language_model\",\"https://en.wikipedia.org/wiki/Master_of_Laws\",\"https://www.lsac.org/discover-law/types-law-programs/llm-degree-programs\",\"https://llm-guide.com/what-is-an-llm\",\"https://hls.harvard.edu/graduate-program/ll-m-program/\",\"http://llm.lsac.org/\",\"https://hls.harvard.edu/graduate-program/graduate-program-admissions-and-financial-aid/ll-m-admissions/\",\"https://www.usnews.com/education/articles/getting-an-llm-degree-what-to-know\",\"https://law.stanford.edu/office-of-student-affairs/the-master-of-laws-llm-degree/\",\"https://gould.usc.edu/academics/degrees/online-llm/\",\"https://www.lawyeredu.org/LLM-degree/\",\"https://www.law.nyu.edu/llmjsd/master-of-laws\",\"https://gould.usc.edu/academics/degrees/llm/\",\"https://www.techtarget.com/whatis/definition/large-language-model-LLM\",\"https://aws.amazon.com/what-is/large-language-model/\",\"https://www.computerworld.com/article/3697649/what-are-large-language-models-and-how-are-they-used-in-generative-ai.html\",\"https://graduate.northeastern.edu/program/master-of-laws-llm-online-17868/\",\"https://www.law.northwestern.edu/academics/degree-programs/llms/\",\"https://www.gartner.com/en/information-technology/glossary/large-language-models-llm\",\"https://en.wikipedia.org/wiki/Wikipedia:Large_language_models\",\"https://www.elastic.co/what-is/large-language-models\",\"https://www.geeksforgeeks.org/large-language-model-llm/\",\"https://developers.google.com/machine-learning/resources/intro-llms\"]});DDG.deep.pageLayoutSummary = \"a1w5dic1w18r1,e1\";DDG.inject('DDG.Data.languages.adLanguages', {});if (DDG.pageLayout) DDG.pageLayout.load('d',[{\"a\":\"A large language model (LLM) is a language model notable for its ability to achieve general-purpose language understanding and generation. LLMs acquire these abilities by learning statistical relationships from text documents during a computationally intensive self-supervised and semi-supervised training process. LLMs are artificial neural networks following a transformer architecture.\",\"ae\":null,\"b\":\"w\\tWikipedia\\ten.wikipedia.org\",\"c\":\"https://en.wikipedia.org/wiki/Large_language_model\",\"d\":\"en.wikipedia.org/wiki/Large_language_model\",\"da\":\"en_wikipedia_queries,nlp_fathead,nlp_wiki\",\"h\":0,\"i\":\"en.wikipedia.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Large language model - Wikipedia\",\"u\":\"https://en.wikipedia.org/wiki/Large_language_model\"},{\"a\":\"A Master of Laws (M.L. or LL.M.; Latin: Magister Legum or Legum Magister) is an advanced postgraduate academic degree, pursued by those either holding an undergraduate academic law degree, a professional law degree, or an undergraduate degree in a related subject.In most jurisdictions, the LL.M. is the advanced professional degree for those usually already admitted into legal practice.\",\"ae\":null,\"b\":\"w\\tWikipedia\\ten.wikipedia.org\",\"c\":\"https://en.wikipedia.org/wiki/Master_of_Laws\",\"d\":\"en.wikipedia.org/wiki/Master_of_Laws\",\"da\":\"en_wikipedia_queries,nlp_fathead,nlp_wiki\",\"h\":0,\"i\":\"en.wikipedia.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Master of Laws - Wikipedia\",\"u\":\"https://en.wikipedia.org/wiki/Master_of_Laws\"},{\"a\":\"An LLM, or Master of Laws, is a graduate qualification in the field of law. The LLM was created for lawyers to expand their knowledge, study a specialized area of law, and gain international qualifications if they have earned a law degree outside the U.S. or Canada. If you're looking to advance your legal career or take the next step in your ...\",\"ae\":null,\"c\":\"https://www.lsac.org/discover-law/types-law-programs/llm-degree-programs\",\"d\":\"www.lsac.org/discover-law/types-law-programs/llm-degree-programs\",\"da\":\"\",\"h\":0,\"i\":\"www.lsac.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"LLM Degree | Masters of Laws | The Law School Admission Council\",\"u\":\"https://www.lsac.org/discover-law/types-law-programs/llm-degree-programs\"},{\"a\":\"The LLM - short for Master of Laws - is an internationally recognized postgraduate law degree that is usually completed in one year of full-time studies. It's different from a JD or an LLB, which are first law degrees and are generally required to practice law. Specialized LLMs can be found in tax law, business law, and other subjects.\",\"ae\":null,\"c\":\"https://llm-guide.com/what-is-an-llm\",\"d\":\"llm-guide.com/what-is-an-llm\",\"da\":\"\",\"h\":0,\"i\":\"llm-guide.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What is an LL.M.? | LLM GUIDE\",\"u\":\"https://llm-guide.com/what-is-an-llm\"},{\"a\":\"Learn about the LL.M. (Master of Laws) program at Harvard Law School, a one-year degree program for students from various legal systems and backgrounds. Find out the degree requirements, academic resources, and class profile of the LL.M. students.\",\"ae\":null,\"c\":\"https://hls.harvard.edu/graduate-program/ll-m-program/\",\"d\":\"hls.harvard.edu/graduate-program/ll-m-program/\",\"da\":\"\",\"h\":0,\"i\":\"hls.harvard.edu\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"LL.M. Program - Harvard Law School | Harvard Law School\",\"u\":\"https://hls.harvard.edu/graduate-program/ll-m-program/\"},{\"a\":\"LSAC offers services for various types of law programs offered by ABA-approved law schools, such as LLM, MCL, MLS, JM, MSLS, JSD, SJD, and DCL. Sign up now to search, apply, and credential assemble for over 130 law programs.\",\"ae\":null,\"c\":\"http://llm.lsac.org/\",\"d\":\"llm.lsac.org\",\"da\":\"\",\"h\":0,\"i\":\"llm.lsac.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Welcome to LLM & Other Law Programs | Law School Admission Council\",\"u\":\"http://llm.lsac.org/\"},{\"a\":\"Learn about the eligibility, criteria, and application process for the one-year LL.M. (Master of Laws) program at Harvard Law School, which typically includes 180 students from some 70 countries. Find out the tuition and financial aid options, and see sample applications and FAQs.\",\"ae\":null,\"c\":\"https://hls.harvard.edu/graduate-program/graduate-program-admissions-and-financial-aid/ll-m-admissions/\",\"d\":\"hls.harvard.edu/graduate-program/graduate-program-admissions-and-financial-aid/ll-m-admissions/\",\"da\":\"\",\"h\":0,\"i\":\"hls.harvard.edu\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"LL.M. Admissions - Harvard Law School | Harvard Law School\",\"u\":\"https://hls.harvard.edu/graduate-program/graduate-program-admissions-and-financial-aid/ll-m-admissions/\"},{\"a\":\"An LL.M. is geared towards those whom either have a J.D. degree and want to gain additional training in areas such as tax law or health-care law, or those who earned a degree outside of the U.S ...\",\"ae\":null,\"c\":\"https://www.usnews.com/education/articles/getting-an-llm-degree-what-to-know\",\"d\":\"www.usnews.com/education/articles/getting-an-llm-degree-what-to-know\",\"da\":\"\",\"e\":\"2022-12-28T00:00:00.0000000\",\"h\":0,\"i\":\"www.usnews.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Getting an LL.M. Degree: What to Know | Education | U.S. News\",\"u\":\"https://www.usnews.com/education/articles/getting-an-llm-degree-what-to-know\"},{\"a\":\"To obtain an LLM degree, students must complete at least 35 but no more than 45 approved quarter units of course work. At least 26 of these units must be in Law School courses; however, see below for the policies and limitations on enrolling in courses from elsewhere in the University, and see the section on the California or New York bar exam for special unit requirements for students ...\",\"ae\":null,\"c\":\"https://law.stanford.edu/office-of-student-affairs/the-master-of-laws-llm-degree/\",\"d\":\"law.stanford.edu/office-of-student-affairs/the-master-of-laws-llm-degree/\",\"da\":\"\",\"h\":0,\"i\":\"law.stanford.edu\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"The Master of Laws (LLM) Degree | Stanford Law School\",\"u\":\"https://law.stanford.edu/office-of-student-affairs/the-master-of-laws-llm-degree/\"},{\"a\":\"Earn a Master of Laws degree from a top-ranked law school in the U.S. with a part-time, flexible and interdisciplinary curriculum. Learn from world-class faculty, seasoned academics and policymakers, and join the global Trojan Family network of more than 15,000 law school alumni.\",\"ae\":null,\"c\":\"https://gould.usc.edu/academics/degrees/online-llm/\",\"d\":\"gould.usc.edu/academics/degrees/online-llm/\",\"da\":\"\",\"h\":0,\"i\":\"gould.usc.edu\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Master of Laws (LLM) - Online - USC Gould School of Law\",\"u\":\"https://gould.usc.edu/academics/degrees/online-llm/\"},{\"a\":\"LLM in Taxation. The Master of Laws (LLM) is the degree of choice for career advancement and international credibility, particularly in today's competitive and globally focused legal environment. Early- and mid-career lawyers pursue the LLM voluntarily when looking to expand their proficiency in a specific area of law.\",\"ae\":null,\"c\":\"https://www.lawyeredu.org/LLM-degree/\",\"d\":\"www.lawyeredu.org/LLM-degree/\",\"da\":\"\",\"h\":0,\"i\":\"www.lawyeredu.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What is an LLM | What is a Master of Laws - Lawyeredu.org\",\"u\":\"https://www.lawyeredu.org/LLM-degree/\"},{\"a\":\"Design Your Own LLM. You will choose from 300+ courses to plan a curriculum that meets your intellectual and professional interests. You can choose to specialize in one or two areas, or take a broad range of classes. You also will have the chance to write a paper in close consultation with a professor, or expand a typical research assignment into a master's thesis.\",\"ae\":null,\"c\":\"https://www.law.nyu.edu/llmjsd/master-of-laws\",\"d\":\"www.law.nyu.edu/llmjsd/master-of-laws\",\"da\":\"\",\"h\":0,\"i\":\"www.law.nyu.edu\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Master of Laws (LLM) | NYU School of Law - New York University\",\"u\":\"https://www.law.nyu.edu/llmjsd/master-of-laws\"},{\"a\":\"Learn about the Master of Laws (LLM) degree programs at USC Gould School of Law, which focus on the U.S. legal system and prepare students for leadership roles in law. Choose from various formats, eligibility criteria, and specialization tracks to suit your goals and interests.\",\"ae\":null,\"c\":\"https://gould.usc.edu/academics/degrees/llm/\",\"d\":\"gould.usc.edu/academics/degrees/llm/\",\"da\":\"\",\"h\":0,\"i\":\"gould.usc.edu\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Master of Laws (LLM) Degree Programs | USC Gould School of Law\",\"u\":\"https://gould.usc.edu/academics/degrees/llm/\"},{\"a\":\"A large language model (LLM) is a type of artificial intelligence ( AI) algorithm that uses deep learning techniques and massively large data sets to understand, summarize, generate and predict new content. The term generative AI also is closely connected with LLMs, which are, in fact, a type of generative AI that has been specifically ...\",\"ae\":null,\"b\":\"whatis\\tWhatIs.com\\twhatis.techtarget.com\",\"c\":\"https://www.techtarget.com/whatis/definition/large-language-model-LLM\",\"d\":\"www.techtarget.com/whatis/definition/large-language-model-LLM\",\"da\":\"\",\"h\":0,\"i\":\"www.techtarget.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What are Large Language Models? | Definition from TechTarget\",\"u\":\"https://www.techtarget.com/whatis/definition/large-language-model-LLM\"},{\"a\":\"Large language models (LLM) are very large deep learning models that are pre-trained on vast amounts of data. The underlying transformer is a set of neural networks that consist of an encoder and a decoder with self-attention capabilities. The encoder and decoder extract meanings from a sequence of text and understand the relationships between words and phrases in it.\",\"ae\":null,\"b\":\"a\\tAmazon.com\\twww.amazon.com\",\"c\":\"https://aws.amazon.com/what-is/large-language-model/\",\"d\":\"aws.amazon.com/what-is/large-language-model/\",\"da\":\"products\",\"h\":0,\"i\":\"aws.amazon.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What are Large Language Models? - LLM AI Explained - AWS\",\"u\":\"https://aws.amazon.com/what-is/large-language-model/\"},{\"a\":\"The LLM could come back with "cereal," or "rice," or "steak tartare." There's no 100% right answer, but there is a probability based on the data already ingested in the model. The ...\",\"ae\":null,\"c\":\"https://www.computerworld.com/article/3697649/what-are-large-language-models-and-how-are-they-used-in-generative-ai.html\",\"d\":\"www.computerworld.com/article/3697649/what-are-large-language-models-and-how-are-they-used-in-generative-ai.html\",\"da\":\"\",\"e\":\"2023-05-30T10:00:00.0000000\",\"h\":0,\"i\":\"www.computerworld.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What are LLMs, and how are they used in generative AI?\",\"u\":\"https://www.computerworld.com/article/3697649/what-are-large-language-models-and-how-are-they-used-in-generative-ai.html\"},{\"a\":\"Northeastern University offers a Master of Laws (LLM) program with a 100% online learning format option designed for internationally trained lawyers and U.S.-trained lawyers to enhance their practical skills and foundational knowledge of the ever-changing U.S. legal environment, and the global practice of law. The online LLM program positions students to take advantage of Northeastern ...\",\"ae\":null,\"c\":\"https://graduate.northeastern.edu/program/master-of-laws-llm-online-17868/\",\"d\":\"graduate.northeastern.edu/program/master-of-laws-llm-online-17868/\",\"da\":\"\",\"h\":0,\"i\":\"graduate.northeastern.edu\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Master of Laws LLM-Online - Graduate Programs\",\"u\":\"https://graduate.northeastern.edu/program/master-of-laws-llm-online-17868/\"},{\"a\":\"LLM Programs. Our LLM (Master of Law) degree programs expand students' knowledge of law and legal processes and provide opportunities for them to gain expertise in a specialized field of law. To apply, students must have a JD from an ABA-accredited law school or a comparable legal degree from a university outside of the United States.\",\"ae\":null,\"c\":\"https://www.law.northwestern.edu/academics/degree-programs/llms/\",\"d\":\"www.law.northwestern.edu/academics/degree-programs/llms/\",\"da\":\"\",\"h\":0,\"i\":\"www.law.northwestern.edu\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"LLM Programs - Northwestern University Pritzker School of Law\",\"u\":\"https://www.law.northwestern.edu/academics/degree-programs/llms/\"},{\"a\":\"Large Language Models (LLMs) A large language model (LLM) is a specialized type of artificial intelligence (AI) that has been trained on vast amounts of text to understand existing content and generate original content.\",\"ae\":null,\"c\":\"https://www.gartner.com/en/information-technology/glossary/large-language-models-llm\",\"d\":\"www.gartner.com/en/information-technology/glossary/large-language-models-llm\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Large Language Models (LLMs) - Gartner\",\"u\":\"https://www.gartner.com/en/information-technology/glossary/large-language-models-llm\"},{\"a\":\"Large language models have limited reliability, limited understanding, limited range, and hence need human supervision. While large language models (colloquially termed "AI chatbots" in some contexts) can be very useful, machine-generated text (much like human-generated text) can contain errors or flaws, or be outright useless.\",\"ae\":null,\"b\":\"w\\tWikipedia\\ten.wikipedia.org\",\"c\":\"https://en.wikipedia.org/wiki/Wikipedia:Large_language_models\",\"d\":\"en.wikipedia.org/wiki/Wikipedia:Large_language_models\",\"da\":\"en_wikipedia_queries,nlp_fathead,nlp_wiki\",\"h\":0,\"i\":\"en.wikipedia.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Wikipedia:Large language models - Wikipedia\",\"u\":\"https://en.wikipedia.org/wiki/Wikipedia:Large_language_models\"},{\"a\":\"Large language model definition. A large language model (LLM) is a deep learning algorithm that can perform a variety of natural language processing (NLP) tasks. Large language models use transformer models and are trained using massive datasets \\u2014 hence, large. This enables them to recognize, translate, predict, or generate text or other content.\",\"ae\":null,\"c\":\"https://www.elastic.co/what-is/large-language-models\",\"d\":\"www.elastic.co/what-is/large-language-models\",\"da\":\"\",\"h\":0,\"i\":\"www.elastic.co\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What is a large language model (LLM)? - Elastic\",\"u\":\"https://www.elastic.co/what-is/large-language-models\"},{\"a\":\"Difference Between NLP and LLM NLP is Natural Language Processing, a field of artificial intelligence (AI). It consists of the development of the algorithms. NLP is a broader field than LLM, which consists of algorithms and techniques. NLP rules two approaches i.e. Machine learning and the analyze language data. Applications of NLP are-\",\"ae\":null,\"c\":\"https://www.geeksforgeeks.org/large-language-model-llm/\",\"d\":\"www.geeksforgeeks.org/large-language-model-llm/\",\"da\":\"\",\"e\":\"2024-01-10T00:00:00.0000000\",\"h\":0,\"i\":\"www.geeksforgeeks.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What is a Large Language Model (LLM) - GeeksforGeeks\",\"u\":\"https://www.geeksforgeeks.org/large-language-model-llm/\"},{\"a\":\"Define key LLM concepts, including Transformers and self-attention. Describe the costs and benefits of LLMs, along with common use cases. What is a language model? A language model is a machine learning model that aims to predict and generate plausible language. Autocomplete is a language model, for example.\",\"ae\":null,\"c\":\"https://developers.google.com/machine-learning/resources/intro-llms\",\"d\":\"developers.google.com/machine-learning/resources/intro-llms\",\"da\":\"\",\"e\":\"2023-08-08T00:00:00.0000000\",\"h\":0,\"i\":\"developers.google.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Introduction to Large Language Models - Google Developers\",\"u\":\"https://developers.google.com/machine-learning/resources/intro-llms\"},{\"n\":\"/d.js?q=llm&kl=wt-wt&l=wt-wt&p=&s=23&ex=-1&ct=US&sp=0&vqd=4-36212277936736004277629252433802891730\"}]);DDG.duckbar.load('images');DDG.duckbar.load('news');DDG.duckbar.load('videos');DDG.duckbar.loadModule('related_searches', {\"ads\":[],\"query\":\"llm\",\"queryEncoded\":\"llm\",\"response_type\":\"places\",\"results\":[{\"display_text\":\"what does #llm mean\",\"text\":\"what does #llm mean\",\"web_search_url\":\"?q=what%20does%20%23llm%20mean\"},{\"display_text\":\"llm meaning\",\"text\":\"llm meaning\",\"web_search_url\":\"?q=llm%20meaning\"},{\"display_text\":\"llm meaning in law\",\"text\":\"llm meaning in law\",\"web_search_url\":\"?q=llm%20meaning%20in%20law\"},{\"display_text\":\"what is llm stand for\",\"text\":\"what is llm stand for\",\"web_search_url\":\"?q=what%20is%20llm%20stand%20for\"},{\"display_text\":\"llm in artificial intelligence\",\"text\":\"llm in artificial intelligence\",\"web_search_url\":\"?q=llm%20in%20artificial%20intelligence\"},{\"display_text\":\"full meaning of llm\",\"text\":\"full meaning of llm\",\"web_search_url\":\"?q=full%20meaning%20of%20llm\"},{\"display_text\":\"what is llm in law\",\"text\":\"what is llm in law\",\"web_search_url\":\"?q=what%20is%20llm%20in%20law\"},{\"display_text\":\"examples of llm models\",\"text\":\"examples of llm models\",\"web_search_url\":\"?q=examples%20of%20llm%20models\"}],\"vqd\":{\"llm\":\"4-36212277936736004277629252433802891730\"}});if (DDG.pageLayout) DDG.pageLayout.initialize({\"mainline\":{\"items\":[[\"ad\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"dictionary_definition\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"related_searches\"]]},\"sidebar\":{\"items\":[[\"wikipedia_fathead\"]]}}, { start: 0 });DDG.deep.emit(\"load:completed\");", + "curl-cffi-POST-https://duckduckgo.com-{\"data\": {\"q\": \"MetaGPT use cases\"}}": "MetaGPT use cases at DuckDuckGo
", + "curl-cffi-GET-https://links.duckduckgo.com/d.js-{\"params\": {\"bing_market\": \"wt-WT\", \"df\": null, \"ex\": \"-1\", \"kl\": \"wt-wt\", \"l\": \"wt-wt\", \"q\": \"MetaGPT use cases\", \"s\": \"0\", \"sp\": \"0\", \"vqd\": \"4-206455801954364851330794682843954609879\"}}": "if (DDG.deep && DDG.deep.setUpstream) DDG.deep.setUpstream(\"bingv7aa\");DDG.deep.bn={'ivc':1};if (DDG.pageLayout) DDG.pageLayout.load('a',[], {\"page_load_url\":\"https://duckduckgo.com/y.js?iurl=%7B2%7DIG%3DA7C157D7FB464F86BD78A7B80D28A7BC%26CID%3D2B7157406A406D2B1C8943466B3F6C14%26Type%3DEvent.CPT%26DATA%3D0\"});DDG.deep.signalSummary = \"\";DDG.inject('DDG.Data.languages.resultLanguages', {\"en\":[\"https://incubity.ambilio.com/metagpt-deep-dive-into-multi-agent-system-with-use-cases/\",\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"https://ts2.pl/en/metagpt-in-action-use-cases-across-industries/\",\"https://geekflare.com/metagpt-multi-agent-framework/\",\"https://docs.deepwisdom.ai/main/en/guide/get_started/introduction.html\",\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"https://aibusiness.com/nlp/metagpt-text-to-app-ai-simplifies-web-dev\",\"https://levelup.gitconnected.com/metagpt-the-future-of-multi-agent-collaboration-in-ai-a-brief-guide-fd4b4429336d\",\"https://github.com/geekan/MetaGPT\",\"https://docs.deepwisdom.ai/main/en/guide/get_started/quickstart.html\",\"https://medium.com/mlearning-ai/metagpt-multi-agent-harmony-for-complex-problem-solving-97bcb8f3fe94\",\"https://docs.deepwisdom.ai/enus/guide/tutorials/concepts.html\",\"https://medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\",\"https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/researcher.html\",\"https://github.com/PlaiD3/MetaGPT/blob/main/README.md\",\"https://generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\",\"https://medium.com/technology-hits/autogpt-langchain-deep-lake-metagpt-a-revolutionary-framework-for-building-advanced-ai-e2c579d86494\",\"https://gpt3demo.com/apps/metagpt\",\"https://docs.deepwisdom.ai/main/en/guide/tutorials/use_memories.html\",\"https://smythos.com/ai-agents/agent-comparison/metagpt-vs-autogen/\",\"https://analyticsindiamag.com/metagpt-realising-the-gpt-4-dream/\",\"https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/tutorial_assistant.html\",\"https://www.washingtonpost.com/technology/2024/01/04/nyt-ai-copyright-lawsuit-fair-use/\",\"https://blog.netwrix.com/2024/01/09/azure-storage/\",\"https://www.bloomberg.com/news/articles/2024-01-09/walmart-wmt-expands-rollout-of-generative-ai-shopping-search-tech\",\"https://health.ny.gov/press/releases/2024/docs/2024-01-08_masking_advisory.pdf\",\"https://www.bloomberg.com/news/articles/2024-01-10/lloyds-bank-manager-awarded-450-000-after-winning-case-over-racist-slur\",\"https://www.washingtonpost.com/world/2024/01/10/south-africa-israel-icj-genocide-case/\"]});DDG.deep.pageLayoutSummary = \"w29\";DDG.inject('DDG.Data.languages.adLanguages', {});if (DDG.pageLayout) DDG.pageLayout.load('d',[{\"a\":\"Some high-value business use cases where MetaGPT could be applied include: Software Development and Engineering: MetaGPT can streamline the software development lifecycle by orchestrating roles like Product Managers, Architects, Engineers, and QA Engineers. It can assist in requirements gathering, design, code generation, testing, and debugging ...\",\"ae\":null,\"c\":\"https://incubity.ambilio.com/metagpt-deep-dive-into-multi-agent-system-with-use-cases/\",\"d\":\"incubity.ambilio.com/metagpt-deep-dive-into-multi-agent-system-with-use-cases/\",\"da\":\"\",\"h\":0,\"i\":\"incubity.ambilio.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Deep Dive into Multi-Agent System with Use Cases\",\"u\":\"https://incubity.ambilio.com/metagpt-deep-dive-into-multi-agent-system-with-use-cases/\"},{\"a\":\"Published 4 months ago on September 11, 2023 By Aayush Mittal With Large Language Models (LLMs) like ChatGPT, OpenAI has witnessed a surge in enterprise and user adoption, currently raking in around $80 million in monthly revenue.\",\"ae\":null,\"c\":\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"d\":\"www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"da\":\"\",\"e\":\"2023-09-11T00:00:00.0000000\",\"h\":0,\"i\":\"www.unite.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\"u\":\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\"},{\"a\":\"MetaGPT in Action: Use-cases Across Industries MetaGPT, a powerful language model developed by OpenAI, has been making waves across various industries due to its versatility and ability to generate human-like text. As artificial intelligence (AI) continues to advance, the potential applications of MetaGPT are becoming increasingly apparent.\",\"ae\":null,\"c\":\"https://ts2.pl/en/metagpt-in-action-use-cases-across-industries/\",\"d\":\"ts2.pl/en/metagpt-in-action-use-cases-across-industries/\",\"da\":\"\",\"e\":\"2023-06-12T00:00:00.0000000\",\"h\":0,\"i\":\"ts2.pl\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT in Action: Use-cases Across Industries\",\"u\":\"https://ts2.pl/en/metagpt-in-action-use-cases-across-industries/\"},{\"a\":\"MetaGPT is a multi-agent framework that takes one-line inputs to produce APIs, user stories, data structures, competitive analysis, and more. GPT is the short form for Generative Pretrained Transformers. MetaGPT framework can behave as a product manager, software engineer, and architect.\",\"ae\":null,\"c\":\"https://geekflare.com/metagpt-multi-agent-framework/\",\"d\":\"geekflare.com/metagpt-multi-agent-framework/\",\"da\":\"\",\"e\":\"2023-09-18T00:00:00.0000000\",\"h\":0,\"i\":\"geekflare.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Is This the Best Multi-Agent Framework Yet? - Geekflare\",\"u\":\"https://geekflare.com/metagpt-multi-agent-framework/\"},{\"a\":\"Software Company Multi-Role Schematic MetaGPT's Abilities MetaGPT started as a software company, but its capabilities are not limited to that. You can use this multi-agent framework in your own scenario to build your own application. For details, you can refer to Researcher under Use Cases. Let's do it. Examples (fully generated by GPT-4)\",\"ae\":null,\"c\":\"https://docs.deepwisdom.ai/main/en/guide/get_started/introduction.html\",\"d\":\"docs.deepwisdom.ai/main/en/guide/get_started/introduction.html\",\"da\":\"\",\"h\":0,\"i\":\"docs.deepwisdom.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework | MetaGPT\",\"u\":\"https://docs.deepwisdom.ai/main/en/guide/get_started/introduction.html\"},{\"a\":\"MetaGPT is a multi-agent system that utilizes Large Language Models (LLMs) to perform complex tasks. ... MetaGPT has demonstrated its capabilities in various use cases, including developing a CLI ...\",\"ae\":null,\"c\":\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"d\":\"www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"da\":\"\",\"e\":\"2023-12-13T00:00:00.0000000\",\"h\":0,\"i\":\"www.straight.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"A Complete Guide to MetaGPT: The Best AI Agent Available Now\",\"u\":\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\"},{\"a\":\"MetaGPT builds microapps - applications designed for specific tasks or use cases. Examples include Facebook Messenger, the project management app Trello, and even Microsoft Word. It only generates web apps - which can be viewed on mobile or desktop browsers but won't run as native apps on Android or iOS.\",\"ae\":null,\"c\":\"https://aibusiness.com/nlp/metagpt-text-to-app-ai-simplifies-web-dev\",\"d\":\"aibusiness.com/nlp/metagpt-text-to-app-ai-simplifies-web-dev\",\"da\":\"\",\"e\":\"2023-08-07T00:00:00.0000000\",\"h\":0,\"i\":\"aibusiness.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Text-To-App AI Simplifies Web Dev\",\"u\":\"https://aibusiness.com/nlp/metagpt-text-to-app-ai-simplifies-web-dev\"},{\"a\":\"Here's a simple example of how to use MetaGPT: python startup.py "Write a cli snake game" # Use code review will cost more money, but will opt for better code quality. python startup.py "Write a cli snake game" --code_review True. ... Over the last few months, we have looked into around 100 agents with various use cases, studied SDKs and ...\",\"ae\":null,\"c\":\"https://levelup.gitconnected.com/metagpt-the-future-of-multi-agent-collaboration-in-ai-a-brief-guide-fd4b4429336d\",\"d\":\"levelup.gitconnected.com/metagpt-the-future-of-multi-agent-collaboration-in-ai-a-brief-guide-fd4b4429336d\",\"da\":\"\",\"e\":\"2023-08-09T00:00:00.0000000\",\"h\":0,\"i\":\"levelup.gitconnected.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Future of Multi-Agent Collaboration in AI (A Brief Guide)\",\"u\":\"https://levelup.gitconnected.com/metagpt-the-future-of-multi-agent-collaboration-in-ai-a-brief-guide-fd4b4429336d\"},{\"a\":\"MetaGPT: The Multi-Agent Framework Assign different roles to GPTs to form a collaborative software entity for complex tasks. MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc.\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT\",\"d\":\"github.com/geekan/MetaGPT\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework - GitHub\",\"u\":\"https://github.com/geekan/MetaGPT\"},{\"a\":\"You can check this by using:</span>\n<span class=\"pl-c\"><span class=\"pl-c\">#</span> You can use conda to initialize a new python env</span>\n<span class=\"pl-c\"><span class=\"pl-c\">#</span> conda create -n metagpt python=3.9</span>\n<span class=\"pl-c\"><span class=\"pl-c\">#</span> conda activate metagpt</span>\npython3 --version\n\n<span...\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT?search=1\",\"d\":\"github.com/geekan/MetaGPT?search=1\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework - GitHub\",\"u\":\"https://github.com/geekan/MetaGPT?search=1\"},{\"a\":\"Now, let's get started! We will create a team of agents to write software based on one line of our instruction. First, import off-the-shelf roles. python. import asyncio from metagpt.roles import ( Architect, Engineer, ProductManager, ProjectManager, ) from metagpt.team import Team. Next, initiate the team, equip it with agents, set their ...\",\"ae\":null,\"c\":\"https://docs.deepwisdom.ai/main/en/guide/get_started/quickstart.html\",\"d\":\"docs.deepwisdom.ai/main/en/guide/get_started/quickstart.html\",\"da\":\"\",\"h\":0,\"i\":\"docs.deepwisdom.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Quickstart | MetaGPT\",\"u\":\"https://docs.deepwisdom.ai/main/en/guide/get_started/quickstart.html\"},{\"a\":\"Stefan Silver \\u00b7 Follow Published in MLearning.ai \\u00b7 4 min read \\u00b7 Aug 9 4 Photo by Penfer on Unsplash Lately, there's been quite a buzz around automating problem-solving using multiagents...\",\"ae\":null,\"c\":\"https://medium.com/mlearning-ai/metagpt-multi-agent-harmony-for-complex-problem-solving-97bcb8f3fe94\",\"d\":\"medium.com/mlearning-ai/metagpt-multi-agent-harmony-for-complex-problem-solving-97bcb8f3fe94\",\"da\":\"\",\"e\":\"2023-08-09T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Multi-Agent Harmony for Complex Problem Solving\",\"u\":\"https://medium.com/mlearning-ai/metagpt-multi-agent-harmony-for-complex-problem-solving-97bcb8f3fe94\"},{\"a\":\"Concepts. After this tutorial, you will be able to: Understand MetaGPT's concept of agent and environment. How agents interact with each other and what a multi-agent collaboration may look like. The goal is to provide an intuitive and simplified explanation of the concepts so that users have a background to further explore the tutorial series.\",\"ae\":null,\"c\":\"https://docs.deepwisdom.ai/enus/guide/tutorials/concepts.html\",\"d\":\"docs.deepwisdom.ai/enus/guide/tutorials/concepts.html\",\"da\":\"\",\"h\":0,\"i\":\"docs.deepwisdom.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Concepts | MetaGPT\",\"u\":\"https://docs.deepwisdom.ai/enus/guide/tutorials/concepts.html\"},{\"a\":\"Capabilities/Use Case of MetaGPT MetaGPT has many potential applications and use cases in various fields and scenarios that involve multi-agent collaboration and coordination. Some of...\",\"ae\":null,\"c\":\"https://medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\",\"d\":\"medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\",\"da\":\"\",\"e\":\"2023-08-03T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: A Framework for Multi-Agent Meta Programming\",\"u\":\"https://medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\"},{\"a\":\"The metagpt.roles.researcher module provides a command-line interface for executing the functionalities of the Researcher. An example is as follows: bash. python3 -m metagpt.roles.researcher "dataiku vs. datarobot". Log output: log.txt Report output: dataiku vs. datarobot.md.\",\"ae\":null,\"c\":\"https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/researcher.html\",\"d\":\"docs.deepwisdom.ai/main/en/guide/use_cases/agent/researcher.html\",\"da\":\"\",\"h\":0,\"i\":\"docs.deepwisdom.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Researcher: Search Web and Write Reports | MetaGPT\",\"u\":\"https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/researcher.html\"},{\"a\":\"You can check this by using:</span>\npython --version\n\n<span class=\"pl-c\"><span class=\"pl-c\">#</span> Step 3: Clone the repository to your local machine, and install it.</span>\ngit clone https://github.com/geekan/metagpt\n<span class=\"pl-c1\">cd</span> metagpt\npython setup.py install</pre></div>\n<h3 tabindex=\"-1\" dir=\"auto\"><a id=\...\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/PlaiD3/MetaGPT/blob/main/README.md\",\"d\":\"github.com/PlaiD3/MetaGPT/blob/main/README.md\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Multi-Agent Meta Programming Framework - GitHub\",\"u\":\"https://github.com/PlaiD3/MetaGPT/blob/main/README.md\"},{\"a\":\"MetaGPT, as a cutting-edge framework, is not just a theoretical marvel but has been tested, showcasing its prowess in real-world applications. ... These articles cover a wide range of topics related to Generative AI, from introductions and use cases to exploring its potential and understanding its underlying layers. Happy reading!\",\"ae\":null,\"c\":\"https://generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\",\"d\":\"generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\",\"da\":\"translations\",\"e\":\"2023-08-14T00:00:00.0000000\",\"h\":0,\"i\":\"generativeai.pub\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Analyzing an exciting Generative AI research called MetaGPT.\",\"u\":\"https://generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\"},{\"a\":\"Here are 10 compelling use cases that demonstrate the vast potential of LangChain: Uses-Cases of LangChain. 1. Conversational AI and Chatbots ... MetaGPT, or multimodal Generative Pretrained ...\",\"ae\":null,\"c\":\"https://medium.com/technology-hits/autogpt-langchain-deep-lake-metagpt-a-revolutionary-framework-for-building-advanced-ai-e2c579d86494\",\"d\":\"medium.com/technology-hits/autogpt-langchain-deep-lake-metagpt-a-revolutionary-framework-for-building-advanced-ai-e2c579d86494\",\"da\":\"\",\"e\":\"2023-08-28T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"AutoGPT \\u2014 LangChain \\u2014 Deep Lake \\u2014 MetaGPT: A ... - Medium\",\"u\":\"https://medium.com/technology-hits/autogpt-langchain-deep-lake-metagpt-a-revolutionary-framework-for-building-advanced-ai-e2c579d86494\"},{\"a\":\"MetaGPT takes a one-line requirement as input and outputs user stories / competitive analysis/requirements/data structures / APIs / documents, etc. Internally, MetaGPT includes product managers/architects/project managers/engineers. It provides the entire process of a software company along with carefully orchestrated SOPs.\",\"ae\":null,\"c\":\"https://gpt3demo.com/apps/metagpt\",\"d\":\"gpt3demo.com/apps/metagpt\",\"da\":\"\",\"h\":0,\"i\":\"gpt3demo.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT | Discover AI use cases - GPT-3 Demo\",\"u\":\"https://gpt3demo.com/apps/metagpt\"},{\"a\":\"Retrieve memory. When recorded memories are needed, such as serving as context for a LLM call, you can use self.get_memories. The function definition is as follows: python. def get_memories(self, k=0) -> list [Message]: """A wrapper to return the most recent k memories of this role, return all when k=0""" return self.rc.memory.get (k=k) For ...\",\"ae\":null,\"c\":\"https://docs.deepwisdom.ai/main/en/guide/tutorials/use_memories.html\",\"d\":\"docs.deepwisdom.ai/main/en/guide/tutorials/use_memories.html\",\"da\":\"\",\"h\":0,\"i\":\"docs.deepwisdom.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Use Memories | MetaGPT\",\"u\":\"https://docs.deepwisdom.ai/main/en/guide/tutorials/use_memories.html\"},{\"a\":\"6 Conclusion Introduction Are you struggling to choose between MetaGPT Vs AutoGen? Comparing these two leading companies can help you make an informed decision. MetaGPT is a powerful tool designed for software developers, project managers, startups, technology companies, and AI enthusiasts.\",\"ae\":null,\"c\":\"https://smythos.com/ai-agents/agent-comparison/metagpt-vs-autogen/\",\"d\":\"smythos.com/ai-agents/agent-comparison/metagpt-vs-autogen/\",\"da\":\"\",\"h\":0,\"i\":\"smythos.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT Vs AutoGen: A Comprehensive Comparison\",\"u\":\"https://smythos.com/ai-agents/agent-comparison/metagpt-vs-autogen/\"},{\"a\":\"While some are just wrappers of OpenAI's APIs with added functionality like Forefront.ai or AnonChatGPT, others, like MemeCam or Bing Chat use the GPT-4 API to facilitate new use-cases altogether. OpenAI now needs to move faster, or risk their dream being stolen by others who are on the bleeding edge. Anirudh VK\",\"ae\":null,\"c\":\"https://analyticsindiamag.com/metagpt-realising-the-gpt-4-dream/\",\"d\":\"analyticsindiamag.com/metagpt-realising-the-gpt-4-dream/\",\"da\":\"\",\"e\":\"2023-04-26T00:00:00.0000000\",\"h\":0,\"i\":\"analyticsindiamag.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT \\u2014 Realising the GPT-4 Dream - Analytics India Magazine\",\"u\":\"https://analyticsindiamag.com/metagpt-realising-the-gpt-4-dream/\"},{\"a\":\"Override the _act method. The _act method is responsible for executing the action.Use todo = self.rc.todo to get the next action to be executed from the context, and then execute the run method of the action.Here, it first obtains the tutorial directory structure through WriteDirectory, then chunks the directory, generates a WriteContent action for each chunk, and initializes the newly added ...\",\"ae\":null,\"c\":\"https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/tutorial_assistant.html\",\"d\":\"docs.deepwisdom.ai/main/en/guide/use_cases/agent/tutorial_assistant.html\",\"da\":\"\",\"h\":0,\"i\":\"docs.deepwisdom.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Tutorial Assistant: Generate technology tutorial | MetaGPT\",\"u\":\"https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/tutorial_assistant.html\"},{\"a\":\"AI's future could hinge on one thorny legal question. A lawsuit accuses OpenAI and Microsoft of violating the New York Times's copyright. But the law is anything but clear. By Will Oremus. and ...\",\"ae\":null,\"c\":\"https://www.washingtonpost.com/technology/2024/01/04/nyt-ai-copyright-lawsuit-fair-use/\",\"d\":\"www.washingtonpost.com/technology/2024/01/04/nyt-ai-copyright-lawsuit-fair-use/\",\"da\":\"news,translations\",\"e\":\"2024-01-04T12:01:54.0000000\",\"h\":0,\"i\":\"www.washingtonpost.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"AI copyright lawsuit hinges on the legal concept of 'fair use' - The ...\",\"u\":\"https://www.washingtonpost.com/technology/2024/01/04/nyt-ai-copyright-lawsuit-fair-use/\"},{\"a\":\"Here are some common use cases for Azure Table Storage: Centralized storage of logs, telemetry data and monitoring data. Storage of catalog and shopping cart data for e-commerce applications. Scalable task scheduling and metadata storage. Storage of sensory data and IoT telemetry data.\",\"ae\":null,\"c\":\"https://blog.netwrix.com/2024/01/09/azure-storage/\",\"d\":\"blog.netwrix.com/2024/01/09/azure-storage/\",\"da\":\"translations\",\"e\":\"2024-01-09T00:00:00.0000000\",\"h\":0,\"i\":\"blog.netwrix.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Understanding Six Popular Azure Storage Types and Their Use Cases\",\"u\":\"https://blog.netwrix.com/2024/01/09/azure-storage/\"},{\"a\":\"January 10, 2024 at 8:10 AM PST. Walmart Inc. opened up access to a generative artificial intelligence tool that allows shoppers to search for products by specific use cases, rather than look up ...\",\"ae\":null,\"c\":\"https://www.bloomberg.com/news/articles/2024-01-09/walmart-wmt-expands-rollout-of-generative-ai-shopping-search-tech\",\"d\":\"www.bloomberg.com/news/articles/2024-01-09/walmart-wmt-expands-rollout-of-generative-ai-shopping-search-tech\",\"da\":\"news,translations\",\"e\":\"2024-01-09T16:10:00.0000000\",\"h\":0,\"i\":\"www.bloomberg.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Walmart Expands Rollout of Generative AI Shopping Search, Tech\",\"u\":\"https://www.bloomberg.com/news/articles/2024-01-09/walmart-wmt-expands-rollout-of-generative-ai-shopping-search-tech\"},{\"a\":\"The purpose of this advisory is to alert healthcare providers and facilities to substantial increases in cases of influenza and COVID-19, at least partially driven by an emerging SARS-CoV-2 variant, and to recommend that healthcare and residential facilities advocate strongly for the use of masks within their facility to prevent transmission\",\"ae\":null,\"c\":\"https://health.ny.gov/press/releases/2024/docs/2024-01-08_masking_advisory.pdf\",\"d\":\"health.ny.gov/press/releases/2024/docs/2024-01-08_masking_advisory.pdf\",\"da\":\"translations\",\"e\":\"2024-01-08T00:00:00.0000000\",\"h\":0,\"i\":\"health.ny.gov\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"PDF Health Advisory: Nys Department of Health Recommends Masking in ...\",\"u\":\"https://health.ny.gov/press/releases/2024/docs/2024-01-08_masking_advisory.pdf\"},{\"a\":\"2:29. The ex- Lloyds Banking Group Plc manager who won his unfair dismissal case over his use of a racist slur was awarded more than \\u00a3450,000 ($572,560) from an employment tribunal that said he ...\",\"ae\":null,\"c\":\"https://www.bloomberg.com/news/articles/2024-01-10/lloyds-bank-manager-awarded-450-000-after-winning-case-over-racist-slur\",\"d\":\"www.bloomberg.com/news/articles/2024-01-10/lloyds-bank-manager-awarded-450-000-after-winning-case-over-racist-slur\",\"da\":\"news,translations\",\"e\":\"2024-01-10T13:25:00.0000000\",\"h\":0,\"i\":\"www.bloomberg.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Lloyds Bank Manager Awarded \\u00a3450,000 After Winning Case Over Racist ...\",\"u\":\"https://www.bloomberg.com/news/articles/2024-01-10/lloyds-bank-manager-awarded-450-000-after-winning-case-over-racist-slur\"},{\"a\":\"The ICJ case adds to international pressure on Israel to scale back or end its war against Hamas, which health officials in Gaza say has killed more than 23,000 people \\u2014 many of them women and ...\",\"ae\":null,\"c\":\"https://www.washingtonpost.com/world/2024/01/10/south-africa-israel-icj-genocide-case/\",\"d\":\"www.washingtonpost.com/world/2024/01/10/south-africa-israel-icj-genocide-case/\",\"da\":\"news,translations\",\"e\":\"2024-01-10T22:24:00.0000000\",\"h\":0,\"i\":\"www.washingtonpost.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What to know about the genocide case against Israel at the ICJ\",\"u\":\"https://www.washingtonpost.com/world/2024/01/10/south-africa-israel-icj-genocide-case/\"},{\"n\":\"/d.js?q=MetaGPT%20use%20cases&kl=wt-wt&l=wt-wt&p=&s=29&ex=-1&ct=US&sp=0&vqd=4-206455801954364851330794682843954609879\"}]);DDG.duckbar.load('images');DDG.duckbar.load('news');DDG.duckbar.load('videos');DDG.duckbar.loadModule('related_searches');if (DDG.pageLayout) DDG.pageLayout.initialize({\"mainline\":{\"items\":[[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"]]}}, { start: 0 });DDG.deep.emit(\"load:completed\");", + "curl-cffi-POST-https://duckduckgo.com-{\"data\": {\"q\": \"The roadmap of MetaGPT\"}}": "The roadmap of MetaGPT at DuckDuckGo
", + "curl-cffi-GET-https://links.duckduckgo.com/d.js-{\"params\": {\"bing_market\": \"wt-WT\", \"df\": null, \"ex\": \"-1\", \"kl\": \"wt-wt\", \"l\": \"wt-wt\", \"q\": \"The roadmap of MetaGPT\", \"s\": \"0\", \"sp\": \"0\", \"vqd\": \"4-25941261128344049410840372626152530092\"}}": "if (DDG.deep && DDG.deep.setUpstream) DDG.deep.setUpstream(\"bingv7aa\");DDG.deep.bn={'ivc':1};if (DDG.pageLayout) DDG.pageLayout.load('a',[], {\"page_load_url\":\"https://duckduckgo.com/y.js?iurl=%7B2%7DIG%3DF478763C5197469DB7B1E366C8182CF2%26CID%3D192D84C7D0B167C5000690C1D1D466C6%26Type%3DEvent.CPT%26DATA%3D0\"});DDG.deep.signalSummary = \"\";DDG.inject('DDG.Data.languages.resultLanguages', {\"en\":[\"https://github.com/geekan/MetaGPT/blob/main/docs/ROADMAP.md\",\"https://github.com/geekan/MetaGPT\",\"https://www.almabetter.com/bytes/articles/metagpt\",\"https://lablab.ai/blog/this-week-in-ai-exploring-the-latest-from-metagpt-and-gpt4-and-more\",\"https://arxiv.org/abs/2308.00352\",\"https://github.com/geekan/MetaGPT/blob/main/README.md\",\"https://github.com/PlaiD3/MetaGPT/blob/main/README.md\",\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"https://www.linkedin.com/pulse/metagpt-important-conceptual-advance-multi-agent-systems-brad-edwards\",\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"https://generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\",\"https://docs.deepwisdom.ai/main/en/guide/get_started/introduction.html\",\"https://geekflare.com/metagpt-multi-agent-framework/\",\"https://www.marktechpost.com/2023/08/09/meet-metagpt-the-open-source-ai-framework-that-transforms-gpts-into-engineers-architects-and-managers/\",\"https://www.louisbouchard.ai/metagpt/\",\"https://pypi.org/project/metagpt/\",\"https://www.reddit.com/r/ChatGPT/comments/14qhn00/metagpt_the_roadmap_has_been_released_come_and/\",\"https://medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\",\"https://xthemadgenius.medium.com/how-to-use-metagpt-to-operate-as-a-full-engineering-team-c0f6e53c1dc3\",\"https://medium.com/@smraiyyan/metagpt-unleashed-crafting-your-virtual-software-company-from-scratch-6ea60cd70da1\",\"https://github.com/Ditto190/MetaGPT/blob/main/docs/ROADMAP.md\"],\"zh-CN\":[\"https://zhuanlan.zhihu.com/p/677608276\"]});DDG.deep.pageLayoutSummary = \"w1i1w4v1w18\";DDG.inject('DDG.Data.languages.adLanguages', {});if (DDG.pageLayout) DDG.pageLayout.load('d',[{\"a\":\"MetaGPT is an open source framework for building innovative AI powered applications with minimal coding. It leverages the power of GPT-3 and other models to generate various software artifacts from natural language inputs. Learn how to use MetaGPT and contribute to its development in this roadmap.\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT/blob/main/docs/ROADMAP.md\",\"d\":\"github.com/geekan/MetaGPT/blob/main/docs/ROADMAP.md\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Roadmap - GitHub\",\"u\":\"https://github.com/geekan/MetaGPT/blob/main/docs/ROADMAP.md\"},{\"a\":\"MetaGPT: The Multi-Agent Framework Assign different roles to GPTs to form a collaborative software entity for complex tasks. MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc.\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT\",\"d\":\"github.com/geekan/MetaGPT\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework - GitHub\",\"u\":\"https://github.com/geekan/MetaGPT\"},{\"a\":\"Understanding MetaGPT MetaGPT, a concept originating from a research paper that received significant attention, represents a leap forward in Artificial Intelligence, specifically in multi-agent collaboration using large language models (LLMs).\",\"ae\":null,\"c\":\"https://www.almabetter.com/bytes/articles/metagpt\",\"d\":\"www.almabetter.com/bytes/articles/metagpt\",\"da\":\"\",\"e\":\"2023-08-28T00:00:00.0000000\",\"h\":0,\"i\":\"www.almabetter.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Future of Multi-Agent Collaboration in AI\",\"u\":\"https://www.almabetter.com/bytes/articles/metagpt\"},{\"a\":\"MetaGPT is a groundbreaking multi-agent framework that is transforming the way software development is approached. By taking a single line of requirement as input, MetaGPT outputs a comprehensive array of development components, including user stories, competitive analysis, requirements, data structures, APIs, and documents.\",\"ae\":null,\"c\":\"https://lablab.ai/blog/this-week-in-ai-exploring-the-latest-from-metagpt-and-gpt4-and-more\",\"d\":\"lablab.ai/blog/this-week-in-ai-exploring-the-latest-from-metagpt-and-gpt4-and-more\",\"da\":\"\",\"e\":\"2023-08-11T00:00:00.0000000\",\"h\":0,\"i\":\"lablab.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"This Week in AI: Exploring the Latest from MetaGPT and GPT-4 and more..\",\"u\":\"https://lablab.ai/blog/this-week-in-ai-exploring-the-latest-from-metagpt-and-gpt4-and-more\"},{\"a\":\"MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-based multi-agent systems.\",\"ae\":null,\"b\":\"arx\\tarXiv.org\\tarxiv.org\",\"c\":\"https://arxiv.org/abs/2308.00352\",\"d\":\"arxiv.org/abs/2308.00352\",\"da\":\"translations\",\"e\":\"2023-08-01T00:00:00.0000000\",\"h\":0,\"i\":\"arxiv.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework\",\"u\":\"https://arxiv.org/abs/2308.00352\"},{\"a\":\"MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc. \n Internally, MetaGPT includes product managers / architects / project managers / engineers.\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT/blob/main/README.md\",\"d\":\"github.com/geekan/MetaGPT/blob/main/README.md\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework - GitHub\",\"u\":\"https://github.com/geekan/MetaGPT/blob/main/README.md\"},{\"a\":\"arXiv.org\",\"ae\":null,\"b\":\"arx\\tarXiv.org\\tarxiv.org\",\"c\":\"https://arxiv.org/pdf/2308.00352.pdf\",\"d\":\"arxiv.org/pdf/2308.00352.pdf\",\"da\":\"translations\",\"h\":0,\"i\":\"arxiv.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"PDF arXiv.org\",\"u\":\"https://arxiv.org/pdf/2308.00352.pdf\"},{\"a\":\"MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc. \n; Internally, MetaGPT includes product managers / architects / project managers / engineers. It provides the entire process of a software company along with carefully orchestrated SOPs.\n \n\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/PlaiD3/MetaGPT/blob/main/README.md\",\"d\":\"github.com/PlaiD3/MetaGPT/blob/main/README.md\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Multi-Agent Meta Programming Framework - GitHub\",\"u\":\"https://github.com/PlaiD3/MetaGPT/blob/main/README.md\"},{\"a\":\"MetaGPT's architecture is divided into two layers: the Foundational Components Layer and the Collaboration Layer. Foundational Components Layer: This layer focuses on individual agent operations and facilitates system-wide information exchange. It introduces core building blocks such as Environment, Memory, Roles, Actions, and Tools.\",\"ae\":null,\"c\":\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"d\":\"www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"da\":\"\",\"e\":\"2023-09-11T00:00:00.0000000\",\"h\":0,\"i\":\"www.unite.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\"u\":\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\"},{\"a\":\"Published Aug 6, 2023 + Follow Recent advances in large language models (LLMs) have opened up new opportunities for developing intelligent software agents capable of replicating human-level...\",\"ae\":null,\"b\":\"li\\tLinkedIn\\twww.linkedin.com\",\"c\":\"https://www.linkedin.com/pulse/metagpt-important-conceptual-advance-multi-agent-systems-brad-edwards\",\"d\":\"www.linkedin.com/pulse/metagpt-important-conceptual-advance-multi-agent-systems-brad-edwards\",\"da\":\"\",\"e\":\"2023-08-06T00:00:00.0000000\",\"h\":0,\"i\":\"www.linkedin.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Important Conceptual Advance in Multi-Agent Systems - LinkedIn\",\"u\":\"https://www.linkedin.com/pulse/metagpt-important-conceptual-advance-multi-agent-systems-brad-edwards\"},{\"a\":\"1. Enhanced Operational Efficiency. MetaGPT is designed to store, retrieve, and share information at varying levels, reducing redundancy and enhancing operational efficiency. This means that ...\",\"ae\":null,\"c\":\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"d\":\"www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"da\":\"\",\"e\":\"2023-12-13T00:00:00.0000000\",\"h\":0,\"i\":\"www.straight.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"A Complete Guide to MetaGPT: The Best AI Agent Available Now\",\"u\":\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\"},{\"a\":\"The MetaGPT approach showcases its ability to decompose highlevel tasks into detailed actionable components handled by distinct roles (ProductManager, Architect, ProjectManager, Engineer, QA Engineer), thereby facilitating role-specific expertise and coordination. This methodology mirrors human software development teams.\",\"ae\":null,\"c\":\"https://generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\",\"d\":\"generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\",\"da\":\"translations\",\"e\":\"2023-08-14T00:00:00.0000000\",\"h\":0,\"i\":\"generativeai.pub\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Analyzing an exciting Generative AI research called MetaGPT.\",\"u\":\"https://generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\"},{\"a\":\"Internally, MetaGPT includes product managers / architects / project managers / engineers. It provides the entire process of a software company along with carefully orchestrated SOPs. Code = SOP (Team) is the core philosophy. We materialize SOP and apply it to teams composed of LLMs. Software Company Multi-Role Schematic.\",\"ae\":null,\"c\":\"https://docs.deepwisdom.ai/main/en/guide/get_started/introduction.html\",\"d\":\"docs.deepwisdom.ai/main/en/guide/get_started/introduction.html\",\"da\":\"\",\"h\":0,\"i\":\"docs.deepwisdom.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework | MetaGPT\",\"u\":\"https://docs.deepwisdom.ai/main/en/guide/get_started/introduction.html\"},{\"a\":\"MetaGPT is a multi-agent framework that takes one-line inputs to produce APIs, user stories, data structures, competitive analysis, and more. GPT is the short form for Generative Pretrained Transformers. MetaGPT framework can behave as a product manager, software engineer, and architect. This framework can act as an entire software company with ...\",\"ae\":null,\"c\":\"https://geekflare.com/metagpt-multi-agent-framework/\",\"d\":\"geekflare.com/metagpt-multi-agent-framework/\",\"da\":\"\",\"e\":\"2023-09-18T00:00:00.0000000\",\"h\":0,\"i\":\"geekflare.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Is This the Best Multi-Agent Framework Yet? - Geekflare\",\"u\":\"https://geekflare.com/metagpt-multi-agent-framework/\"},{\"a\":\"MetaGPT manages far more software complexity than GPT-3.5 or other open-source frameworks like AutoGPT and AgentVerse, measured by lines of produced code. Additionally, MetaGPT generates high-quality requirement papers, design artifacts, flowcharts, and interface specifications throughout the automated end-to-end process. ...\",\"ae\":null,\"c\":\"https://www.marktechpost.com/2023/08/09/meet-metagpt-the-open-source-ai-framework-that-transforms-gpts-into-engineers-architects-and-managers/\",\"d\":\"www.marktechpost.com/2023/08/09/meet-metagpt-the-open-source-ai-framework-that-transforms-gpts-into-engineers-architects-and-managers/\",\"da\":\"translations\",\"e\":\"2023-08-09T00:00:00.0000000\",\"h\":0,\"i\":\"www.marktechpost.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Meet MetaGPT: The Open-Source AI Framework That Transforms GPTs into ...\",\"u\":\"https://www.marktechpost.com/2023/08/09/meet-metagpt-the-open-source-ai-framework-that-transforms-gpts-into-engineers-architects-and-managers/\"},{\"a\":\"MetaGPT is a new paper and open-source work that is making a lot of noise on GitHub! The researchers developed a new framework for combining or chaining large language models and mitigating hallucination risks by integrating human standardized operating procedures (SOPs) into the chaining process. This new design scheme allows the system to ...\",\"ae\":null,\"c\":\"https://www.louisbouchard.ai/metagpt/\",\"d\":\"www.louisbouchard.ai/metagpt/\",\"da\":\"\",\"e\":\"2023-08-27T00:00:00.0000000\",\"h\":0,\"i\":\"www.louisbouchard.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Mitigating AI Hallucinations: Exploring MetaGPT's Collaborative Framework\",\"u\":\"https://www.louisbouchard.ai/metagpt/\"},{\"a\":\"MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc. Internally, MetaGPT includes product managers / architects / project managers / engineers. It provides the entire process of a software company along with carefully orchestrated SOPs.\",\"ae\":null,\"c\":\"https://pypi.org/project/metagpt/\",\"d\":\"pypi.org/project/metagpt/\",\"da\":\"\",\"e\":\"2024-01-10T00:00:00.0000000\",\"h\":0,\"i\":\"pypi.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"metagpt \\u00b7 PyPI\",\"u\":\"https://pypi.org/project/metagpt/\"},{\"a\":\"Hey u/embessoaat, if your post is a ChatGPT conversation screenshot, please reply with the conversation link or prompt. Thanks! We have a public discord server.There's a free Chatgpt bot, Open Assistant bot (Open-source model), AI image generator bot, Perplexity AI bot, \\ud83e\\udd16 GPT-4 bot (Now with Visual capabilities (cloud vision)!) and channel for latest prompts.\",\"ae\":null,\"b\":\"r\\tReddit\\twww.reddit.com\",\"c\":\"https://www.reddit.com/r/ChatGPT/comments/14qhn00/metagpt_the_roadmap_has_been_released_come_and/\",\"d\":\"www.reddit.com/r/ChatGPT/comments/14qhn00/metagpt_the_roadmap_has_been_released_come_and/\",\"da\":\"translations\",\"h\":0,\"i\":\"www.reddit.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The roadmap has been released! Come and take a look ... - Reddit\",\"u\":\"https://www.reddit.com/r/ChatGPT/comments/14qhn00/metagpt_the_roadmap_has_been_released_come_and/\"},{\"a\":\"Business: MetaGPT can be used to create and execute business programs that can optimize or automate various processes, such as scheduling, planning, budgeting, marketing, etc. MetaGPT can also...\",\"ae\":null,\"c\":\"https://medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\",\"d\":\"medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\",\"da\":\"\",\"e\":\"2023-08-03T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: A Framework for Multi-Agent Meta Programming\",\"u\":\"https://medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\"},{\"a\":\"MetaGPT is an innovative solution that allows us to assign different roles to GPTs, forging a collaborative software force. In this guide, we'll explore how to harness the power of MetaGPT for...\",\"ae\":null,\"c\":\"https://xthemadgenius.medium.com/how-to-use-metagpt-to-operate-as-a-full-engineering-team-c0f6e53c1dc3\",\"d\":\"xthemadgenius.medium.com/how-to-use-metagpt-to-operate-as-a-full-engineering-team-c0f6e53c1dc3\",\"da\":\"translations\",\"e\":\"2023-08-12T00:00:00.0000000\",\"h\":0,\"i\":\"xthemadgenius.medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"How to use MetaGPT to Operate as a full Engineering Team\",\"u\":\"https://xthemadgenius.medium.com/how-to-use-metagpt-to-operate-as-a-full-engineering-team-c0f6e53c1dc3\"},{\"a\":\"MetaGPT, available on Github (crossed 13,000 stars), aims to change the way we make software.This exciting tool can take a single line of what you want to do and turn it into many things like user ...\",\"ae\":null,\"c\":\"https://medium.com/@smraiyyan/metagpt-unleashed-crafting-your-virtual-software-company-from-scratch-6ea60cd70da1\",\"d\":\"medium.com/@smraiyyan/metagpt-unleashed-crafting-your-virtual-software-company-from-scratch-6ea60cd70da1\",\"da\":\"translations\",\"e\":\"2023-08-07T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT Lets You Create Your Own Virtual Software Company from ... - Medium\",\"u\":\"https://medium.com/@smraiyyan/metagpt-unleashed-crafting-your-virtual-software-company-from-scratch-6ea60cd70da1\"},{\"a\":\"\\u57282023\\u5e7412\\u670819\\u65e5\\u65f6\\uff0c\\u542c\\u4e86\\u6797\\u4e49\\u7ae0\\u8001\\u5e08\\u5173\\u4e8e"\\u57fa\\u4e8eMetaGPT\\u8fdb\\u884c\\u667a\\u80fd\\u4f53\\u5f00\\u53d1"\\u7684\\u8bb2\\u5ea7\\uff1a \\u89c9\\u5f97\\u65b0\\u5947\\u6709\\u8da3\\uff0c\\u5982\\u679c\\u80fd\\u8fd9\\u6837\\u5728\\u5de5\\u4f5c\\u751f\\u6d3b\\u4e2d\\u5b8c\\u6210\\u81ea\\u5df1\\u7684\\u4efb\\u52a1\\uff0c\\u90a3\\u7b80\\u76f4\\u662f\\u4e8b\\u534a\\u529f\\u500d\\u3002\\u4e8e\\u662f\\u8fd9\\u4e24\\u5929\\u53c8\\u5b66\\u4e60\\u4e86\\u300aMetaGPT\\u667a\\u80fd\\u4f53\\u5f00\\u53d1\\u5165\\u95e8\\u300b\\u6559\\u2026\",\"ae\":null,\"c\":\"https://zhuanlan.zhihu.com/p/677608276\",\"d\":\"zhuanlan.zhihu.com/p/677608276\",\"da\":\"translations\",\"e\":\"2024-01-12T00:00:00.0000000\",\"h\":0,\"i\":\"zhuanlan.zhihu.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"\\u5b66\\u4e60\\u7b14\\u8bb0-\\u300aMetaGPT\\u667a\\u80fd\\u4f53\\u5f00\\u53d1\\u5165\\u95e8\\u300b\\u6559\\u7a0b - \\u77e5\\u4e4e\",\"u\":\"https://zhuanlan.zhihu.com/p/677608276\"},{\"a\":\"Roadmap \n Long-term Objective \n. Enable MetaGPT to self-evolve, accomplishing self-training, fine-tuning, optimization, utilization, and updates. \n Short-term Objective \n \n; Become the multi-agent framework with the highest ROI. \n; Support fully automatic implementation of medium-sized projects (around 2000 lines of code). \n\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/Ditto190/MetaGPT/blob/main/docs/ROADMAP.md\",\"d\":\"github.com/Ditto190/MetaGPT/blob/main/docs/ROADMAP.md\",\"da\":\"translations\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Roadmap - GitHub\",\"u\":\"https://github.com/Ditto190/MetaGPT/blob/main/docs/ROADMAP.md\"},{\"n\":\"/d.js?q=The%20roadmap%20of%20MetaGPT&kl=wt-wt&l=wt-wt&p=&s=23&ex=-1&ct=US&sp=0&vqd=4-25941261128344049410840372626152530092\"}]);DDG.duckbar.load('images', {\"ads\":[],\"query\":\"The roadmap of MetaGPT\",\"queryEncoded\":\"The%20roadmap%20of%20MetaGPT\",\"response_type\":\"places\",\"results\":[{\"height\":720,\"image\":\"https://i.ytimg.com/vi/8cxLdYtwx4M/maxresdefault.jpg\",\"image_token\":\"25476bee58d891e0b100edecfc9022b60c5c458e8d078f04908c2fe341449aad\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.Sbc4rHZKxrQ7JJKFfx4pggHaEK&pid=Api\",\"thumbnail_token\":\"b8ca3fc5d5109341b5fa2a52479d696225049ce7a678a01730e9440c44454ef0\",\"title\":\"How to use metagpt || What is MetaGPT || Meta AI Tool - YouTube\",\"url\":\"https://www.youtube.com/watch?v=8cxLdYtwx4M\",\"width\":1280},{\"height\":1699,\"image\":\"https://cdn-cashy-static-assets.lucidchart.com/lucidspark/marketing/blog/2020Q4/product-roadmap/product-roadmap-example.png\",\"image_token\":\"45bef86b333d99b8975de0658ef5da261356dcfea369bc8c529fe98c02e9508f\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.zBKuJobHBxYMSdOL3b7oOAHaG1&pid=Api\",\"thumbnail_token\":\"4480400578522cbc135bd7ce753dee35cbbb49e2709c4e5775b3f6334842c409\",\"title\":\"How to Build a Product Roadmap | Lucidspark\",\"url\":\"https://lucidspark.com/blog/how-to-build-a-product-roadmap\",\"width\":1839},{\"height\":688,\"image\":\"https://fanpu.io/assets/img/summaries/metagpt-overview.webp\",\"image_token\":\"7b40dc9efbd841a6810483fe46865f2a8fbc6def3902f385bb02c8199488d8d1\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.jEHUvpk8FOPdH12J79rFXQHaFR&pid=Api\",\"thumbnail_token\":\"8490d5575bc2435a2ae2adde324f594a1fd905d74bc8c8849565a99d1cf8e658\",\"title\":\"MetaGPT: Meta Programming for Multi-Agent Collaborative Framework | Fan ...\",\"url\":\"https://fanpu.io/summaries/2023-08-11-metagpt-meta-programming-for-multi-agent-collaborative-framework/\",\"width\":966},{\"height\":920,\"image\":\"https://roadmunk.com/guides/content/images/2020/09/Timeline-Roadmap-1.png\",\"image_token\":\"96f5e93a0d50706ce051a1024537055b9f1f1f7e2db4da2f158f13b98d56cd9d\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.hchaQb3VwheAODLNSOIAdQHaEe&pid=Api\",\"thumbnail_token\":\"28d9e72b560992d38447bd1a9d050d154d32f1eb0bf8690fe33d04c56ecdd618\",\"title\":\"What is a roadmap? The guide to roadmapping - Roadmunk\",\"url\":\"https://roadmunk.com/guides/roadmap-definition/\",\"width\":1520},{\"height\":920,\"image\":\"https://lh3.googleusercontent.com/H1-gvtbro-_27q3NnYbGO37i7a_xTqVRQ0ZvqJtRJBkfRjuPMg-11djNlPDLFJpjY8hKCzKwIlKiy040Us5unlwBPLUyqEMHIOUm7qqcEobhB-Uqsf2qHEyzEQywl9dkdErjkkrZ\",\"image_token\":\"8912b09257d9b4cef5ed84acd84b034f77aca601cf6d10094d87836b7b2bf7b5\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.qjGOCXm2nvDzRX8JRwxTagHaEe&pid=Api\",\"thumbnail_token\":\"7b3a7ba7cbcec30ecf21e2ac3f06daf1f8d55a9e3a7b4c657b9e1f1656c21f01\",\"title\":\"What is a product roadmap and how to create it? - Weje.io\",\"url\":\"https://weje.io/blog/product-roadmap\",\"width\":1520},{\"height\":3500,\"image\":\"https://static.vecteezy.com/system/resources/previews/000/680/342/original/infographic-business-roadmap-timeline.jpg\",\"image_token\":\"f78e25fbc66da7d380c8b378b3b51d2e3aabb98e01b39239b0184e8eff3f3b1d\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.1XTASxs0KABNJjUYwMRIWQHaFL&pid=Api\",\"thumbnail_token\":\"b41dcc02238e5f5150208de2a5f4d508fbecccc0040c24314e76107185be772a\",\"title\":\"Business Roadmap Vector Art, Icons, and Graphics for Free Download\",\"url\":\"https://www.vecteezy.com/free-vector/business-roadmap\",\"width\":5000},{\"height\":3871,\"image\":\"https://uniserveit.com/uploads/Building-A-Technology-Roadmap.jpg\",\"image_token\":\"2cd4a4a7699e095734ebd1278facc076305f4cc59854186bef8b98152a794f08\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.2ZnbiyLbkRcKHXL1_6u8JwHaE2&pid=Api\",\"thumbnail_token\":\"de73a3f195d39fb167707545a4761d3a15d0ef308a4b29e2e244202c52d76628\",\"title\":\"How To Build A Technology Roadmap | Uniserve IT Soltutions\",\"url\":\"https://uniserveit.com/blog/building-a-technology-roadmap\",\"width\":5903},{\"height\":940,\"image\":\"https://media.nngroup.com/media/editor/2020/10/28/screen-shot-2020-10-28-at-12537-pm.png\",\"image_token\":\"e90c0ef520ee067896af8acc0653d9ea2082d41fc2d82075c551a61de427ee42\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.RDV9bbgkuW_SJ28N8n_R9AHaDu&pid=Api\",\"thumbnail_token\":\"c242005da7b72897176ef634488b5025eb2d4925e6aae4aa6cec3ace673f62e3\",\"title\":\"The 6 steps to roadmapping (2022)\",\"url\":\"https://edduls.pics/article/the-6-steps-to-roadmapping\",\"width\":1872},{\"height\":720,\"image\":\"https://slidevilla.com/wp-content/uploads/2019/02/b7548f226f6de734c5dfa5f141a5918d-6.jpg\",\"image_token\":\"c6ac89b3b79b7e7d2a8f1246dbe131f95256f0ee2de78c478b92733ef40e63e1\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.PJUe_oduaD-FLmTMHHYp2wHaFj&pid=Api\",\"thumbnail_token\":\"e9193de0027c0317d3ea8ac3f6ffd3e30ec2043df987c29e4c002e9b2476681d\",\"title\":\"Roadmap with milestones powerpoint template - Slidevilla\",\"url\":\"https://slidevilla.com/shop/powerpoint-templates/roadmap-with-milestones/\",\"width\":960},{\"height\":2050,\"image\":\"https://www.jibility.com/wp-content/uploads/2021/09/digital-transformation-example-roadmap-detail.png\",\"image_token\":\"45a07b34c3b25676ca4f531482db5c858f6bbfd24ca0e593808aebfbb150acaa\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.sbKPggSDMYdKDZ5jbz14iwHaFJ&pid=Api\",\"thumbnail_token\":\"2a087acc29b5f757b8f7469d08f6c80701eb0393627932e93ecf7206714120c1\",\"title\":\"Strategic Roadmap Tool | Jibility | Professional Plan from $39\",\"url\":\"https://www.jibility.com/pricing/\",\"width\":2951},{\"height\":2095,\"image\":\"https://media.nngroup.com/media/articles/opengraph_images/6_Steps_Roadmapping_Social-Media-Posts_2020-38.png\",\"image_token\":\"855d0a05e27aee26c8f4ca738a99fd20f7b0efa43bfa177a22ce0717463e8a1b\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.bkZKyld4JdobfUy5xZaMzAHaD4&pid=Api\",\"thumbnail_token\":\"a0046653e2b02e1b76f8bc160d0c7734914e5cea3a37d5d61534943ccafb3f00\",\"title\":\"The 6 Steps to Roadmapping\",\"url\":\"https://www.nngroup.com/articles/roadmapping-steps/\",\"width\":4001},{\"height\":1440,\"image\":\"https://www.ciloart.com/files/free-process-roadmap-timeline-infographics-for-powerpoint-templates.jpg\",\"image_token\":\"f8a130afc6893bb6cec1a071b2f3fe6fec48bc8f15eb0efc0ad415a4e2c9d162\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.wDWVEEfr5zg9vz7HAnK0DQHaEK&pid=Api\",\"thumbnail_token\":\"fafeddafec61e36c6e39575442bfd415d85c909580b432618d4bc79efcc5b9b5\",\"title\":\"Roadmap ppt template free - plmnoble\",\"url\":\"https://plmnoble.weebly.com/blog/roadmap-ppt-template-free\",\"width\":2560},{\"height\":576,\"image\":\"https://cdn.infodiagram.com/c/a84123/team-roadmap-engineering-chart-development-innovation-technology.png\",\"image_token\":\"aaf2d11a998569ac9cebb8b0441fca9a1a5f9b88a902737cca46a41b2a3d5b1f\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.IBaC7bT304-c6nyTTJiijAHaEK&pid=Api\",\"thumbnail_token\":\"788dc194a239068cff396bf9d134d6dd3aa22adb27fa480345951cb142fc37ec\",\"title\":\"Technology Roadmap PPT Template\",\"url\":\"https://www.infodiagram.co.uk/slides/roadmap-technology-template/\",\"width\":1024},{\"height\":2048,\"image\":\"https://1.bp.blogspot.com/-Dv1SChkX87k/YD3c7mfegKI/AAAAAAAARSI/8thS6TtRC30DiAwzBXXfKw1IwgLp695JQCLcBGAsYHQ/s2048/Wed%2BRoadmap.jpeg\",\"image_token\":\"9744a089f465662e7961b05bbf9859438a69af2f7d7190af5059835b9c3001d6\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.xTQzIRZCy3BS7DuA2YWXVgHaLG&pid=Api\",\"thumbnail_token\":\"d3f95531ab49a8166b2eb7b49aafe8b09b08ecb4224151456a63fd892ae077f7\",\"title\":\"Learn Web Development as an absolute Beginner Roadmap & What Skills you ...\",\"url\":\"https://codewithwastik.blogspot.com/2021/03/learn-web-development-as-absolute.html\",\"width\":1367},{\"height\":1440,\"image\":\"https://www.itce.com/wp-content/uploads/2018/11/SAFe-Implementation-Roadmap-ITCE-1920x1440.png\",\"image_token\":\"922478c3965e75a6f91ba2aec69832a2a725feffed976e0422377ce7e1c61146\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.Mkqd375BYhPyxasV59LLPwHaFj&pid=Api\",\"thumbnail_token\":\"2319f3ca85bae584140ce010bacecfa89823bc3ac15760fc2bc620eaa4c09492\",\"title\":\"SAFe Roadmap Implementation - ITCE\",\"url\":\"https://www.itce.com/services/safe-implementation-roadmap/\",\"width\":1920},{\"height\":1214,\"image\":\"https://graphicpanda.net/wp-content/uploads/2019/12/09.jpg\",\"image_token\":\"8c3fec9753bddf54dbbc4334adcb7c3845ebc2c9ac9d9919a625b4e81b931227\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.aer6Fq6Foz4Ugx0PGAUX1wHaE8&pid=Api\",\"thumbnail_token\":\"5cda767e92851048094f8b0eb9e5782c590d178766a35e12f102bdaf12eebb55\",\"title\":\"Top 48 Best Roadmap Infographics of 2019\",\"url\":\"https://graphicpanda.net/top-48-best-roadmap-infographics-of-2019/\",\"width\":1820},{\"height\":858,\"image\":\"https://47billion.com/wp-content/uploads/2022/02/Roadmap-for-Transforming-into-a-Data-Driven-Organization-e1645684780855.png\",\"image_token\":\"89aa4e1ff6bbf4325203cf48edcd389e876ad5b4aece7c79c127206fd7af53e3\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.8_44ACp4csLk-5DvQxJ1WgHaF4&pid=Api\",\"thumbnail_token\":\"e34f7de48ebea075b768b643bdca97ca0f5780511cbd5d512360baf9f61e5a74\",\"title\":\"Roadmap for Transforming into a Data-Driven Organization - 47billion.com\",\"url\":\"https://47billion.com/blog/roadmap-for-transforming-into-a-data-driven-organization/\",\"width\":1080},{\"height\":1656,\"image\":\"https://business-docs.co.uk/wp-content/uploads/2021/06/BDUK43StrategyRoadmapTemplatePowerpoint16x90501.png\",\"image_token\":\"4c7ed30a8f7f563a9a9c556ff684737bd5c57e4f2fa9643543a0961a6ea81748\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.9SJg6AkiAlFFaiSaR_wt-AHaEQ&pid=Api\",\"thumbnail_token\":\"1aa46a29b71fb20bce0482e7d652e25fd9b0068d27c153dc8934c0cdabe8be87\",\"title\":\"Strategy Roadmap Template PowerPoint - Present your strategic plans!\",\"url\":\"https://business-docs.co.uk/downloads/strategy-roadmap-template-powerpoint/\",\"width\":2880},{\"height\":1163,\"image\":\"https://i.pinimg.com/originals/55/17/fb/5517fbb701b86448db0e2027c3143d24.png\",\"image_token\":\"26a8a386dc179392ce51475382e003749b26eab3020410abee2451f837227e1e\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.m3dqCemXYTHDwnTNHr9CzgHaEj&pid=Api\",\"thumbnail_token\":\"be77ab5985646acf21a6268137d9c9108f60731a90cd9a36e116e30ba89ba445\",\"title\":\"Marketing Roadmap - Template and Examples | Roadmunk | Marketing ...\",\"url\":\"https://www.pinterest.de/pin/588704982531603300/\",\"width\":1893},{\"height\":1170,\"image\":\"https://d2slcw3kip6qmk.cloudfront.net/marketing/blog/2019Q4/technology-roadmap/it-roadmap-example.png\",\"image_token\":\"093a2a27e4cd0988223d8947a600db27208ce6c77f522eaca579c3eddab2d6e7\",\"source\":\"Bing\",\"thumbnail\":\"https://tse1.mm.bing.net/th?id=OIP.WRAD5IO2lrB7GGe7fLSJwgHaFN&pid=Api\",\"thumbnail_token\":\"910b3be01ddda5ea65a713080fb458385fb72d8911f434b59d08c18cf7ad5d38\",\"title\":\"What Is a Product Roadmap and How to Create One? | LaunchPad Lab\",\"url\":\"https://launchpadlab.com/blog/what-is-a-product-roadmap-and-why-you-need-one/\",\"width\":1662}],\"vqd\":{\"The%20roadmap%20of%20MetaGPT\":\"4-25941261128344049410840372626152530092\"}});DDG.duckbar.load('news');DDG.duckbar.load('videos', {\"ads\":[],\"query\":\"The roadmap of MetaGPT\",\"queryEncoded\":\"The%20roadmap%20of%20MetaGPT\",\"response_type\":\"places\",\"results\":[{\"content\":\"https://www.youtube.com/watch?v=uT75J_KG_aY\",\"description\":\"In this video, we review MetaGPT, a new project that aims to recreate an entire engineering organization using AI. MetaGPT is a CEO, Product Manager, Architect, Project Manager, Engineering, and QA. Write a simple prompt, and you get everything from the requirements to the PRDs to the code and tests. How To Find Me: Become a Patron \\ud83d\\udd25 - https ...\",\"duration\":\"6:36\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/uT75J_KG_aY?autoplay=1\",\"image_token\":\"57974159b78b309485721c0bce280219d9927e071e542a34777864767d6cb8d4\",\"images\":{\"large\":\"https://tse3.mm.bing.net/th?id=OVP.BbSKV8N1vyYv-3m8vyuCoQEsDh&pid=Api\",\"medium\":\"https://tse3.mm.bing.net/th?id=OVP.BbSKV8N1vyYv-3m8vyuCoQEsDh&pid=Api\",\"motion\":\"https://tse3.mm.bing.net/th?id=OM1.bsXxoMoJ9ZWQBw&pid=Api\",\"small\":\"https://tse3.mm.bing.net/th?id=OVP.BbSKV8N1vyYv-3m8vyuCoQEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-08-14T14:09:10.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":75408},\"title\":\"How To Install MetaGPT - Build A Startup With One Prompt!!\",\"uploader\":\"Matthew Berman\"},{\"content\":\"https://www.youtube.com/watch?v=YtxMderNrzU\",\"description\":\"Subscribe to my Newsletter (My AI updates and news clearly explained): https://louisbouchard.substack.com/ References: Read the full article: https://www.louisbouchard.ai/metagpt/ Hong et al., 2023: MetaGPT, https://arxiv.org/pdf/2308.00352.pdf Code: https://github.com/geekan/MetaGPT/blob/main/README.md Twitter: https://twitter.com/Whats_AI ...\",\"duration\":\"7:38\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/YtxMderNrzU?autoplay=1\",\"image_token\":\"2e0774ace2e34bbe23ece04e80b7bb2ee976fd8ef7f53001e8f8b137763561dc\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.HP81CZ34ap22GZZG2l024QHgFo&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.HP81CZ34ap22GZZG2l024QHgFo&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM2.xArTjo5bOxSBhg&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.HP81CZ34ap22GZZG2l024QHgFo&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-08-27T15:05:12.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":9594},\"title\":\"MetaGPT: Redefining Multi-Agent Collaboration for Complex Tasks\",\"uploader\":\"What's AI by Louis Bouchard\"},{\"content\":\"https://www.youtube.com/watch?v=nqZlTV_L6Ao\",\"description\":\"Welcome to our video review! \\ud83c\\udfa5 Dive into the world of MetaGPT, a revolutionary project that's redefining the boundaries of AI. \\ud83e\\udd16 Imagine having an entire engineering team - from CEO to QA - compacted into one AI system. Just input a prompt, and voila! You're handed everything from requirements, PRDs, to the actual code and tests. Let ...\",\"duration\":\"14:15\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/nqZlTV_L6Ao?autoplay=1\",\"image_token\":\"9d13b27084400da23ef8d8567bd6b5c8a3758d4129f2b28c3619c0e2e1ba8276\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.VBEy5DF-0BQshjEkqA9T0wHgFo&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.VBEy5DF-0BQshjEkqA9T0wHgFo&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM2.N7S3-wAngkj7VA&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.VBEy5DF-0BQshjEkqA9T0wHgFo&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-09-04T11:45:06.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":23248},\"title\":\"\\ud83d\\ude80 MetaGPT Setup: Launch a Startup with One \\u270d\\ufe0f Prompt!\",\"uploader\":\"Prompt Engineering\"},{\"content\":\"https://www.youtube.com/watch?v=12X4pupy4No\",\"description\":\"Simple as Plug n Play Visit www.MetaIDT.com\",\"duration\":\"1:00\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/12X4pupy4No?autoplay=1\",\"image_token\":\"3bf00a4528bef3408e273fd9403d2bce8428fc915c51ba5d0b09527abb7b47ce\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.gqgtA4cHlbRoVhYkFEkUuQEsDh&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.gqgtA4cHlbRoVhYkFEkUuQEsDh&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM1.dgsWk4LJc4VGrQ_1691420084&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.gqgtA4cHlbRoVhYkFEkUuQEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-07-17T09:43:32.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":470},\"title\":\"MetaGPT Key Drive Installation Guide\",\"uploader\":\"MetaGPT\"},{\"content\":\"https://www.youtube.com/watch?v=EgipcKPhqME\",\"description\":\"In this video I provide a great demo and overview of a project called MetaGPT. Have you ever wondered if each person in a development project (such as the project manager, developers, architects, QA testers, etc.) were all AI's and how they'd behave? MetaGPT is doing just that. Not only are all the docs, designs, and tasks delivered, but also a ...\",\"duration\":\"7:35\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/EgipcKPhqME?autoplay=1\",\"image_token\":\"624d4ccdb6d1605da1e388e85c9124957bcba9c70a11a575e751ba6fc09bc5f8\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.hG0c3nw7X-uz0gzUjnOVNwEsDh&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.hG0c3nw7X-uz0gzUjnOVNwEsDh&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM1.8F2lEMy1JlCKsQ_1698986522&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.hG0c3nw7X-uz0gzUjnOVNwEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-09-24T08:00:11.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":1587},\"title\":\"MetaGPT Tutorial | It builds an entire project (with working source code) with just one prompt!!\",\"uploader\":\"CraceCasts\"},{\"content\":\"https://www.youtube.com/watch?v=T_wBUpzxxPY\",\"description\":\"In this video i talk about this awesome project called MetaGPT in my video. Now, MetaGPT is like an all-in-one AI powerhouse. It can do everything from being a CEO to a QA tester for an engineering organization. And the cool thing is, you just give it a simple prompt, and it spits out everything you need - requirements, PRDs, code, and tests ...\",\"duration\":\"4:00\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/T_wBUpzxxPY?autoplay=1\",\"image_token\":\"ef14791d7faff848cb15177567e9f4f9c04ccae4fafc7ef7386e69df3a012010\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.EWCOFStB_tQza4SLrUA0AAEsDh&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.EWCOFStB_tQza4SLrUA0AAEsDh&pid=Api\",\"motion\":\"https://tse1.mm.bing.net/th?id=OM1.itG5pHJg6MKYzg_1696190983&pid=Api\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.EWCOFStB_tQza4SLrUA0AAEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-09-11T10:41:22.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":368},\"title\":\"MetaGPT Installation Guide: From Setup to Startup With One Prompt!\",\"uploader\":\"Py Man\"},{\"content\":\"https://www.youtube.com/watch?v=AwnltW8n74A\",\"description\":\"MetaGPT is a framework that uses GPT-4 to automate multiple roles within a software company. For example product managers, software architects, project managers and software engineers. It writes code, documentation, user stories, competitive analysis, and creates diagrams. Github: https://github.com/geekan/MetaGPT #ai #gpt4\",\"duration\":\"7:53\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/AwnltW8n74A?autoplay=1\",\"image_token\":\"b7c3d4481f0f7b7b7c7c43d3da07368a2feb28b2fbdbd8b86b8d5c64b19833fd\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.J4PD9qpp3rIqXai84Jsu2wEsDh&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.J4PD9qpp3rIqXai84Jsu2wEsDh&pid=Api\",\"motion\":\"https://tse1.mm.bing.net/th?id=OM1.EGElEVpTnZYCdQ_1691938448&pid=Api\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.J4PD9qpp3rIqXai84Jsu2wEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-08-06T23:09:15.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":6497},\"title\":\"MetaGPT - Multi-Agent Framework with GPT-4\",\"uploader\":\"Tosh Velaga\"},{\"content\":\"https://www.youtube.com/watch?v=D80u__nYYWw\",\"description\":\"Learn how to quickly build a roadmap alongside the same table and board views you already know and love in GitHub Projects. With Senior Product Manager, Riley Broughten and Developer Advocate, Kedasha Kerr (@itsthatladydev) Blog: https://gh.io/roadmaps-changelog Project Roadmaps Docs: https://gh.io/roadmaps Tell us what you think!: https://gh ...\",\"duration\":\"7:01\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/D80u__nYYWw?autoplay=1\",\"image_token\":\"2a89cec713d7aae159325e0cb365581ed2715f02621e9f83a9738ffa92664166\",\"images\":{\"large\":\"https://tse3.mm.bing.net/th?id=OVP.46T5385YNZojaEJclzxHKQEsDh&pid=Api\",\"medium\":\"https://tse3.mm.bing.net/th?id=OVP.46T5385YNZojaEJclzxHKQEsDh&pid=Api\",\"motion\":\"https://tse3.mm.bing.net/th?id=OM.jWPqoPJyqHDaVw_1685085608&pid=Api\",\"small\":\"https://tse3.mm.bing.net/th?id=OVP.46T5385YNZojaEJclzxHKQEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-04-18T13:48:05.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":19906},\"title\":\"Learn how to use Project Roadmaps - GitHub Checkout\",\"uploader\":\"GitHub\"},{\"content\":\"https://www.youtube.com/watch?v=pJwR5pv0_gs\",\"description\":\"Multi agent framework tutorial of MetaGPT & chatDev; Check the Hubspot x Jasper research of Using Generative AI to Scale Your Content Operations: https://offers.hubspot.com/generative-ai-for-content-operations?utm_source=youtube&utm_medium=social&utm_campaign=CR0087Sep2023_AIJason/partner_youtube \\ud83d\\udd17 Links - Follow me on twitter: https ...\",\"duration\":\"13:41\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/pJwR5pv0_gs?autoplay=1\",\"image_token\":\"18ac54a8e5144c74f2010219781c47c295099a6eed7479645733832910d19aec\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.LJ0SK8DLWjCcwVVh-PEcOwHgFo&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.LJ0SK8DLWjCcwVVh-PEcOwHgFo&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM2.PxMMOsse4Yi_FQ&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.LJ0SK8DLWjCcwVVh-PEcOwHgFo&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-09-08T11:36:03.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":167793},\"title\":\"Build AI agent workforce - Multi agent framework with MetaGPT & chatDev\",\"uploader\":\"AI Jason\"},{\"content\":\"https://www.youtube.com/watch?v=q16Gi9pTG_M\",\"description\":\"In this captivating video, we explore the core concept of MetaGPT, which centers on task distribution and coordination among individual GPT agents. Each agent is bestowed with specific roles that capitalize on their unique strengths and expertise. Imagine one GPT excelling in natural language understanding, while another showcases prowess in ...\",\"duration\":\"14:56\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/q16Gi9pTG_M?autoplay=1\",\"image_token\":\"bee3657ef83c9da2bc4ccfea770244e18958f5789a39d0136c3a049cc22a0e54\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.eiPUmQWRU1sE-01-x5Kn7gEsDh&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.eiPUmQWRU1sE-01-x5Kn7gEsDh&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM2.eWDmjf8nvrSrhw&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.eiPUmQWRU1sE-01-x5Kn7gEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-07-25T00:37:40.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":14365},\"title\":\"MetaGPT: Deploy POWERFUL Autonomous Ai Agents BETTER Than SUPERAGI! (Installation Tutorial)\",\"uploader\":\"WorldofAI\"}],\"vqd\":{\"The%20roadmap%20of%20MetaGPT\":\"4-25941261128344049410840372626152530092\"}});DDG.duckbar.loadModule('related_searches');if (DDG.pageLayout) DDG.pageLayout.initialize({\"mainline\":{\"items\":[[\"organic\"],[\"images\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"videos\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"]]}}, { start: 0 });DDG.deep.emit(\"load:completed\");", + "curl-cffi-POST-https://duckduckgo.com-{\"data\": {\"q\": \"The function of MetaGPT\"}}": "The function of MetaGPT at DuckDuckGo
", + "curl-cffi-GET-https://links.duckduckgo.com/d.js-{\"params\": {\"bing_market\": \"wt-WT\", \"df\": null, \"ex\": \"-1\", \"kl\": \"wt-wt\", \"l\": \"wt-wt\", \"q\": \"The function of MetaGPT\", \"s\": \"0\", \"sp\": \"0\", \"vqd\": \"4-148519746540767190220111387879117509726\"}}": "if (DDG.deep && DDG.deep.setUpstream) DDG.deep.setUpstream(\"bingv7aa\");DDG.deep.bn={'ivc':1};if (DDG.pageLayout) DDG.pageLayout.load('a',[], {\"page_load_url\":\"https://duckduckgo.com/y.js?iurl=%7B2%7DIG%3D3A2CFCB179EC4A63AF1E2047F34A7CBB%26CID%3D3280021F2FA667E6037316192E5B66D4%26Type%3DEvent.CPT%26DATA%3D0\"});DDG.deep.signalSummary = \"\";DDG.inject('DDG.Data.languages.resultLanguages', {\"en\":[\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"https://levelup.gitconnected.com/metagpt-the-future-of-multi-agent-collaboration-in-ai-a-brief-guide-fd4b4429336d\",\"https://geekflare.com/metagpt-multi-agent-framework/\",\"https://medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\",\"https://arxiv.org/abs/2308.00352\",\"https://github.com/geekan/MetaGPT\",\"https://medium.com/@reddy.khoushik/metagpt-the-multi-agent-framework-revolutionizing-software-collaboration-38e48397021f\",\"https://www.marktechpost.com/2023/08/09/meet-metagpt-the-open-source-ai-framework-that-transforms-gpts-into-engineers-architects-and-managers/\",\"https://ai-scholar.tech/en/articles/agent-simulation/meta-gpt\",\"https://docs.deepwisdom.ai/main/en/guide/tutorials/multi_agent_101.html\",\"https://lablab.ai/blog/this-week-in-ai-exploring-the-latest-from-metagpt-and-gpt4-and-more\",\"https://analyticsindiamag.com/metagpt-realising-the-gpt-4-dream/\",\"https://docs.deepwisdom.ai/main/en/guide/tutorials/agent_101.html\",\"https://www.almabetter.com/bytes/articles/metagpt\",\"https://medium.com/@korolalexei/metagpt-a-multi-agent-framework-revolutionizing-software-development-f585fe1aa950\",\"https://github.com/PlaiD3/MetaGPT/blob/main/README.md\",\"https://eightify.app/summary/computer-science-and-technology/metagpt-advanced-autonomous-ai-agents-installation-tutorial\",\"https://ar5iv.labs.arxiv.org/html/2308.00352\",\"https://www.freegpttools.org/metagpt\",\"https://github.com/geekan/MetaGPT/releases\",\"https://theventurecation.com/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"https://blogs.windows.com/windowsexperience/2024/01/04/introducing-a-new-copilot-key-to-kick-off-the-year-of-ai-powered-windows-pcs/\",\"https://www.instagram.com/richfieldmusic/p/C1bpt1eucbU/\"]});DDG.deep.pageLayoutSummary = \"w25\";DDG.inject('DDG.Data.languages.adLanguages', {});if (DDG.pageLayout) DDG.pageLayout.load('d',[{\"a\":\"To actualize an agile, flexible software architecture that can adapt to dynamic programming tasks. Agile Development SOPs act as a meta-function here, coordinating agents to auto-generate code based on defined inputs.\",\"ae\":null,\"c\":\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"d\":\"www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"da\":\"\",\"e\":\"2023-09-11T00:00:00.0000000\",\"h\":0,\"i\":\"www.unite.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\"u\":\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\"},{\"a\":\"MetaGPT is a multi-agent system that utilizes Large Language Models (LLMs) to perform complex tasks. It is designed to overcome the limitations of LLMs in fostering effective collaboration and...\",\"ae\":null,\"c\":\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"d\":\"www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"da\":\"\",\"e\":\"2023-12-13T00:00:00.0000000\",\"h\":0,\"i\":\"www.straight.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"A Complete Guide to MetaGPT: The Best AI Agent Available Now\",\"u\":\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\"},{\"a\":\"1 Created by Bing In the ever-evolving world of artificial intelligence, one term has recently taken the spotlight: MetaGPT. As the digital landscape becomes more competitive, understanding and leveraging the capabilities of MetaGPT can be a game-changer for businesses, developers, and AI enthusiasts alike.\",\"ae\":null,\"c\":\"https://levelup.gitconnected.com/metagpt-the-future-of-multi-agent-collaboration-in-ai-a-brief-guide-fd4b4429336d\",\"d\":\"levelup.gitconnected.com/metagpt-the-future-of-multi-agent-collaboration-in-ai-a-brief-guide-fd4b4429336d\",\"da\":\"\",\"e\":\"2023-08-09T00:00:00.0000000\",\"h\":0,\"i\":\"levelup.gitconnected.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Future of Multi-Agent Collaboration in AI (A Brief Guide)\",\"u\":\"https://levelup.gitconnected.com/metagpt-the-future-of-multi-agent-collaboration-in-ai-a-brief-guide-fd4b4429336d\"},{\"a\":\"MetaGPT is a multi-agent framework that takes one-line inputs to produce APIs, user stories, data structures, competitive analysis, and more. GPT is the short form for Generative Pretrained Transformers. MetaGPT framework can behave as a product manager, software engineer, and architect. This framework can act as an entire software company with ...\",\"ae\":null,\"c\":\"https://geekflare.com/metagpt-multi-agent-framework/\",\"d\":\"geekflare.com/metagpt-multi-agent-framework/\",\"da\":\"\",\"e\":\"2023-09-18T00:00:00.0000000\",\"h\":0,\"i\":\"geekflare.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Is This the Best Multi-Agent Framework Yet? - Geekflare\",\"u\":\"https://geekflare.com/metagpt-multi-agent-framework/\"},{\"a\":\"Gaming: MetaGPT can be used to create and control intelligent agents that can cooperate or compete with human players or other agents in various games, such as board games, card games, video...\",\"ae\":null,\"c\":\"https://medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\",\"d\":\"medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\",\"da\":\"\",\"e\":\"2023-08-03T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: A Framework for Multi-Agent Meta Programming\",\"u\":\"https://medium.com/aimonks/metagpt-a-framework-for-multi-agent-meta-programming-6c79f2eafb8e\"},{\"a\":\"You can check this by using:</span>\n<span class=\"pl-c\"><span class=\"pl-c\">#</span> You can use conda to initialize a new python env</span>\n<span class=\"pl-c\"><span class=\"pl-c\">#</span> conda create -n metagpt python=3.9</span>\n<span class=\"pl-c\"><span class=\"pl-c\">#</span> conda activate metagpt</span>\npython3 --version\n\n<span...\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT/blob/main/README.md\",\"d\":\"github.com/geekan/MetaGPT/blob/main/README.md\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework - GitHub\",\"u\":\"https://github.com/geekan/MetaGPT/blob/main/README.md\"},{\"a\":\"MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-based multi-agent systems.\",\"ae\":null,\"b\":\"arx\\tarXiv.org\\tarxiv.org\",\"c\":\"https://arxiv.org/abs/2308.00352\",\"d\":\"arxiv.org/abs/2308.00352\",\"da\":\"translations\",\"e\":\"2023-08-01T00:00:00.0000000\",\"h\":0,\"i\":\"arxiv.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework\",\"u\":\"https://arxiv.org/abs/2308.00352\"},{\"a\":\"MetaGPT: The Multi-Agent Framework Assign different roles to GPTs to form a collaborative software entity for complex tasks. MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc.\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT\",\"d\":\"github.com/geekan/MetaGPT\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework - GitHub\",\"u\":\"https://github.com/geekan/MetaGPT\"},{\"a\":\"MetaGPT's innovative approach to collaborative AI has the potential to reshape the landscape of software development. By harnessing the collective power of specialized AI roles, developers can ...\",\"ae\":null,\"c\":\"https://medium.com/@reddy.khoushik/metagpt-the-multi-agent-framework-revolutionizing-software-collaboration-38e48397021f\",\"d\":\"medium.com/@reddy.khoushik/metagpt-the-multi-agent-framework-revolutionizing-software-collaboration-38e48397021f\",\"da\":\"translations\",\"e\":\"2023-08-18T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework Revolutionizing Software ... - Medium\",\"u\":\"https://medium.com/@reddy.khoushik/metagpt-the-multi-agent-framework-revolutionizing-software-collaboration-38e48397021f\"},{\"a\":\"MetaGPT streamlines the coordination between interdependent jobs by formalizing the artifacts that human experts exchange. Agents are connected by a shared environment that offers insight into activities and shared use of tools and resources. All communications between agents are contained in this environment.\",\"ae\":null,\"c\":\"https://www.marktechpost.com/2023/08/09/meet-metagpt-the-open-source-ai-framework-that-transforms-gpts-into-engineers-architects-and-managers/\",\"d\":\"www.marktechpost.com/2023/08/09/meet-metagpt-the-open-source-ai-framework-that-transforms-gpts-into-engineers-architects-and-managers/\",\"da\":\"translations\",\"e\":\"2023-08-09T00:00:00.0000000\",\"h\":0,\"i\":\"www.marktechpost.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Meet MetaGPT: The Open-Source AI Framework That Transforms GPTs into ...\",\"u\":\"https://www.marktechpost.com/2023/08/09/meet-metagpt-the-open-source-ai-framework-that-transforms-gpts-into-engineers-architects-and-managers/\"},{\"a\":\"This paper presents MetaGPT, a multi-agent framework that extends complex problem solving capabilities by encoding SOPs that incorporate real-world expertise into LLM agents, and shows through experiments that it can generate more consistent and comprehensive solutionsthan existing methods.\",\"ae\":null,\"c\":\"https://ai-scholar.tech/en/articles/agent-simulation/meta-gpt\",\"d\":\"ai-scholar.tech/en/articles/agent-simulation/meta-gpt\",\"da\":\"\",\"e\":\"2023-08-18T00:00:00.0000000\",\"h\":0,\"i\":\"ai-scholar.tech\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT, a multi-agent framework in which AI consistently develops ...\",\"u\":\"https://ai-scholar.tech/en/articles/agent-simulation/meta-gpt\"},{\"a\":\"The core advantage of MetaGPT also lies in the easy and flexible development of a team of agents. Under MetaGPT framework, users can enable interactions between agents with a minimal amount of codes. ... we need three steps to set up the team and make it function: Define each role capable of intended actions; Think about the Standard Operating ...\",\"ae\":null,\"c\":\"https://docs.deepwisdom.ai/main/en/guide/tutorials/multi_agent_101.html\",\"d\":\"docs.deepwisdom.ai/main/en/guide/tutorials/multi_agent_101.html\",\"da\":\"translations\",\"h\":0,\"i\":\"docs.deepwisdom.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MultiAgent 101 | MetaGPT\",\"u\":\"https://docs.deepwisdom.ai/main/en/guide/tutorials/multi_agent_101.html\"},{\"a\":\"MetaGPT is a groundbreaking multi-agent framework that is transforming the way software development is approached. By taking a single line of requirement as input, MetaGPT outputs a comprehensive array of development components, including user stories, competitive analysis, requirements, data structures, APIs, and documents.\",\"ae\":null,\"c\":\"https://lablab.ai/blog/this-week-in-ai-exploring-the-latest-from-metagpt-and-gpt4-and-more\",\"d\":\"lablab.ai/blog/this-week-in-ai-exploring-the-latest-from-metagpt-and-gpt4-and-more\",\"da\":\"\",\"e\":\"2023-08-11T00:00:00.0000000\",\"h\":0,\"i\":\"lablab.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"This Week in AI: Exploring the Latest from MetaGPT and GPT-4 and more..\",\"u\":\"https://lablab.ai/blog/this-week-in-ai-exploring-the-latest-from-metagpt-and-gpt4-and-more\"},{\"a\":\"MetaGPT then asks for a few additional details, such as the required inputs from the user. Subscribe to our Newsletter. ... One only needs to look at the success of AutoGPT, an open-source project looking to allow GPT-4 to function autonomously. Other similar projects include BabyAGI, a GPT API powered task management system, ...\",\"ae\":null,\"c\":\"https://analyticsindiamag.com/metagpt-realising-the-gpt-4-dream/\",\"d\":\"analyticsindiamag.com/metagpt-realising-the-gpt-4-dream/\",\"da\":\"\",\"e\":\"2023-04-26T00:00:00.0000000\",\"h\":0,\"i\":\"analyticsindiamag.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT \\u2014 Realising the GPT-4 Dream - Analytics India Magazine\",\"u\":\"https://analyticsindiamag.com/metagpt-realising-the-gpt-4-dream/\"},{\"a\":\"In MetaGPT, class Action is the logical abstraction for an action. Users may use LLM to empower this Action by simply invoking the self._aask function, which will make LLM api call under the hood. In our scenario, we define a SimpleWriteCode subclassed Action.\",\"ae\":null,\"c\":\"https://docs.deepwisdom.ai/main/en/guide/tutorials/agent_101.html\",\"d\":\"docs.deepwisdom.ai/main/en/guide/tutorials/agent_101.html\",\"da\":\"translations\",\"h\":0,\"i\":\"docs.deepwisdom.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Agent 101 | MetaGPT\",\"u\":\"https://docs.deepwisdom.ai/main/en/guide/tutorials/agent_101.html\"},{\"a\":\"Understanding MetaGPT MetaGPT, a concept originating from a research paper that received significant attention, represents a leap forward in Artificial Intelligence, specifically in multi-agent collaboration using large language models (LLMs).\",\"ae\":null,\"c\":\"https://www.almabetter.com/bytes/articles/metagpt\",\"d\":\"www.almabetter.com/bytes/articles/metagpt\",\"da\":\"\",\"e\":\"2023-08-28T00:00:00.0000000\",\"h\":0,\"i\":\"www.almabetter.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Future of Multi-Agent Collaboration in AI\",\"u\":\"https://www.almabetter.com/bytes/articles/metagpt\"},{\"a\":\"MetaGPT is a trending GitHub repository that simulates different roles in a software company using GPT-4. It's like a software company in a box (or CLI to be precise).\",\"ae\":null,\"c\":\"https://medium.com/@korolalexei/metagpt-a-multi-agent-framework-revolutionizing-software-development-f585fe1aa950\",\"d\":\"medium.com/@korolalexei/metagpt-a-multi-agent-framework-revolutionizing-software-development-f585fe1aa950\",\"da\":\"translations\",\"e\":\"2023-08-09T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: A Multi-Agent Framework Revolutionizing Software ... - Medium\",\"u\":\"https://medium.com/@korolalexei/metagpt-a-multi-agent-framework-revolutionizing-software-development-f585fe1aa950\"},{\"a\":\"You can check this by using:</span>\npython --version\n\n<span class=\"pl-c\"><span class=\"pl-c\">#</span> Step 3: Clone the repository to your local machine, and install it.</span>\ngit clone https://github.com/geekan/metagpt\n<span class=\"pl-c1\">cd</span> metagpt\npython setup.py install</pre></div>\n<h3 tabindex=\"-1\" dir=\"auto\"><a id=\...\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/PlaiD3/MetaGPT/blob/main/README.md\",\"d\":\"github.com/PlaiD3/MetaGPT/blob/main/README.md\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Multi-Agent Meta Programming Framework - GitHub\",\"u\":\"https://github.com/PlaiD3/MetaGPT/blob/main/README.md\"},{\"a\":\"\\u2014 MetaGPT is a multi-agent framework that enables collaboration among AI agents to tackle complex tasks and achieve collective intelligence. How does MetaGPT work? \\u2014 MetaGPT assigns specific roles to GPT agents based on their strengths and expertise, allowing them to collaborate, communicate, and share information to effectively tackle ...\",\"ae\":null,\"c\":\"https://eightify.app/summary/computer-science-and-technology/metagpt-advanced-autonomous-ai-agents-installation-tutorial\",\"d\":\"eightify.app/summary/computer-science-and-technology/metagpt-advanced-autonomous-ai-agents-installation-tutorial\",\"da\":\"\",\"h\":0,\"i\":\"eightify.app\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Advanced Autonomous AI Agents Installation Tutorial\",\"u\":\"https://eightify.app/summary/computer-science-and-technology/metagpt-advanced-autonomous-ai-agents-installation-tutorial\"},{\"a\":\"Therefore, we introduce MetaGPT, an innovative framework that incorporates efficient human workflows as a meta programming approach into LLM-based multi-agent collaboration. Specifically, MetaGPT encodes Standardized Operating Procedures (SOPs) into prompts to enhance structured coordination. ... SOPs act as a meta-function, taking the team and ...\",\"ae\":null,\"b\":\"arx\\tarXiv.org\\tarxiv.org\",\"c\":\"https://ar5iv.labs.arxiv.org/html/2308.00352\",\"d\":\"ar5iv.labs.arxiv.org/html/2308.00352\",\"da\":\"translations\",\"e\":\"2023-09-05T00:00:00.0000000\",\"h\":0,\"i\":\"ar5iv.labs.arxiv.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Meta Programming for Multi-Agent Collaborative Framework\",\"u\":\"https://ar5iv.labs.arxiv.org/html/2308.00352\"},{\"a\":\"Discover MetaGPT, a cutting-edge technology that harnesses Standardized Operating Procedures (SOPs) to orchestrate Large Language Model (LLM)-driven multi-agent systems, revolutionizing software development and collaborative task resolution. Explore its key features, delve into the core mechanisms, and learn how it enhances collaboration efficiency.\",\"ae\":null,\"c\":\"https://www.freegpttools.org/metagpt\",\"d\":\"www.freegpttools.org/metagpt\",\"da\":\"\",\"h\":0,\"i\":\"www.freegpttools.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Unlocking the Power of MetaGPT: A Multi-Agent Framework for Complex ...\",\"u\":\"https://www.freegpttools.org/metagpt\"},{\"a\":\"Message Function: Retained for event notification, weakened data transportation. Configuration Optimization: Default to gpt-4-1106-preview. ~/.metagpt for highest priority config, reading config.yaml. METAGPT_PROJECT_ROOT for workspace path specification. project_name specification via command line, generated by ProductManager. CLI Support\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT/releases\",\"d\":\"github.com/geekan/MetaGPT/releases\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Releases \\u00b7 geekan/MetaGPT \\u00b7 GitHub\",\"u\":\"https://github.com/geekan/MetaGPT/releases\"},{\"a\":\"SOPs act as a meta-function here, coordinating agents to auto-generate code based on defined inputs. In simple terms, it's as if you've turned a highly coordinated team of software engineers into an adaptable, intelligent software system. ... MetaGPT's architecture is divided into two layers: the Foundational Components Layer and the ...\",\"ae\":null,\"c\":\"https://theventurecation.com/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"d\":\"theventurecation.com/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"da\":\"\",\"e\":\"2023-09-11T00:00:00.0000000\",\"h\":0,\"i\":\"theventurecation.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\"u\":\"https://theventurecation.com/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\"},{\"a\":\"Today, we are excited to take the next significant step forward and introduce a new Copilot key to Windows 11 PCs. In this new year, we will be ushering in a significant shift toward a more personal and intelligent computing future where AI will be seamlessly woven into Windows from the system, to the silicon, to the hardware.\",\"ae\":null,\"c\":\"https://blogs.windows.com/windowsexperience/2024/01/04/introducing-a-new-copilot-key-to-kick-off-the-year-of-ai-powered-windows-pcs/\",\"d\":\"blogs.windows.com/windowsexperience/2024/01/04/introducing-a-new-copilot-key-to-kick-off-the-year-of-ai-powered-windows-pcs/\",\"da\":\"translations\",\"e\":\"2024-01-04T00:00:00.0000000\",\"h\":0,\"i\":\"blogs.windows.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Introducing a new Copilot key to kick off the year of AI-powered ...\",\"u\":\"https://blogs.windows.com/windowsexperience/2024/01/04/introducing-a-new-copilot-key-to-kick-off-the-year-of-ai-powered-windows-pcs/\"},{\"a\":\"11 Cosmic Contingencies About 600,000 words between ChatGPT and I later. Please see pinned post on profile for modification of the Einstein field equations including contributions from quantum ram...\",\"ae\":null,\"c\":\"https://www.instagram.com/richfieldmusic/p/C1bpt1eucbU/\",\"d\":\"www.instagram.com/richfieldmusic/p/C1bpt1eucbU/\",\"da\":\"\",\"h\":0,\"i\":\"www.instagram.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"\\u042f\\u13c6\\u13df\\u13bb\\u0192\\u13c6\\u13ac\\u13de\\u13a0 on Instagram\",\"u\":\"https://www.instagram.com/richfieldmusic/p/C1bpt1eucbU/\"},{\"n\":\"/d.js?q=The%20function%20of%20MetaGPT&kl=wt-wt&l=wt-wt&p=&s=25&ex=-1&ct=US&sp=0&vqd=4-148519746540767190220111387879117509726\"}]);DDG.duckbar.load('images');DDG.duckbar.load('news');DDG.duckbar.load('videos');DDG.duckbar.loadModule('related_searches');if (DDG.pageLayout) DDG.pageLayout.initialize({\"mainline\":{\"items\":[[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"]]}}, { start: 0 });DDG.deep.emit(\"load:completed\");", + "curl-cffi-POST-https://duckduckgo.com-{\"data\": {\"q\": \"What llm MetaGPT support\"}}": "What llm MetaGPT support at DuckDuckGo
", + "curl-cffi-GET-https://links.duckduckgo.com/d.js-{\"params\": {\"bing_market\": \"wt-WT\", \"df\": null, \"ex\": \"-1\", \"kl\": \"wt-wt\", \"l\": \"wt-wt\", \"q\": \"What llm MetaGPT support\", \"s\": \"0\", \"sp\": \"0\", \"vqd\": \"4-73487995398881375915343809280473758117\"}}": "if (DDG.deep && DDG.deep.setUpstream) DDG.deep.setUpstream(\"bingv7aa\");DDG.deep.bn={'ivc':1};if (DDG.pageLayout) DDG.pageLayout.load('a',[], {\"page_load_url\":\"https://duckduckgo.com/y.js?iurl=%7B2%7DIG%3D0C43B15D5A884367BD85DF1F28ABDA06%26CID%3D26CF35F2E42B60EF229421F4E5D6611D%26Type%3DEvent.CPT%26DATA%3D0\"});DDG.deep.signalSummary = \"\";DDG.inject('DDG.Data.languages.resultLanguages', {\"en\":[\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"https://docs.deepwisdom.ai/main/en/guide/tutorials/integration_with_open_llm.html\",\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"https://mathaware.org/ai/metagpt-encoding-sops-with-llm-agents/\",\"https://arxiv.org/abs/2308.00352\",\"https://github.com/geekan/MetaGPT\",\"https://www.louisbouchard.ai/metagpt/\",\"https://lablab.ai/blog/this-week-in-ai-exploring-the-latest-from-metagpt-and-gpt4-and-more\",\"https://www.linkedin.com/pulse/what-metagpt-llm-agents-collaborating-solve-complex-bouchard-\",\"https://towardsai.net/p/machine-learning/what-is-metagpt-llm-agents-collaborating-to-solve-complex-tasks\",\"https://medium.com/mlearning-ai/metagpt-multi-agent-harmony-for-complex-problem-solving-97bcb8f3fe94\",\"https://medium.com/@yousra.aoudi/navigating-the-future-metagpts-innovative-approach-to-multi-agent-collaboration-ed1cc5835011\",\"https://openreview.net/forum?id=VtmBAGCN7o\",\"https://hackernoon.com/autogpt-langchain-deep-lake-metagpt-building-the-ultimate-llm-app\",\"https://generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\",\"https://ar5iv.labs.arxiv.org/html/2308.00352\",\"https://louisbouchard.substack.com/p/what-is-metagpt-llm-agents-collaborating\",\"https://developer.nvidia.com/blog/supercharging-llm-applications-on-windows-pcs-with-nvidia-rtx-systems/\",\"https://github.com/geekan/MetaGPT/releases\",\"https://github.com/geekan/MetaGPT-docs/blob/main/src/en/guide/tutorials/integration_with_open_llm.md\",\"https://mathaware.org/ai/empowering-ai-with-llm-based-agents-metagpt-framework-transforms-human-sops/\",\"https://stackshare.io/metagpt\",\"https://medium.com/gta-generative-tech-advances/metagpt-an-interesting-approach-to-multi-agent-collaboration-5ace263c4fd8\",\"https://nvidianews.nvidia.com/news/generative-ai-rtx-pcs-and-workstations\",\"https://www.intel.com/content/www/us/en/developer/articles/technical/finetuning-llms-on-intel-gpus-using-bigdl-llm.html\",\"https://arxiv.org/abs/2401.05778\",\"https://www.ft.com/content/116f3541-bf2f-483e-a36a-ed3618548f9b\"],\"zh-CN\":[\"https://community.modelscope.cn/659cb258d4226e0eb42708e5.html\"]});DDG.deep.pageLayoutSummary = \"w29\";DDG.inject('DDG.Data.languages.adLanguages', {});if (DDG.pageLayout) DDG.pageLayout.load('d',[{\"a\":\"Enter MetaGPT \\u2014 a Multi-agent system that utilizes Large Language models by Sirui Hong fuses Standardized Operating Procedures (SOPs) with LLM-based multi-agent systems. This emerging paradigm disrupts the existing limitations of LLMs in fostering effective collaboration and task decomposition in complex, real-world applications.\",\"ae\":null,\"c\":\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"d\":\"www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\",\"da\":\"\",\"e\":\"2023-09-11T00:00:00.0000000\",\"h\":0,\"i\":\"www.unite.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Complete Guide to the Best AI Agent Available Right Now\",\"u\":\"https://www.unite.ai/metagpt-complete-guide-to-the-best-ai-agent-available-right-now/\"},{\"a\":\"The methods of integrating open source LLM and integrating some non-openai closed source models (such as Baidu Wenxinyiyan, iFLYTEK Spark, Zhipu ChatGLM, etc.) are similar, the main difference is the configuration. For details on the configuration of other closed-source LLMs, please refer to other LLM configuration documents under the online ...\",\"ae\":null,\"c\":\"https://docs.deepwisdom.ai/main/en/guide/tutorials/integration_with_open_llm.html\",\"d\":\"docs.deepwisdom.ai/main/en/guide/tutorials/integration_with_open_llm.html\",\"da\":\"\",\"e\":\"2023-12-21T00:00:00.0000000\",\"h\":0,\"i\":\"docs.deepwisdom.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Integration with open LLM | MetaGPT\",\"u\":\"https://docs.deepwisdom.ai/main/en/guide/tutorials/integration_with_open_llm.html\"},{\"a\":\"MetaGPT is a multi-agent system that utilizes Large Language Models (LLMs) to perform complex tasks. It is designed to overcome the limitations of LLMs in fostering effective collaboration and...\",\"ae\":null,\"c\":\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"d\":\"www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\",\"da\":\"\",\"e\":\"2023-12-13T00:00:00.0000000\",\"h\":0,\"i\":\"www.straight.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"A Complete Guide to MetaGPT: The Best AI Agent Available Now\",\"u\":\"https://www.straight.com/guides/software/a-complete-guide-to-metagpt-the-best-ai-agent-available-now/\"},{\"a\":\"The advent of MetaGPT and similar LLM agents represents a significant leap forward in the realm of process management and optimization. By addressing the complexities of encoding SOPs and acknowledging the nuanced nature of their integration, these intelligent systems are poised to redefine operational efficiency.\",\"ae\":null,\"c\":\"https://mathaware.org/ai/metagpt-encoding-sops-with-llm-agents/\",\"d\":\"mathaware.org/ai/metagpt-encoding-sops-with-llm-agents/\",\"da\":\"\",\"h\":0,\"i\":\"mathaware.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Encoding SOPs with LLM Agents | MathAware AI\",\"u\":\"https://mathaware.org/ai/metagpt-encoding-sops-with-llm-agents/\"},{\"a\":\"Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks.\",\"ae\":null,\"b\":\"arx\\tarXiv.org\\tarxiv.org\",\"c\":\"https://arxiv.org/abs/2308.00352\",\"d\":\"arxiv.org/abs/2308.00352\",\"da\":\"translations\",\"e\":\"2023-08-01T00:00:00.0000000\",\"h\":0,\"i\":\"arxiv.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework\",\"u\":\"https://arxiv.org/abs/2308.00352\"},{\"a\":\"agent multi-agent gpt hacktoberfest llm metagpt Resources. Readme License. MIT license Activity. Stars. 33.2k stars Watchers. 802 watching Forks. 3.9k forks Report repository Releases 11. Patch release: v0.6.4 Latest Jan 12, 2024 + 10 releases Packages 0. No packages published . Contributors 55 + 41 contributors Languages.\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT\",\"d\":\"github.com/geekan/MetaGPT\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: The Multi-Agent Framework - GitHub\",\"u\":\"https://github.com/geekan/MetaGPT\"},{\"a\":\"Aug 27, 2023 \\u2022 6 min read Watch the video! MetaGPT: Redefining Multi-Agent Collaboration for Complex Tasks Watch on Thanks to GPT and the recent large language models, we've seen the popularization of a new type of AI-based system\\u2026 agents. An agent is basically an AI model like ChatGPT that can access and interact with one or more applications.\",\"ae\":null,\"c\":\"https://www.louisbouchard.ai/metagpt/\",\"d\":\"www.louisbouchard.ai/metagpt/\",\"da\":\"\",\"e\":\"2023-08-27T00:00:00.0000000\",\"h\":0,\"i\":\"www.louisbouchard.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Mitigating AI Hallucinations: Exploring MetaGPT's Collaborative Framework\",\"u\":\"https://www.louisbouchard.ai/metagpt/\"},{\"a\":\"MetaGPT is a groundbreaking multi-agent framework that is transforming the way software development is approached. By taking a single line of requirement as input, MetaGPT outputs a comprehensive array of development components, including user stories, competitive analysis, requirements, data structures, APIs, and documents.\",\"ae\":null,\"c\":\"https://lablab.ai/blog/this-week-in-ai-exploring-the-latest-from-metagpt-and-gpt4-and-more\",\"d\":\"lablab.ai/blog/this-week-in-ai-exploring-the-latest-from-metagpt-and-gpt4-and-more\",\"da\":\"\",\"e\":\"2023-08-11T00:00:00.0000000\",\"h\":0,\"i\":\"lablab.ai\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"This Week in AI: Exploring the Latest from MetaGPT and GPT-4 and more..\",\"u\":\"https://lablab.ai/blog/this-week-in-ai-exploring-the-latest-from-metagpt-and-gpt4-and-more\"},{\"a\":\"This iteration focuses on MetaGPT, a new approach to improving collaborations between AI agents (e.g., ChatGPT-based entities mimicking human roles). ... 3D-LLM Unleashes Language Models into the ...\",\"ae\":null,\"b\":\"li\\tLinkedIn\\twww.linkedin.com\",\"c\":\"https://www.linkedin.com/pulse/what-metagpt-llm-agents-collaborating-solve-complex-bouchard-\",\"d\":\"www.linkedin.com/pulse/what-metagpt-llm-agents-collaborating-solve-complex-bouchard-\",\"da\":\"\",\"e\":\"2023-08-28T00:00:00.0000000\",\"h\":0,\"i\":\"www.linkedin.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What is MetaGPT? LLM Agents Collaborating to Solve Complex Tasks - LinkedIn\",\"u\":\"https://www.linkedin.com/pulse/what-metagpt-llm-agents-collaborating-solve-complex-bouchard-\"},{\"a\":\"Latest Machine Learning What is MetaGPT? LLM Agents Collaborating to Solve Complex Tasks August 28, 2023 Last Updated on August 29, 2023 by Editorial Team Author (s): Louis Bouchard Watch the video! This member-only story is on us. Upgrade to access all of Medium. Originally published on louisbouchard.ai, read it 2 days before on my blog!\",\"ae\":null,\"c\":\"https://towardsai.net/p/machine-learning/what-is-metagpt-llm-agents-collaborating-to-solve-complex-tasks\",\"d\":\"towardsai.net/p/machine-learning/what-is-metagpt-llm-agents-collaborating-to-solve-complex-tasks\",\"da\":\"\",\"e\":\"2023-08-29T00:00:00.0000000\",\"h\":0,\"i\":\"towardsai.net\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What is MetaGPT? LLM Agents Collaborating to Solve Complex Tasks\",\"u\":\"https://towardsai.net/p/machine-learning/what-is-metagpt-llm-agents-collaborating-to-solve-complex-tasks\"},{\"a\":\"You know how those multi-agent systems powered by Large Language Models (LLMs) have the potential to mimic and jazz up human workflows? But, the real world's a tangled place, and these systems...\",\"ae\":null,\"c\":\"https://medium.com/mlearning-ai/metagpt-multi-agent-harmony-for-complex-problem-solving-97bcb8f3fe94\",\"d\":\"medium.com/mlearning-ai/metagpt-multi-agent-harmony-for-complex-problem-solving-97bcb8f3fe94\",\"da\":\"\",\"e\":\"2023-08-09T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Multi-Agent Harmony for Complex Problem Solving\",\"u\":\"https://medium.com/mlearning-ai/metagpt-multi-agent-harmony-for-complex-problem-solving-97bcb8f3fe94\"},{\"a\":\"T he essence of MetaGPT is the seamless integration of SOPs to craft a highly coordinated LLM-based multi-agent ecosystem. With a focus on emulating human-like roles and intricate workflows, it...\",\"ae\":null,\"c\":\"https://medium.com/@yousra.aoudi/navigating-the-future-metagpts-innovative-approach-to-multi-agent-collaboration-ed1cc5835011\",\"d\":\"medium.com/@yousra.aoudi/navigating-the-future-metagpts-innovative-approach-to-multi-agent-collaboration-ed1cc5835011\",\"da\":\"translations\",\"e\":\"2023-08-10T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Navigating the Future: MetaGPT's Innovative Approach to ... - Medium\",\"u\":\"https://medium.com/@yousra.aoudi/navigating-the-future-metagpts-innovative-approach-to-multi-agent-collaboration-ed1cc5835011\"},{\"a\":\"Recently, remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Previous LLM-based multi-agent systems can already solve simple dialogue tasks.\",\"ae\":null,\"c\":\"https://openreview.net/forum?id=VtmBAGCN7o\",\"d\":\"openreview.net/forum?id=VtmBAGCN7o\",\"da\":\"\",\"e\":\"2023-09-22T00:00:00.0000000\",\"h\":0,\"i\":\"openreview.net\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Meta Programming for Multi-Agent Collaborative Framework\",\"u\":\"https://openreview.net/forum?id=VtmBAGCN7o\"},{\"a\":\"Deep Lake is a remarkable answer to the problem of storing gigabytes of data for LLMs \\u2014 efficiently, easily, and practically. Its unique configuration allows the optimal usage of finances. OpenAI's LLM Operational Cost Daily is on average 700,000 USD a day. Some are even predicting bankruptcy for the company.\",\"ae\":null,\"c\":\"https://hackernoon.com/autogpt-langchain-deep-lake-metagpt-building-the-ultimate-llm-app\",\"d\":\"hackernoon.com/autogpt-langchain-deep-lake-metagpt-building-the-ultimate-llm-app\",\"da\":\"\",\"e\":\"2023-08-29T00:00:00.0000000\",\"h\":0,\"i\":\"hackernoon.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Deep Lake \\u2014 MetaGPT: Building the Ultimate LLM App - HackerNoon\",\"u\":\"https://hackernoon.com/autogpt-langchain-deep-lake-metagpt-building-the-ultimate-llm-app\"},{\"a\":\"The MetaGPT approach showcases its ability to decompose highlevel tasks into detailed actionable components handled by distinct roles (ProductManager, Architect, ProjectManager, Engineer, QA Engineer), thereby facilitating role-specific expertise and coordination. This methodology mirrors human software development teams.\",\"ae\":null,\"c\":\"https://generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\",\"d\":\"generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\",\"da\":\"translations\",\"e\":\"2023-08-14T00:00:00.0000000\",\"h\":0,\"i\":\"generativeai.pub\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Analyzing an exciting Generative AI research called MetaGPT.\",\"u\":\"https://generativeai.pub/analyzing-an-exciting-generative-ai-research-called-metagpt-2106385312db\"},{\"a\":\"In this work, we present MetaGPT, a promising framework for collaborative agents using SOPs that leverages LLMs to mimic efficient human workflows. MetaGPT is a meta programming technology that utilizes SOPs to coordinate LLM-based multi-agent systems. Specifically, to encode SOPs into prompts, MetaGPT manages multi-agents through role ...\",\"ae\":null,\"b\":\"arx\\tarXiv.org\\tarxiv.org\",\"c\":\"https://ar5iv.labs.arxiv.org/html/2308.00352\",\"d\":\"ar5iv.labs.arxiv.org/html/2308.00352\",\"da\":\"translations\",\"e\":\"2023-09-05T00:00:00.0000000\",\"h\":0,\"i\":\"ar5iv.labs.arxiv.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: Meta Programming for Multi-Agent Collaborative Framework\",\"u\":\"https://ar5iv.labs.arxiv.org/html/2308.00352\"},{\"a\":\"MetaGPT: Meta Programming for Multi-Agent Collaborative Framework. Topsakal, O., & Akinci, T.C. (2023). Creating Large Language Model Applications Utilizing LangChain: A Primer on Developing LLM ...\",\"ae\":null,\"c\":\"https://medium.com/technology-hits/autogpt-langchain-deep-lake-metagpt-a-revolutionary-framework-for-building-advanced-ai-e2c579d86494\",\"d\":\"medium.com/technology-hits/autogpt-langchain-deep-lake-metagpt-a-revolutionary-framework-for-building-advanced-ai-e2c579d86494\",\"da\":\"\",\"e\":\"2023-08-28T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"AutoGPT \\u2014 LangChain \\u2014 Deep Lake \\u2014 MetaGPT: A ... - Medium\",\"u\":\"https://medium.com/technology-hits/autogpt-langchain-deep-lake-metagpt-a-revolutionary-framework-for-building-advanced-ai-e2c579d86494\"},{\"a\":\"Louis , starting with a trending topic: AI agents! This iteration focuses on MetaGPT, a new approach to improving collaborations between AI agents (e.g., ChatGPT-based entities mimicking human roles).\",\"ae\":null,\"c\":\"https://louisbouchard.substack.com/p/what-is-metagpt-llm-agents-collaborating\",\"d\":\"louisbouchard.substack.com/p/what-is-metagpt-llm-agents-collaborating\",\"da\":\"\",\"e\":\"2023-08-28T00:00:00.0000000\",\"h\":0,\"i\":\"louisbouchard.substack.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What is MetaGPT? LLM Agents Collaborating to Solve Complex Tasks\",\"u\":\"https://louisbouchard.substack.com/p/what-is-metagpt-llm-agents-collaborating\"},{\"a\":\"Today, LLM-powered applications are running predominantly in the cloud. However, many use cases that would benefit from running LLMs locally on Windows PCs, including gaming, creativity, productivity, and developer experiences. AT CES 2024, NVIDIA announced several developer tools to accelerate LLM inference and development on NVIDIA RTX ...\",\"ae\":null,\"c\":\"https://developer.nvidia.com/blog/supercharging-llm-applications-on-windows-pcs-with-nvidia-rtx-systems/\",\"d\":\"developer.nvidia.com/blog/supercharging-llm-applications-on-windows-pcs-with-nvidia-rtx-systems/\",\"da\":\"\",\"e\":\"2024-01-08T00:00:00.0000000\",\"h\":0,\"i\":\"developer.nvidia.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Supercharging LLM Applications on Windows PCs with NVIDIA RTX Systems\",\"u\":\"https://developer.nvidia.com/blog/supercharging-llm-applications-on-windows-pcs-with-nvidia-rtx-systems/\"},{\"a\":\"Supported Ollama as underlying LLM #603 by @better629; Enabled MetaGPT to be used as a dependency for web applications, such as https: ... PIP Support: pip install metagpt is now available for installing and using metagpt, enabling direct access to the command-line version of metagpt.\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT/releases\",\"d\":\"github.com/geekan/MetaGPT/releases\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Releases \\u00b7 geekan/MetaGPT \\u00b7 GitHub\",\"u\":\"https://github.com/geekan/MetaGPT/releases\"},{\"a\":\"If you want to support <code>http: //ip:11434/api/chat</code>, you can do as follows:</p>\n<div class=\"highlight highlight-source-shell notranslate position-relative overflow-auto\" dir=\"auto\" data-snippet-clipboard-copy-content=\"service ollama stop\n\nOLLAMA_HOST=0.0.0.0 OLLAMA_ORIGINS=* ollama serve # one terminal\n\nollama run llama2 # ot...\",\"ae\":null,\"b\":\"gh\\tGitHub\\tgithub.com\",\"c\":\"https://github.com/geekan/MetaGPT-docs/blob/main/src/en/guide/tutorials/integration_with_open_llm.md\",\"d\":\"github.com/geekan/MetaGPT-docs/blob/main/src/en/guide/tutorials/integration_with_open_llm.md\",\"da\":\"\",\"h\":0,\"i\":\"github.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Integration with open LLM - GitHub\",\"u\":\"https://github.com/geekan/MetaGPT-docs/blob/main/src/en/guide/tutorials/integration_with_open_llm.md\"},{\"a\":\"With LLM-based agents empowered by the MetaGPT framework, companies can streamline their workflows and improve productivity. These agents can assist employees by automating repetitive tasks, generating reports, and even coming up with creative solutions to problems. The MetaGPT framework allows for fine-tuning the LLM-based agents based on ...\",\"ae\":null,\"c\":\"https://mathaware.org/ai/empowering-ai-with-llm-based-agents-metagpt-framework-transforms-human-sops/\",\"d\":\"mathaware.org/ai/empowering-ai-with-llm-based-agents-metagpt-framework-transforms-human-sops/\",\"da\":\"\",\"h\":0,\"i\":\"mathaware.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Empowering AI with LLM-based Agents: MetaGPT Framework Transforms Human ...\",\"u\":\"https://mathaware.org/ai/empowering-ai-with-llm-based-agents-metagpt-framework-transforms-human-sops/\"},{\"a\":\"Check out popular companies that use MetaGPT and some tools that integrate with MetaGPT. ... On top of llm, there is a CLI application, llm-cli, which provides a convenient interface for running inference on supported models. Chroma. It is an open-source embedding database. Chroma makes it easy to build LLM apps by making knowledge, facts, and ...\",\"ae\":null,\"c\":\"https://stackshare.io/metagpt\",\"d\":\"stackshare.io/metagpt\",\"da\":\"\",\"h\":0,\"i\":\"stackshare.io\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT - Reviews, Pros & Cons | Companies using MetaGPT - StackShare\",\"u\":\"https://stackshare.io/metagpt\"},{\"a\":\"MetaGPT is the maestro who brings harmony to this chaos. By encoding Standardized Operating Procedures (SOPs) into prompts, MetaGPT ensures structured collaboration akin to a well-rehearsed ...\",\"ae\":null,\"c\":\"https://medium.com/gta-generative-tech-advances/metagpt-an-interesting-approach-to-multi-agent-collaboration-5ace263c4fd8\",\"d\":\"medium.com/gta-generative-tech-advances/metagpt-an-interesting-approach-to-multi-agent-collaboration-5ace263c4fd8\",\"da\":\"\",\"e\":\"2023-08-15T00:00:00.0000000\",\"h\":0,\"i\":\"medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MetaGPT: An Interesting Approach to Multi-Agent Collaboration\",\"u\":\"https://medium.com/gta-generative-tech-advances/metagpt-an-interesting-approach-to-multi-agent-collaboration-5ace263c4fd8\"},{\"a\":\"NVIDIA recently extended TensorRT to text-based applications with TensorRT-LLM for Windows, an open-source library for accelerating LLMs. The latest update to TensorRT-LLM, available now, adds Phi-2 to the growing list of pre-optimized models for PC, which run up to 5x faster compared to other inference backends.\",\"ae\":null,\"c\":\"https://nvidianews.nvidia.com/news/generative-ai-rtx-pcs-and-workstations\",\"d\":\"nvidianews.nvidia.com/news/generative-ai-rtx-pcs-and-workstations\",\"da\":\"\",\"e\":\"2024-01-08T00:00:00.0000000\",\"h\":0,\"i\":\"nvidianews.nvidia.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"NVIDIA Brings Generative AI to Millions, With Tensor Core GPUs, LLMs ...\",\"u\":\"https://nvidianews.nvidia.com/news/generative-ai-rtx-pcs-and-workstations\"},{\"a\":\"The BigDL LLM library extends support for fine-tuning LLMs to a variety of Intel GPUs, including the Intel\\u00ae Data Center GPU Flex 170 and Intel\\u00ae Arc\\u2122 series graphics. Specifically, using the Intel\\u00ae Data Center GPU Flex 170 hardware as an example, you can complete the fine-tuning of the Llama 2 7B model in approximately 2 hours on a single ...\",\"ae\":null,\"b\":\"ark\\tIntel Processor Specification\\tark.intel.com\",\"c\":\"https://www.intel.com/content/www/us/en/developer/articles/technical/finetuning-llms-on-intel-gpus-using-bigdl-llm.html\",\"d\":\"www.intel.com/content/www/us/en/developer/articles/technical/finetuning-llms-on-intel-gpus-using-bigdl-llm.html\",\"da\":\"\",\"e\":\"2023-12-22T00:00:00.0000000\",\"h\":0,\"i\":\"www.intel.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Fine-tuning Llama 2 models on Intel\\u00ae Data Center GPUs using BigDL LLM\",\"u\":\"https://www.intel.com/content/www/us/en/developer/articles/technical/finetuning-llms-on-intel-gpus-using-bigdl-llm.html\"},{\"a\":\"Large language models (LLMs) have strong capabilities in solving diverse natural language processing tasks. However, the safety and security issues of LLM systems have become the major obstacle to their widespread application. Many studies have extensively investigated risks in LLM systems and developed the corresponding mitigation strategies. Leading-edge enterprises such as OpenAI, Google ...\",\"ae\":null,\"b\":\"arx\\tarXiv.org\\tarxiv.org\",\"c\":\"https://arxiv.org/abs/2401.05778\",\"d\":\"arxiv.org/abs/2401.05778\",\"da\":\"translations\",\"e\":\"2024-01-11T09:29:00.0000000\",\"h\":0,\"i\":\"arxiv.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"[2401.05778] Risk Taxonomy, Mitigation, and Assessment Benchmarks of ...\",\"u\":\"https://arxiv.org/abs/2401.05778\"},{\"a\":\"It carries on regardless and gives a definitive answer anyway," the BIS paper noted. The tendency of LLMs to make hilariously confident mistakes (eg inventing case law) is sometimes innocuously ...\",\"ae\":null,\"c\":\"https://www.ft.com/content/116f3541-bf2f-483e-a36a-ed3618548f9b\",\"d\":\"www.ft.com/content/116f3541-bf2f-483e-a36a-ed3618548f9b\",\"da\":\"\",\"e\":\"2024-01-05T12:13:51.0000000\",\"h\":0,\"i\":\"www.ft.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"BIS vs LLM - Financial Times\",\"u\":\"https://www.ft.com/content/116f3541-bf2f-483e-a36a-ed3618548f9b\"},{\"a\":\"\\u5927\\u578b\\u8bed\\u8a00\\u6a21\\u578b\\uff08LLM\\uff09\\u7684\\u51fa\\u73b0\\u5e26\\u706b\\u4e86Agent\\u3002\\u5229\\u7528LLM\\u7406\\u89e3\\u4eba\\u7c7b\\u610f\\u56fe\\u3001\\u751f\\u6210\\u590d\\u6742\\u8ba1\\u5212\\u5e76\\u4e14\\u80fd\\u591f\\u81ea\\u4e3b\\u884c\\u52a8\\u7684\\u80fd\\u529b\\u3002Agent\\u5177\\u6709\\u65e0\\u4e0e\\u4f26\\u6bd4\\u7684\\u80fd\\u529b\\uff0c\\u80fd\\u591f\\u505a\\u51fa\\u7c7b\\u4f3c\\u4e8e\\u4eba\\u7c7b\\u590d\\u6742\\u6027\\u7684\\u51b3\\u7b56\\u548c\\u5b8c\\u6210\\u4e00\\u4e9b\\u590d\\u6742\\u7684\\u5de5\\u4f5c\\u3002\\u76ee\\u524d\\u5e02\\u9762\\u4e0a\\u5df2\\u7ecf\\u51fa\\u73b0\\u975e\\u5e38\\u591a\\u5f97Agent\\u6846\\u67b6\\uff1aXAgent, AutoGPT\\u3001BabyAGI\\u3001CAMEL\\u3001MetaGPT\\u3001AutoGen\\u3001DSPy\\u3001AutoAgents\\u3001OpenAgents ...\",\"ae\":null,\"c\":\"https://community.modelscope.cn/659cb258d4226e0eb42708e5.html\",\"d\":\"community.modelscope.cn/659cb258d4226e0eb42708e5.html\",\"da\":\"translations\",\"e\":\"2024-01-09T00:00:00.0000000\",\"h\":0,\"i\":\"community.modelscope.cn\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"\\u5982\\u4f55\\u63d0\\u5347\\u5927\\u6a21\\u578bAgent\\u7684\\u80fd\\u529b \\u2014\\u2014LLM Agent\\u6846\\u67b6 modelscope-agent \\u5b9e\\u6218\",\"u\":\"https://community.modelscope.cn/659cb258d4226e0eb42708e5.html\"},{\"n\":\"/d.js?q=What%20llm%20MetaGPT%20support&kl=wt-wt&l=wt-wt&p=&s=29&ex=-1&ct=US&sp=0&vqd=4-73487995398881375915343809280473758117\"}]);DDG.duckbar.load('images');DDG.duckbar.load('news');DDG.duckbar.load('videos');DDG.duckbar.loadModule('related_searches');if (DDG.pageLayout) DDG.pageLayout.initialize({\"mainline\":{\"items\":[[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"]]}}, { start: 0 });DDG.deep.emit(\"load:completed\");", + "curl-cffi-POST-https://duckduckgo.com-{\"data\": {\"q\": \"dataiku\"}}": "dataiku at DuckDuckGo
", + "curl-cffi-POST-https://duckduckgo.com-{\"data\": {\"q\": \"datarobot\"}}": "datarobot at DuckDuckGo
", + "curl-cffi-GET-https://links.duckduckgo.com/d.js-{\"params\": {\"bing_market\": \"wt-WT\", \"df\": null, \"ex\": \"-1\", \"kl\": \"wt-wt\", \"l\": \"wt-wt\", \"q\": \"datarobot\", \"s\": \"0\", \"sp\": \"0\", \"vqd\": \"4-305438614248843041332096319235456803678\"}}": "DDG.search.altIsNavigational = 1;DDG.search.isNavigational = 1;if (DDG.deep && DDG.deep.setUpstream) DDG.deep.setUpstream(\"bingv7aa\");DDG.deep.bn={'ivc':1};if (DDG.pageLayout) DDG.pageLayout.load('a',[{\"a\":\"\\u9ad8\\u7cbe\\u5ea6\\u306a\\u6a5f\\u68b0\\u5b66\\u7fd2\\u30e2\\u30c7\\u30eb\\u3092\\u69cb\\u7bc9\\u3001\\u5b9f\\u88c5\\u3001\\u904b\\u7528\\u3002DataRobot\\u306f\\u793e\\u5185\\u30c7\\u30fc\\u30bf\\u304b\\u3089\\u65b0\\u3057\\u3044\\u4fa1\\u5024\\u3092\\u5275\\u9020\\u3057\\u307e\\u3059. DataRobot\\u306f\\u4f01\\u696d\\u306e\\u8ab2\\u984c\\u89e3\\u6c7a\\u306b\\u7279\\u5316\\u3002\\u610f\\u601d\\u6c7a\\u5b9a\\u306e\\u81ea\\u52d5\\u5316\\u304b\\u3089\\u9700\\u8981\\u4e88\\u6e2c\\u3001\\u8981\\u56e0\\u5206\\u6790\\u307e\\u3067\\u3053\\u306a\\u3059AI\\u30c4\\u30fc\\u30eb\",\"adext\":{\"callout\":{\"t\":\"Accelerate Time to Impact \\u00b7 Trust Your AI Models\",\"tid\":\"6\"},\"filterlinks\":{\"l\":[],\"tid\":\"\"},\"sitelinks\":{\"l\":[{\"snippet\":\"Explore the DataRobot AI Platform Get Started With a 30-Day Trial\",\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=4t4PwhnMmcY7atJfp41CAw%3D%3D&rut=e62e2cb72625106a43222549f786956db024f90f62131cbc4a16a28c8968f74c&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8CWdnSSqYRxodv2hK6GQYijVUCUw3ed58BZbCDycwDIpFPyWnwhXm4uvKBLQcGynMpDz_AvA1H9RQnhR9goEmV9Ya3_wHg3eI0DOkTWJinjiudX5vGJJNWufOQNDYFdDHFVXChhUck3LNxc3D4UakPcG3Fgqa6IzJHoPcJWXkWGOqxuYGxVGkxJO3aqSinbclEqi5d0At_9OjMeDihix9q58SuTw%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZnRyaWFsJTJmJTNmdXRtX21lZGl1bSUzZHNlYXJjaCUyNnV0bV9zb3VyY2UlM2RiaW5nJTI2dXRtX2NhbXBhaWduJTNkRnJlZVRyaWFsMjAyM1dXMDgxNkdQU2FkZXh0JTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDFlNjcxOTNiY2UzZDFlNzBhZTQ2N2M5ODMxM2UxOTI0%26rlid%3D1e67193bce3d1e70ae467c98313e1924&vqd=4-304301655096002530435728103296846286110&iurl=%7B1%7DIG%3DEFC9E56534984E60A01E1AD18F949C41%26CID%3D17342A5B7AD96D85041C3E5D7B5C6C74%26ID%3DDevEx%2C5065.1\",\"text\":\"DataRobot Free Trial\"},{\"snippet\":\"Unlock Your AI Success in 2023 Tips on the Path of Value-Driven AI\",\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=4t4PwhnMmcY7atJfp41CAw%3D%3D&rut=25d9bbfaa9cbfaaf08d9a6b444b633a6ce8d72930552b70b34d90df428188bf0&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8qLHGkuDcZ8xxbn%2DtJPQw1jVUCUxi3KfzBWZ8dNgaK8%2DSoRj4nbRrRFfQVuiV7AIxRtZS4mXd7F1paHlN1BDqwOZNm7_O3fvHO59UXgQmhFNY1DQ7kMdZ%2Did8G0JnG_Kzxief1jx20D1mrfhnsLHb6_5GY1RZ4vzYXUnjih6Hh8nrgoRbxzYS5s8evGIka2E8%2Dq%2DIbZtX%2DEHSMg1sz2yxt770lqc%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZnJlc291cmNlcyUyZmFpc3VjY2VzczIwMjMlMmYlM2Z1dG1fbWVkaXVtJTNkc2VhcmNoJTI2dXRtX3NvdXJjZSUzZGJpbmclMjZ1dG1fY2FtcGFpZ24lM2RDb250ZW50MTBLZXlzdG9BSVN1Y2Nlc3MyMDIzV1cwNTIyR1BTYWRleHQlMjZ1dG1fdGVybSUzZGRhdGFyb2JvdCUyNnV0bV9jb250ZW50JTNkYWRfZXh0JTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDBiNTgwOTJlZGMzNjFlNGFiOTgyNmM4ZDIzMzViNTFm%26rlid%3D0b58092edc361e4ab9826c8d2335b51f&vqd=4-17900397268746114651881769682671895645&iurl=%7B1%7DIG%3DEFC9E56534984E60A01E1AD18F949C41%26CID%3D17342A5B7AD96D85041C3E5D7B5C6C74%26ID%3DDevEx%2C5067.1\",\"text\":\"10 Keys to AI Success\"},{\"snippet\":\"Our Platform Includes Four Fully Integrated Products. Read More.\",\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=4t4PwhnMmcY7atJfp41CAw%3D%3D&rut=9b50c0e6e845f83a4b6122341b7007b55cc637bf24bc814ebfbdb41c4570e842&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De80Tber2J5eyzs7ehxic3bQzVUCUyYDJpssb8FQM4q5TzHPQTbxhVuzWgr30VBdcQ%2Du_fAfiqmWEHQ13X%2DWe_zzqhxfJqe8TH1WdLsIIKUrxWqqxfZyPQuZ818htUh82k2s2Co_K3ZgklXSA%2Duj9j4sghZ155%2DCpGDXbSizpxOVw8TwgUDyW_ZxEZDxtS0Rk5iH4G6PuzQvhP02YdMD_rMZTOt42M%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZnByb2R1Y3QlMmYlM2ZjYW1wYWlnbmlkJTNkNTMwNzA4MDk5JTI2YWRncm91cGlkJTNkMTM1MDIwMjc3NDIxNzY5OCUyNmFkaWQlM2QlMjZtc2Nsa2lkJTNkZDQ0ZDJiNzQ0YjEzMWFmZTcyZDQ0ZWQ3YjQxMDY3MDI%26rlid%3Dd44d2b744b131afe72d44ed7b4106702&vqd=4-135405568356283083312160903053804829572&iurl=%7B1%7DIG%3DEFC9E56534984E60A01E1AD18F949C41%26CID%3D17342A5B7AD96D85041C3E5D7B5C6C74%26ID%3DDevEx%2C5069.1\",\"text\":\"Product Overview\"}],\"tid\":\"7\\t9[8]\\t11[10]\\t13[12]\",\"type\":\"EnhancedSiteLink\"},\"tid\":\"1\"},\"ae\":{\"callout\":[\"Accelerate Time to Impact \\u00b7 Trust Your AI Models\"]},\"c\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=4t4PwhnMmcY7atJfp41CAw%3D%3D&rut=4e8bc6239074926ffa0595d2f0838a03d95a9f20653372406dff4b73bb47a802&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De87ziwl19iJFSSt9AnpU7A2TVUCUyhd2uAWuXw7lbtLG3tobaae8IKDFy1RftUyaK7hmjFguIcBXLMF0__8U%2DYMqp1lRmGet90G40qSPB8wuC4MyZjuA8D06WqXRZsdl4uyGEuNXLmrp1n4swCoXfw3cJtq1Sl1iqwNQBdH4Ev%2DJQUf54N5TQ274OfwCR8PMamVlYCWg%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZmpwJTJmbHAlMmZhaS1mb3ItYnVzaW5lc3MlMmYlM2Z1dG1fbWVkaXVtJTNkc2VhcmNoJTI2dXRtX3NvdXJjZSUzZGJpbmclMjZ1dG1fY2FtcGFpZ24lM2RERU1PMjAyM0FsbFByb2R1Y3RzSlAwNjI2QlBTJTI2dXRtX3Rlcm0lM2RkYXRhcm9ib3QlMjZ1dG1fY29udGVudCUzZERSX2JyYW5kZWRfcnNhJTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDdlMDA4NWE0OTQ3MzE5ODdlNzJjZTAwNzZiNzAxMmFm%26rlid%3D7e0085a494731987e72ce0076b7012af&vqd=4-129716528454193272263152190229962811420&iurl=%7B1%7DIG%3DEFC9E56534984E60A01E1AD18F949C41%26CID%3D17342A5B7AD96D85041C3E5D7B5C6C74%26ID%3DDevEx%2C5060.1\",\"d\":\"datarobot.com\",\"h\":0,\"i\":\"\",\"k\":0,\"m\":0,\"o\":\"\",\"p\":1,\"relevancy\":{\"abstract\":\"%E9%AB%98%E7%B2%BE%E5%BA%A6%E3%81%AA%E6%A9%9F%E6%A2%B0%E5%AD%A6%E7%BF%92%E3%83%A2%E3%83%87%E3%83%AB%E3%82%92%E6%A7%8B%E7%AF%89%E3%80%81%E5%AE%9F%E8%A3%85%E3%80%81%E9%81%8B%E7%94%A8%E3%80%82%3Cb%3EDataRobot%3C%2Fb%3E%E3%81%AF%E7%A4%BE%E5%86%85%E3%83%87%E3%83%BC%E3%82%BF%E3%81%8B%E3%82%89%E6%96%B0%E3%81%97%E3%81%84%E4%BE%A1%E5%80%A4%E3%82%92%E5%89%B5%E9%80%A0%E3%81%97%E3%81%BE%E3%81%99.%20DataRobot%E3%81%AF%E4%BC%81%E6%A5%AD%E3%81%AE%E8%AA%B2%E9%A1%8C%E8%A7%A3%E6%B1%BA%E3%81%AB%E7%89%B9%E5%8C%96%E3%80%82%E6%84%8F%E6%80%9D%E6%B1%BA%E5%AE%9A%E3%81%AE%E8%87%AA%E5%8B%95%E5%8C%96%E3%81%8B%E3%82%89%E9%9C%80%E8%A6%81%E4%BA%88%E6%B8%AC%E3%80%81%E8%A6%81%E5%9B%A0%E5%88%86%E6%9E%90%E3%81%BE%E3%81%A7%E3%81%93%E3%81%AA%E3%81%99AI%E3%83%84%E3%83%BC%E3%83%AB\",\"adx_name\":\"none\",\"is_good_v10\":1,\"organic_ranks\":[\"0\",1,2,3,5,6,7,8,9,10,11,12,13,14,15,18],\"q\":\"datarobot\",\"q_words\":1,\"q_words_fuzzy\":1,\"q_words_in_ad\":1,\"root_domain\":\"datarobot.com\",\"start\":\"0\",\"title\":\"%E3%83%87%E3%83%BC%E3%82%BF%E3%81%8B%E3%82%89%E6%96%B0%E3%81%97%E3%81%84%E4%BE%A1%E5%80%A4%E3%82%92%20%2D%20%E7%A4%BE%E5%86%85%E3%83%87%E3%83%BC%E3%82%BF%E3%81%8B%E3%82%89%E4%BE%A1%E5%80%A4%E5%89%B5%E5%87%BA\"},\"s\":\"bingv7aa\",\"t\":\"\\u30c7\\u30fc\\u30bf\\u304b\\u3089\\u65b0\\u3057\\u3044\\u4fa1\\u5024\\u3092 - \\u793e\\u5185\\u30c7\\u30fc\\u30bf\\u304b\\u3089\\u4fa1\\u5024\\u5275\\u51fa\",\"tid\":\"1,6,7,9[8],11[10],13[12]\",\"u\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=4t4PwhnMmcY7atJfp41CAw%3D%3D&rut=4e8bc6239074926ffa0595d2f0838a03d95a9f20653372406dff4b73bb47a802&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De87ziwl19iJFSSt9AnpU7A2TVUCUyhd2uAWuXw7lbtLG3tobaae8IKDFy1RftUyaK7hmjFguIcBXLMF0__8U%2DYMqp1lRmGet90G40qSPB8wuC4MyZjuA8D06WqXRZsdl4uyGEuNXLmrp1n4swCoXfw3cJtq1Sl1iqwNQBdH4Ev%2DJQUf54N5TQ274OfwCR8PMamVlYCWg%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZmpwJTJmbHAlMmZhaS1mb3ItYnVzaW5lc3MlMmYlM2Z1dG1fbWVkaXVtJTNkc2VhcmNoJTI2dXRtX3NvdXJjZSUzZGJpbmclMjZ1dG1fY2FtcGFpZ24lM2RERU1PMjAyM0FsbFByb2R1Y3RzSlAwNjI2QlBTJTI2dXRtX3Rlcm0lM2RkYXRhcm9ib3QlMjZ1dG1fY29udGVudCUzZERSX2JyYW5kZWRfcnNhJTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDdlMDA4NWE0OTQ3MzE5ODdlNzJjZTAwNzZiNzAxMmFm%26rlid%3D7e0085a494731987e72ce0076b7012af&vqd=4-129716528454193272263152190229962811420&iurl=%7B1%7DIG%3DEFC9E56534984E60A01E1AD18F949C41%26CID%3D17342A5B7AD96D85041C3E5D7B5C6C74%26ID%3DDevEx%2C5060.1\"}], {\"page_load_url\":\"https://duckduckgo.com/y.js?ifu=%7B3%7Dappid%3D055AAD1BA669BEB8B048128DC89A107C678B527B%26rguid%3Dbff00ba70e8f4285a2ad22f803500ac4&iurl=%7B2%7DIG%3DEFC9E56534984E60A01E1AD18F949C41%26CID%3D17342A5B7AD96D85041C3E5D7B5C6C74%26Type%3DEvent.CPT%26DATA%3D0\",\"visibility_url\":\"https://duckduckgo.com/y.js?ivu=%7B4%7Dtype%3Dmv%26reqver%3D1.0%26rg%3Dbff00ba70e8f4285a2ad22f803500ac4\"});DDG.deep.signalSummary = \"\";DDG.inject('DDG.Data.languages.resultLanguages', {\"en\":[\"https://www.datarobot.com/\",\"https://www.datarobot.com/trial/\",\"https://www.datarobot.com/pricing/\",\"https://www.datarobot.com/platform/new/datarobot-9-0/\",\"https://www.linkedin.com/company/datarobot/\",\"https://docs.datarobot.com/\",\"https://docs.datarobot.com/en/docs/get-started/index.html\",\"https://www.datarobot.com/newsroom/press/datarobot-launches-pathfinder-a-comprehensive-library-of-100-ai-use-cases/\",\"https://www.datarobot.com/blog/introducing-the-datarobot-use-case-value-tracker/\",\"https://docs.datarobot.com/en/docs/data/index.html\",\"https://app.datarobot.com/\",\"https://pathfinder.datarobot.com/integrations\",\"https://docs.datarobot.com/en/docs/api/api-quickstart/index.html\",\"https://docs.datarobot.com/en/docs/data/connect-data/data-conn.html\",\"https://app.datarobot.com/sign-in\",\"https://learn.datarobot.com/\",\"https://www.carahsoft.com/datarobot\",\"https://www.afa.org/company/datarobot/\",\"https://www.datarobot.com/use-cases/\",\"https://www.nomuraholdings.com/top.html\",\"https://www.nomura.com/\"],\"es\":[\"https://vivevirtual.es/inteligencia-artificial/tutoriales-ia/como-integrar-datarobot-en-squarespace/\"]});DDG.deep.pageLayoutSummary = \"a1w22v1r1\";DDG.inject('DDG.Data.languages.adLanguages', {});if (DDG.pageLayout) DDG.pageLayout.load('d',[{\"a\":\"DataRobot is a leading platform for generative and predictive AI that lets you focus on tangible business outcomes, not infrastructure. Learn how DataRobot helps customers across industries and organizations scale AI with enterprise monitoring, governance, and open ecosystems.\",\"ae\":null,\"c\":\"https://www.datarobot.com/\",\"d\":\"www.datarobot.com\",\"da\":\"\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot AI Platform | Deliver Value from AI\",\"u\":\"https://www.datarobot.com/\"},{\"a\":\"DataRobot is a single platform that streamlines your predictive and generative AI workflows. Start your free 30-day trial to experience how to fast-track preparing data, running experiments, and testing models, and to automate your AI processes with a single solution.\",\"ae\":null,\"c\":\"https://www.datarobot.com/trial/\",\"d\":\"www.datarobot.com/trial/\",\"da\":\"\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot AI Platform Free Trial | DataRobot AI Platform\",\"u\":\"https://www.datarobot.com/trial/\"},{\"a\":\"DataRobot offers a range of pricing plans to suit your business needs and goals, from Essentials to Business Critical. Learn how to customize your solution, get support, and see the ROI and savings of DataRobot AI Platform.\",\"ae\":null,\"c\":\"https://www.datarobot.com/pricing/\",\"d\":\"www.datarobot.com/pricing/\",\"da\":\"\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Pricing | DataRobot AI Platform\",\"u\":\"https://www.datarobot.com/pricing/\"},{\"a\":\"DataRobot AI Platform 9.0 is a complete and open AI lifecycle platform that leverages machine learning and supports Experimentation, Production, and Compliance. Learn about the new features, such as collaborative experimentation, workbench, data preparation, notebooks, drift management, and more, and how they integrate with Snowflake, GitHub, SAP, and Kubernetes.\",\"ae\":null,\"c\":\"https://www.datarobot.com/platform/new/datarobot-9-0/\",\"d\":\"www.datarobot.com/platform/new/datarobot-9-0/\",\"da\":\"translations\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot AI Platform 9.0 Release | DataRobot AI Platform\",\"u\":\"https://www.datarobot.com/platform/new/datarobot-9-0/\"},{\"a\":\"DataRobot is the Value-Driven AI company, empowering organizations to accelerate AI from idea to impact. With over a decade at the forefront of AI innovation, we know what it takes to make a real ...\",\"ae\":null,\"b\":\"li\\tLinkedIn\\twww.linkedin.com\",\"c\":\"https://www.linkedin.com/company/datarobot/\",\"d\":\"www.linkedin.com/company/datarobot/\",\"da\":\"\",\"h\":0,\"i\":\"www.linkedin.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot | LinkedIn\",\"u\":\"https://www.linkedin.com/company/datarobot/\"},{\"a\":\"Learn how to use DataRobot, a platform for data science and machine learning, with UI and API docs, tutorials, and release information. Find out how to get started, manage the platform, and access additional resources for modeling success.\",\"ae\":null,\"c\":\"https://docs.datarobot.com/\",\"d\":\"docs.datarobot.com\",\"da\":\"\",\"h\":0,\"i\":\"docs.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot Product Documentation\",\"u\":\"https://docs.datarobot.com/\"},{\"a\":\"Learn how to use DataRobot's value-driven AI to analyze data, create and deploy models, and work with code-first notebooks. Explore the topics of workbench, data preparation, model building, model exploration, model deployment, and more.\",\"ae\":null,\"c\":\"https://docs.datarobot.com/en/docs/get-started/index.html\",\"d\":\"docs.datarobot.com/en/docs/get-started/index-html\",\"da\":\"\",\"e\":\"2023-08-21T00:00:00.0000000\",\"h\":0,\"i\":\"docs.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Get started: DataRobot docs\",\"u\":\"https://docs.datarobot.com/en/docs/get-started/index.html\"},{\"a\":\"DataRobot is the leader in enterprise AI, delivering trusted AI technology and enablement services to global enterprises competing in today's Intelligence Revolution. DataRobot's enterprise AI platform democratizes data science with end-to-end automation for building, deploying, and managing machine learning models. This platform maximizes ...\",\"ae\":null,\"c\":\"https://www.datarobot.com/newsroom/press/datarobot-launches-pathfinder-a-comprehensive-library-of-100-ai-use-cases/\",\"d\":\"www.datarobot.com/newsroom/press/datarobot-launches-pathfinder-a-comprehensive-library-of-100-ai-use-cases/\",\"da\":\"translations\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot Launches Pathfinder: A Comprehensive Library of 100+ AI Use ...\",\"u\":\"https://www.datarobot.com/newsroom/press/datarobot-launches-pathfinder-a-comprehensive-library-of-100-ai-use-cases/\"},{\"a\":\"In Release 6.1, we are thrilled to introduce the DataRobot Use Case Value Tracker, designed to help you with the business operationalization of your AI.As a centralized hub to collaborate with team members on any machine learning initiative from start to finish, it provides a systematic way to manage, monitor, and track the return on investment generated from your AI efforts.\",\"ae\":null,\"c\":\"https://www.datarobot.com/blog/introducing-the-datarobot-use-case-value-tracker/\",\"d\":\"www.datarobot.com/blog/introducing-the-datarobot-use-case-value-tracker/\",\"da\":\"\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Introducing the DataRobot Use Case Value Tracker\",\"u\":\"https://www.datarobot.com/blog/introducing-the-datarobot-use-case-value-tracker/\"},{\"a\":\"Learn how to import, transform, analyze, and manage data for machine learning projects using DataRobot tools and visualizations. Find out the data requirements, limitations, and best practices for different data types, sources, and scenarios.\",\"ae\":null,\"c\":\"https://docs.datarobot.com/en/docs/data/index.html\",\"d\":\"docs.datarobot.com/en/docs/data/index-html\",\"da\":\"\",\"e\":\"2023-06-15T00:00:00.0000000\",\"h\":0,\"i\":\"docs.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Data: DataRobot docs\",\"u\":\"https://docs.datarobot.com/en/docs/data/index.html\"},{\"a\":\"DataRobot\",\"ae\":null,\"c\":\"https://app.datarobot.com/\",\"d\":\"app.datarobot.com\",\"da\":\"\",\"h\":0,\"i\":\"app.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot\",\"u\":\"https://app.datarobot.com/\"},{\"a\":\"DataRobot does not share customer data, personal data, or sensitive use cases on Pathfinder. The AI applications and frameworks shared in Pathfinder are widespread and commonplace across their respective industries. This tool was developed to provide a framework for how you can solve AI use cases with problems that are within the context of ...\",\"ae\":null,\"c\":\"https://pathfinder.datarobot.com/integrations\",\"d\":\"pathfinder.datarobot.com/integrations\",\"da\":\"\",\"h\":0,\"i\":\"pathfinder.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Integrations | Explore 100+ AI Use Cases | DataRobot Pathfinder\",\"u\":\"https://pathfinder.datarobot.com/integrations\"},{\"a\":\"API quickstart. The DataRobot API provides a programmatic alternative to the web interface for creating and managing DataRobot projects. The API can be used via REST or with DataRobot's Python or R clients in Windows, UNIX, and OS X environments. This guide walks you through setting up your environment and then you can follow a sample problem ...\",\"ae\":null,\"c\":\"https://docs.datarobot.com/en/docs/api/api-quickstart/index.html\",\"d\":\"docs.datarobot.com/en/docs/api/api-quickstart/index-html\",\"da\":\"\",\"e\":\"2023-08-07T00:00:00.0000000\",\"h\":0,\"i\":\"docs.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"API Quickstart: DataRobot docs\",\"u\":\"https://docs.datarobot.com/en/docs/api/api-quickstart/index.html\"},{\"a\":\"From the Data Connections tab, select the data connection in the left-panel connections list. Click the Delete button in the upper right ( ). DataRobot prompts for confirmation. Click Delete to remove the data connection. If there are data sources dependent on the data connection, DataRobot returns a notification.\",\"ae\":null,\"c\":\"https://docs.datarobot.com/en/docs/data/connect-data/data-conn.html\",\"d\":\"docs.datarobot.com/en/docs/data/connect-data/data-conn.html\",\"da\":\"\",\"e\":\"2023-11-15T00:00:00.0000000\",\"h\":0,\"i\":\"docs.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Data connections: DataRobot docs - DataRobot AI Platform\",\"u\":\"https://docs.datarobot.com/en/docs/data/connect-data/data-conn.html\"},{\"a\":\"Sign in to DataRobot, the leading enterprise AI platform that democratizes data science and automates machine learning. DataRobot offers comprehensive solutions for MLOps, AI use cases, and AI cloud. Learn from DataRobot University and Algorithmia, and join the Intelligence Revolution.\",\"ae\":null,\"c\":\"https://app.datarobot.com/sign-in\",\"d\":\"app.datarobot.com/sign-in\",\"da\":\"\",\"h\":0,\"i\":\"app.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot\",\"u\":\"https://app.datarobot.com/sign-in\"},{\"a\":\"This article will help you better navigate DataRobot University. View Details. What's New in 9.0. Class. Learn about new features in the DataRobot 9.0 release. View Details. Integrating Snowflake with DataRobot. Class. Connect Snowflake to DataRobot to build models and make predictions.\",\"ae\":null,\"c\":\"https://learn.datarobot.com/\",\"d\":\"learn.datarobot.com\",\"da\":\"\",\"h\":0,\"i\":\"learn.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot University\",\"u\":\"https://learn.datarobot.com/\"},{\"a\":\"DataRobot is the leader in enterprise AI, delivering trusted AI technology and ROI enablement services to global enterprises. DataRobot's enterprise AI platform democratizes data science with end-to-end automation for building, deploying, and managing machine learning models. This platform maximizes value to the mission by delivering AI at ...\",\"ae\":null,\"c\":\"https://www.carahsoft.com/datarobot\",\"d\":\"www.carahsoft.com/datarobot\",\"da\":\"\",\"h\":0,\"i\":\"www.carahsoft.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot - Enterprise AI Cloud Platform | Carahsoft\",\"u\":\"https://www.carahsoft.com/datarobot\"},{\"a\":\"DataRobot is the leading Augmented Intelligence platform, delivering trusted AI technology and ROI enablement services to global enterprises competing in today's Intelligence Revolution. Its enterprise AI platform maximizes business value by delivering AI at scale and continuously optimizing performance over time.\",\"ae\":null,\"c\":\"https://www.afa.org/company/datarobot/\",\"d\":\"www.afa.org/company/datarobot/\",\"da\":\"\",\"e\":\"2024-01-09T00:00:00.0000000\",\"h\":0,\"i\":\"www.afa.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot - Air & Space Forces Association\",\"u\":\"https://www.afa.org/company/datarobot/\"},{\"a\":\"DataRobot is a platform for generative and predictive AI that helps you deploy and run AI solutions across various industries and outcomes. Learn how DataRobot customers use their platform to solve business problems, innovate, and drive value with AI.\",\"ae\":null,\"c\":\"https://www.datarobot.com/use-cases/\",\"d\":\"www.datarobot.com/use-cases/\",\"da\":\"\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Machine Learning Use Cases | DataRobot AI Platform\",\"u\":\"https://www.datarobot.com/use-cases/\"},{\"a\":\"Para integrar DataRobot en tu sitio de Squarespace, iniciar con la configuraci\\u00f3n de una cuenta en la plataforma de DataRobot es esencial. El proceso es directo y f\\u00e1cil de seguir y asegurar\\u00e1 que dispongas de todas las herramientas anal\\u00edticas avanzadas para potenciar tu sitio web.. Crear Tu Cuenta de DataRobot. Visita el sitio web de DataRobot y localiza la opci\\u00f3n de registro.\",\"ae\":null,\"c\":\"https://vivevirtual.es/inteligencia-artificial/tutoriales-ia/como-integrar-datarobot-en-squarespace/\",\"d\":\"vivevirtual.es/inteligencia-artificial/tutoriales-ia/como-integrar-datarobot-en-squarespace/\",\"da\":\"\",\"e\":\"2024-01-11T00:00:00.0000000\",\"h\":0,\"i\":\"vivevirtual.es\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"C\\u00f3mo Integrar DataRobot En Squarespace \\ufe0f 2024 - \\u00a9Vive Virtual\",\"u\":\"https://vivevirtual.es/inteligencia-artificial/tutoriales-ia/como-integrar-datarobot-en-squarespace/\"},{\"a\":\"Nomura is a global financial services group with an integrated network spanning over 30 countries. By connecting markets East & West, Nomura services the needs of individuals, institutions, corporates and governments through its four business divisions: Retail, Asset Management, Wholesale (Global Markets and Investment Banking), and Merchant Banking.\",\"ae\":null,\"c\":\"https://www.nomuraholdings.com/top.html\",\"d\":\"www.nomuraholdings.com/top-html\",\"da\":\"\",\"h\":0,\"i\":\"www.nomuraholdings.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Home | NOMURA\",\"u\":\"https://www.nomuraholdings.com/top.html\"},{\"a\":\"Nomura is a global financial services group with an integrated network spanning over 30 countries. By connecting markets East & West, Nomura services the needs of individuals, institutions, corporates and governments through its four business divisions: Retail, Asset Management, Wholesale (Global Markets and Investment Banking), and Merchant ...\",\"ae\":null,\"c\":\"https://www.nomura.com/\",\"d\":\"www.nomura.com\",\"da\":\"\",\"h\":0,\"i\":\"www.nomura.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Home - NOMURA\",\"u\":\"https://www.nomura.com/\"},{\"n\":\"/d.js?q=datarobot&kl=wt-wt&l=wt-wt&p=&s=22&ex=-1&ct=US&sp=0&vqd=4-305438614248843041332096319235456803678\"}]);DDG.duckbar.load('images');DDG.duckbar.load('news');DDG.duckbar.load('videos', {\"ads\":[],\"query\":\"datarobot\",\"queryEncoded\":\"datarobot\",\"response_type\":\"places\",\"results\":[{\"content\":\"https://www.youtube.com/watch?v=vyi_0D-rJ1A\",\"description\":\"Demonstration of how the DataRobot AI Platform works covering both ML Experimentation and ML Production. Request a live, personalized demonstration at https://www.datarobot.com/request-a-demo. This demo shows the workflows in DataRobot data ingest and preparation, model development, insight extraction, model deployment, on-going monitoring and ...\",\"duration\":\"13:17\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/vyi_0D-rJ1A?autoplay=1\",\"image_token\":\"46e31c38546fa6c15f77d2eaca52158f719c396ddbc4e84f07f660a20f050f23\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.RjJmdFbBiUCndVAZOmjitwEsDh&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.RjJmdFbBiUCndVAZOmjitwEsDh&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM2.GlK_gSFTQdYbbg_1695678156&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.RjJmdFbBiUCndVAZOmjitwEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-06-13T21:14:17.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":5574},\"title\":\"DataRobot AI Platform Demo 2023 | End-to-end Workflow | How DataRobot Works\",\"uploader\":\"DataRobot\"},{\"content\":\"https://www.youtube.com/watch?v=cOV5dss8xo0\",\"description\":\"DataRobot offers a platform and a reusable framework for developing AI applications that have a generative and a predictive component to them. Watch the process of creating a fully functioning joint generative and predictive AI solution for a real-world business problem that delivers tangible value. Use this framework and process to deliver ...\",\"duration\":\"5:06\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/cOV5dss8xo0?autoplay=1\",\"image_token\":\"1f5b660aa742a554ce19c9e8b001eb5d5a89059afab5ab4ef499f34bbef8ae2d\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.z0cOprAHCz_P_Hpd5bMHWgEsDh&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.z0cOprAHCz_P_Hpd5bMHWgEsDh&pid=Api\",\"motion\":\"https://tse1.mm.bing.net/th?id=OM1.pQ6zRQHggxqCCw_1696646714&pid=Api\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.z0cOprAHCz_P_Hpd5bMHWgEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-08-18T22:22:31.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":7622},\"title\":\"End-to-end Generative AI Applications with DataRobot | Develop, Deploy, Monitor and Maintain\",\"uploader\":\"DataRobot\"},{\"content\":\"https://www.youtube.com/watch?v=IMP0OZC6wPw\",\"description\":\"DataRobot is the leading end-to-end enterprise AI/ML platform that automates the process of building, training and deploying AI models at scale. Download the data and slides here: https://drive.google.com/drive/folders/1Zl1XO24zkbY7fHEh59Ux3NssNPXQD19t?usp=sharing In this video, we will learn how to build, train and deploy a machine learning ...\",\"duration\":\"21:22\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/IMP0OZC6wPw?autoplay=1\",\"image_token\":\"1a5261fccec96060141db7cec373afd6834e80eed802a6ed6c7ee3f67f6228ec\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.uJ2Vw0goB-5yx8dORs0CPgHgFo&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.uJ2Vw0goB-5yx8dORs0CPgHgFo&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM2.21pythA4GgwdwQ&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.uJ2Vw0goB-5yx8dORs0CPgHgFo&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2021-08-08T15:42:18.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":18696},\"title\":\"DataRobot AI For Absolute Beginners (Part 1) | Build, Train & Deploy an AI in 30 Minutes\",\"uploader\":\"Prof. Ryan Ahmed\"},{\"content\":\"https://www.youtube.com/watch?v=Grip5G1EUgY\",\"description\":\"Machine learning models developed with DataRobot can be deployed to Azure ML with complete service health, drift and accuracy monitoring. In this video Brian Bell demonstrates the Azure ML deployment capability. Users can create a DataRobot-managed AzureML prediction environment to deploy DataRobot Scoring Code in AzureML. With DataRobot ...\",\"duration\":\"3:22\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/Grip5G1EUgY?autoplay=1\",\"image_token\":\"8db48ef7fbe873efad3cfa34f62c3b13b4e77e556767a5d60a215edbb13b3e14\",\"images\":{\"large\":\"https://tse3.mm.bing.net/th?id=OVP.klj-M0G2PlRq58QgzSlIwAEsDh&pid=Api\",\"medium\":\"https://tse3.mm.bing.net/th?id=OVP.klj-M0G2PlRq58QgzSlIwAEsDh&pid=Api\",\"motion\":\"https://tse3.mm.bing.net/th?id=OM.-_UGz9qtcxRXvw_1704026949&pid=Api\",\"small\":\"https://tse3.mm.bing.net/th?id=OVP.klj-M0G2PlRq58QgzSlIwAEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-06-09T20:38:50.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":409},\"title\":\"Deploy DataRobot Models to AzureML | Demonstration of Azure ML Deployment Capability\",\"uploader\":\"DataRobot\"},{\"content\":\"https://www.youtube.com/watch?v=xZUaBvPQfXY\",\"description\":\"Get a high-level introduction to DataRobot's AI Production through a tour of several live Deployments. See the monitoring, alerting, lifecycle management and reporting capabilities in action for both predictive and generative AI via a series of examples. Learn more at: https://www.datarobot.com/platform/ https://docs.datarobot.com/en/docs/mlops ...\",\"duration\":\"7:08\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/xZUaBvPQfXY?autoplay=1\",\"image_token\":\"faecb8d567fd4445c52cd8e60c649952b393188212856a19ce331371c4b4b21b\",\"images\":{\"large\":\"https://tse3.mm.bing.net/th?id=OVP.V95ETtZnbbbKDAA2lzjFHgEsDh&pid=Api\",\"medium\":\"https://tse3.mm.bing.net/th?id=OVP.V95ETtZnbbbKDAA2lzjFHgEsDh&pid=Api\",\"motion\":\"https://tse3.mm.bing.net/th?id=OM1.oMwA1JZw78kwsw_1701730108&pid=Api\",\"small\":\"https://tse3.mm.bing.net/th?id=OVP.V95ETtZnbbbKDAA2lzjFHgEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-11-09T05:05:53.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":329},\"title\":\"Operate AI with DataRobot | Welcome to the AI Operations Console for New DataRobot Users\",\"uploader\":\"DataRobot\"},{\"content\":\"https://www.youtube.com/watch?v=Y00VSO6Uq60\",\"description\":\"Complete all phases of building, operating and governing a Predictive AI solution following the starter Flight Delays Use Case. This starter use case showcases essential DataRobot capabilities, but is not comprehensive. Learn about the complete capabilities of the DataRobot AI Platform at https://www.datarobot.com/platform. Watch the video as ...\",\"duration\":\"14:12\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/Y00VSO6Uq60?autoplay=1\",\"image_token\":\"e687f48c41420bafef42b0d7aec2ea6e0d55ae6c8c51adbb6d76c5d197637430\",\"images\":{\"large\":\"https://tse3.mm.bing.net/th?id=OVP.WMkyYYho3O9V85gpNsutVAEsDh&pid=Api\",\"medium\":\"https://tse3.mm.bing.net/th?id=OVP.WMkyYYho3O9V85gpNsutVAEsDh&pid=Api\",\"motion\":\"https://tse3.mm.bing.net/th?id=OM1.s30yJWAIBWugpw_1704039193&pid=Api\",\"small\":\"https://tse3.mm.bing.net/th?id=OVP.WMkyYYho3O9V85gpNsutVAEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-11-28T02:29:50.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":829},\"title\":\"Predictive AI: Build, Operate, and Govern with the DataRobot AI Platform | Flight Delays Use Case\",\"uploader\":\"DataRobot\"},{\"content\":\"https://www.youtube.com/watch?v=Jj8JovBRflA\",\"description\":\"Quick overview of DataRobot AI Accelerators including how to access them, what topics are covered, and how to get started using them with the data science notebook of your choice. Learn more https://community.datarobot.com/t5/ai-accelerators-library/tkb-p/ai-accelerators-library https://github.com/datarobot-community/ai-accelerators Transcript ...\",\"duration\":\"1:45\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/Jj8JovBRflA?autoplay=1\",\"image_token\":\"2749c14ed9db6fea61b6d86d8b55a56c24a8ac5900035d1ce6b326d0f9d807fe\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.yk9KOy_GBh3vO51YxcV8NQEsDh&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.yk9KOy_GBh3vO51YxcV8NQEsDh&pid=Api\",\"motion\":\"https://tse1.mm.bing.net/th?id=OM2.w0xOKKBTuyvZdw_1699233002&pid=Api\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.yk9KOy_GBh3vO51YxcV8NQEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-09-28T17:01:32.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":1},\"title\":\"AI Accelerators Overview | Repeatable Workflows using the DataRobot API\",\"uploader\":\"DataRobot\"},{\"content\":\"https://www.youtube.com/watch?v=fm6nxsAo5J0\",\"description\":\"This demo showcases the end-to-end capabilities in the DataRobot Enterprise AI Platform using a house price listings dataset containing diverse feature types including numeric, categorical, raw text, images, and geospatial data. The demo takes us on a journey from raw data to value, and highlights DataRobot's governance, explainability, and ...\",\"duration\":\"4:56\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/fm6nxsAo5J0?autoplay=1\",\"image_token\":\"8aee60e8b0fc16a6e77cd5a9391dd3c6214fa2fab314b27a320055efcb29f75e\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.chafFyMzRYblao3a5sr79gEsDh&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.chafFyMzRYblao3a5sr79gEsDh&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM1.lHW5r59lMDBG5w_1684178452&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.chafFyMzRYblao3a5sr79gEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2020-08-11T16:00:10.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":17912},\"title\":\"DataRobot AI Vision Demo\",\"uploader\":\"DataRobot\"},{\"content\":\"https://www.youtube.com/watch?v=XhipOG-S1q8\",\"description\":\"This end-to-end demo shows the tight integrations between the DataRobot AI Platform and AWS services. By natively connecting to data in Amazon S3, you can build, test, and evaluate models in DataRobot, and then deploy them in Amazon SageMaker. These models can be monitored for drift and other relevant parameters via DataRobot MLOps. In this ...\",\"duration\":\"13:27\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/XhipOG-S1q8?autoplay=1\",\"image_token\":\"d2a00656028a69312df6f3ae2ff1e484fd23dc4bceff58bc5157813853d6db90\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.BC-1oDSg7Hw6OofUPNCBFwEsDh&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.BC-1oDSg7Hw6OofUPNCBFwEsDh&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM1.gmEOiAfzgn4Y-A_1684167397&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.BC-1oDSg7Hw6OofUPNCBFwEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-02-08T10:14:17.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":2025},\"title\":\"DataRobot and AWS: Rapidly Prototype and Deploy AI Models | Demo Tutorial\",\"uploader\":\"DataRobot\"},{\"content\":\"https://www.youtube.com/watch?v=RrbJLm6atwc\",\"description\":\"Please visit the 2023 DataRobot Product Demo at https://www.youtube.com/watch?v=vyi_0D-rJ1A This video shows the DataRobot AI Platform in action as of 2018. DataRobot is the category creator of AutoML and MLOps with a rich history of innovation as detailed here - https://www.datarobot.com/innovation. Our Platform is constantly evolving with new ...\",\"duration\":\"1:32\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/RrbJLm6atwc?autoplay=1\",\"image_token\":\"f08d101a4ecaa1ecbc1702f740cddd0e35c504901e82dcfe0276733759319a8e\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.NzKh9KZZ5OuUbK1j19RfbwHgFo&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.NzKh9KZZ5OuUbK1j19RfbwHgFo&pid=Api\",\"motion\":\"https://tse1.mm.bing.net/th?id=OM1.AWDbr86dOILmXQ_1645855537&pid=Api\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.NzKh9KZZ5OuUbK1j19RfbwHgFo&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2018-04-16T14:01:36.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":49270},\"title\":\"DataRobot AI Platform [2018 Version - Update Available]\",\"uploader\":\"DataRobot\"}],\"vqd\":{\"datarobot\":\"4-305438614248843041332096319235456803678\"}});DDG.duckbar.loadModule('related_searches', {\"ads\":[],\"query\":\"datarobot\",\"queryEncoded\":\"datarobot\",\"response_type\":\"places\",\"results\":[{\"display_text\":\"datarobot login\",\"text\":\"datarobot login\",\"web_search_url\":\"?q=datarobot%20login\"},{\"display_text\":\"datarobot download\",\"text\":\"datarobot download\",\"web_search_url\":\"?q=datarobot%20download\"},{\"display_text\":\"datarobot products\",\"text\":\"datarobot products\",\"web_search_url\":\"?q=datarobot%20products\"},{\"display_text\":\"datarobot company\",\"text\":\"datarobot company\",\"web_search_url\":\"?q=datarobot%20company\"},{\"display_text\":\"datarobot wikipedia\",\"text\":\"datarobot wikipedia\",\"web_search_url\":\"?q=datarobot%20wikipedia\"},{\"display_text\":\"datarobot artificial intelligence\",\"text\":\"datarobot artificial intelligence\",\"web_search_url\":\"?q=datarobot%20artificial%20intelligence\"},{\"display_text\":\"datarobot for your daily life\",\"text\":\"datarobot for your daily life\",\"web_search_url\":\"?q=datarobot%20for%20your%20daily%20life\"},{\"display_text\":\"data robot tool\",\"text\":\"data robot tool\",\"web_search_url\":\"?q=data%20robot%20tool\"}],\"vqd\":{\"datarobot\":\"4-305438614248843041332096319235456803678\"}});if (DDG.pageLayout) DDG.pageLayout.initialize({\"mainline\":{\"items\":[[\"ad\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"videos\"],[\"related_searches\"]]}}, { start: 0 });DDG.deep.emit(\"load:completed\");", + "curl-cffi-GET-https://links.duckduckgo.com/d.js-{\"params\": {\"bing_market\": \"wt-WT\", \"df\": null, \"ex\": \"-1\", \"kl\": \"wt-wt\", \"l\": \"wt-wt\", \"q\": \"dataiku\", \"s\": \"0\", \"sp\": \"0\", \"vqd\": \"4-337400409169293617055811118659485228425\"}}": "DDG.search.altIsNavigational = 1;DDG.search.isNavigational = 1;if (DDG.deep && DDG.deep.setUpstream) DDG.deep.setUpstream(\"bingv7aa\");DDG.deep.bn={'ivc':1};if (DDG.pageLayout) DDG.pageLayout.load('a',[], {\"page_load_url\":\"https://duckduckgo.com/y.js?iurl=%7B2%7DIG%3D4B3C73388F5840C299E628F54B339615%26CID%3D15DC198D7A096819249D0D8B7B3C6947%26Type%3DEvent.CPT%26DATA%3D0\"});DDG.duckbar.future_signal_tab({signal:'medium',from:'deep_answer'});DDG.duckbar.add({\"data\":{\"Abstract\":\"Dataiku is an artificial intelligence and machine learning company which was founded in 2013. In December 2019, Dataiku announced that CapitalG\\u2014the late-stage growth venture capital fund financed by Alphabet Inc.\\u2014joined Dataiku as an investor and that it had achieved unicorn status. As of 2021, Dataiku is valued at $4.6 billion. Dataiku currently employs more than 1,000 people worldwide between offices in New York, Denver, Washington DC, Los Angeles, Paris, London, Munich, Frankfurt, Sydney, Singapore, Tokyo, and Dubai.\",\"AbstractSource\":\"Wikipedia\",\"AbstractText\":\"Dataiku is an artificial intelligence and machine learning company which was founded in 2013. In December 2019, Dataiku announced that CapitalG\\u2014the late-stage growth venture capital fund financed by Alphabet Inc.\\u2014joined Dataiku as an investor and that it had achieved unicorn status. As of 2021, Dataiku is valued at $4.6 billion. Dataiku currently employs more than 1,000 people worldwide between offices in New York, Denver, Washington DC, Los Angeles, Paris, London, Munich, Frankfurt, Sydney, Singapore, Tokyo, and Dubai.\",\"AbstractURL\":\"https://en.wikipedia.org/wiki/Dataiku\",\"Answer\":\"\",\"AnswerType\":\"\",\"Definition\":\"\",\"DefinitionSource\":\"\",\"DefinitionURL\":\"\",\"Entity\":\"company\",\"Heading\":\"Dataiku\",\"Image\":\"/i/b50c1c3f.png\",\"ImageHeight\":270,\"ImageIsLogo\":1,\"ImageWidth\":483,\"Infobox\":{\"content\":[{\"data_type\":\"string\",\"label\":\"Type\",\"sort_order\":\"1000\",\"value\":\"Private\",\"wiki_order\":0},{\"data_type\":\"string\",\"label\":\"Industry\",\"sort_order\":\"1001\",\"value\":\"Computer software\",\"wiki_order\":1},{\"data_type\":\"string\",\"label\":\"Founded\",\"sort_order\":\"1\",\"value\":\"February 14, 2013 in Paris, France\",\"wiki_order\":2},{\"data_type\":\"string\",\"label\":\"Founders\",\"sort_order\":\"1002\",\"value\":\"Florian Douetteau, Cl\\u00e9ment Stenac, Marc Batty, Thomas Cabrol\",\"wiki_order\":3},{\"data_type\":\"string\",\"label\":\"Key people\",\"sort_order\":\"2\",\"value\":\"Florian Douetteau (CEO)\",\"wiki_order\":4},{\"data_type\":\"string\",\"label\":\"Products\",\"sort_order\":\"1003\",\"value\":\"Dataiku Data Science Studio\",\"wiki_order\":5},{\"data_type\":\"string\",\"label\":\"Revenue\",\"sort_order\":\"3\",\"value\":\"US$ 150 million (2021)\",\"wiki_order\":6},{\"data_type\":\"string\",\"label\":\"Number of employees\",\"sort_order\":\"1004\",\"value\":\"1,000+ (2022)\",\"wiki_order\":7},{\"data_type\":\"string\",\"label\":\"Website\",\"sort_order\":\"1005\",\"value\":\"[dataiku.com]\",\"wiki_order\":8},{\"data_type\":\"twitter_profile\",\"label\":\"Twitter profile\",\"value\":\"dataiku\",\"wiki_order\":\"102\"},{\"data_type\":\"instance\",\"label\":\"Instance of\",\"value\":{\"entity-type\":\"item\",\"id\":\"Q4830453\",\"numeric-id\":4830453},\"wiki_order\":\"207\"},{\"data_type\":\"official_website\",\"label\":\"Official Website\",\"value\":\"http://www.dataiku.com/\",\"wiki_order\":\"208\"}],\"meta\":[{\"data_type\":\"string\",\"label\":\"article_title\",\"value\":\"Dataiku\"},{\"data_type\":\"string\",\"label\":\"template_name\",\"value\":\"infobox company\"},{\"data_type\":\"string\",\"label\":\"formatting_rules\",\"value\":\"company\"}]},\"OfficialDomain\":\"dataiku.com\",\"OfficialWebsite\":\"https://dataiku.com\",\"Redirect\":\"\",\"RelatedTopics\":[{\"FirstURL\":\"https://duckduckgo.com/c/Big_data_companies\",\"Icon\":{\"Height\":\"\",\"URL\":\"\",\"Width\":\"\"},\"Result\":\"Big data companies\",\"Text\":\"Big data companies\"},{\"FirstURL\":\"https://duckduckgo.com/c/Data_analysis_software\",\"Icon\":{\"Height\":\"\",\"URL\":\"\",\"Width\":\"\"},\"Result\":\"Data analysis software\",\"Text\":\"Data analysis software\"},{\"FirstURL\":\"https://duckduckgo.com/c/Privately_held_companies_based_in_New_York_City\",\"Icon\":{\"Height\":\"\",\"URL\":\"\",\"Width\":\"\"},\"Result\":\"Privately held companies based in New York City\",\"Text\":\"Privately held companies based in New York City\"},{\"FirstURL\":\"https://duckduckgo.com/c/Proprietary_software\",\"Icon\":{\"Height\":\"\",\"URL\":\"\",\"Width\":\"\"},\"Result\":\"Proprietary software\",\"Text\":\"Proprietary software\"}],\"Results\":[{\"FirstURL\":\"https://dataiku.com\",\"Icon\":{\"Height\":16,\"URL\":\"/i/dataiku.com.ico\",\"Width\":16},\"Result\":\"Official site\",\"Text\":\"Official site\"},{\"FirstURL\":\"http://www.dataiku.com/\",\"Icon\":{\"Height\":16,\"URL\":\"/i/dataiku.com.ico\",\"Width\":16},\"Result\":\"Official site - Dataiku\",\"Text\":\"Official site - Dataiku\"}],\"Type\":\"A\",\"meta\":{\"attribution\":null,\"blockgroup\":null,\"created_date\":null,\"description\":\"Wikipedia\",\"designer\":null,\"dev_date\":null,\"dev_milestone\":\"live\",\"developer\":[{\"name\":\"DDG Team\",\"type\":\"ddg\",\"url\":\"http://www.duckduckhack.com\"}],\"example_query\":\"nikola tesla\",\"id\":\"wikipedia_fathead\",\"is_stackexchange\":null,\"js_callback_name\":\"wikipedia\",\"live_date\":null,\"maintainer\":{\"github\":\"duckduckgo\"},\"name\":\"Wikipedia\",\"perl_module\":\"DDG::Fathead::Wikipedia\",\"producer\":null,\"production_state\":\"online\",\"repo\":\"fathead\",\"signal_from\":\"wikipedia_fathead\",\"src_domain\":\"en.wikipedia.org\",\"src_id\":1,\"src_name\":\"Wikipedia\",\"src_options\":{\"directory\":\"\",\"is_fanon\":0,\"is_mediawiki\":1,\"is_wikipedia\":1,\"language\":\"en\",\"min_abstract_length\":\"20\",\"skip_abstract\":0,\"skip_abstract_paren\":0,\"skip_end\":\"0\",\"skip_icon\":0,\"skip_image_name\":0,\"skip_qr\":\"\",\"source_skip\":\"\",\"src_info\":\"\"},\"src_url\":null,\"status\":\"live\",\"tab\":\"About\",\"topic\":[\"productivity\"],\"unsafe\":0}},\"duckbar_topic\":\"About\",\"from\":\"deep_answer\",\"meta\":{\"attribution\":null,\"blockgroup\":null,\"created_date\":null,\"description\":\"Wikipedia\",\"designer\":null,\"dev_date\":null,\"dev_milestone\":\"live\",\"developer\":[{\"name\":\"DDG Team\",\"type\":\"ddg\",\"url\":\"http://www.duckduckhack.com\"}],\"example_query\":\"nikola tesla\",\"id\":\"wikipedia_fathead\",\"is_stackexchange\":null,\"js_callback_name\":\"wikipedia\",\"live_date\":null,\"maintainer\":{\"github\":\"duckduckgo\"},\"name\":\"Wikipedia\",\"perl_module\":\"DDG::Fathead::Wikipedia\",\"producer\":null,\"production_state\":\"online\",\"repo\":\"fathead\",\"signal_from\":\"wikipedia_fathead\",\"src_domain\":\"en.wikipedia.org\",\"src_id\":1,\"src_name\":\"Wikipedia\",\"src_options\":{\"directory\":\"\",\"is_fanon\":0,\"is_mediawiki\":1,\"is_wikipedia\":1,\"language\":\"en\",\"min_abstract_length\":\"20\",\"skip_abstract\":0,\"skip_abstract_paren\":0,\"skip_end\":\"0\",\"skip_icon\":0,\"skip_image_name\":0,\"skip_qr\":\"\",\"source_skip\":\"\",\"src_info\":\"\"},\"src_url\":null,\"status\":\"live\",\"tab\":\"About\",\"topic\":[\"productivity\"],\"unsafe\":0},\"model\":\"FatheadArticle\",\"official_site\":\"https://dataiku.com\",\"pixel_id\":\"wikipedia_fathead_deep\",\"signal\":\"medium\",\"templates\":{\"detail\":\"info_detail\"}});DDG.deep.signalSummary = \"about:m\";DDG.inject('DDG.Data.languages.resultLanguages', {\"en\":[\"https://www.dataiku.com/\",\"https://en.wikipedia.org/wiki/Dataiku\",\"https://www.dataiku.com/product/get-started/\",\"https://academy.dataiku.com/basics-101\",\"https://www.dataiku.com/product/dataiku-as-a-managed-service/\",\"https://knowledge.dataiku.com/latest/getting-started/about-dataiku/index.html\",\"https://discover.dataiku.com/data-quality/\",\"https://discover.dataiku.com/dataiku-12/\",\"https://www.linkedin.com/company/dataiku\",\"https://pages.dataiku.com/interactive-data-sheet\",\"https://developer.dataiku.com/latest/tutorials/index.html\",\"https://discover.dataiku.com/dataiku-for-generative-ai/\",\"https://blog.dataiku.com/dataiku-12\",\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\",\"https://blog.dataiku.com/why-users-love-dataiku\",\"https://knowledge.dataiku.com/latest/getting-started/about-dataiku/concept-value-proposition.html\",\"https://twitter.com/dataiku\",\"https://in.linkedin.com/company/persistent-systems\",\"https://www.freelancer.com/projects/database-administration/snowflake-dbt-dataiku-support\"],\"ja\":[\"https://jp.linkedin.com/in/tadashi-mishima-32638445\",\"https://www.intellilink.co.jp/topics/seminar_event/2024/dataiku-fy2023-2h.aspx\"]});DDG.deep.pageLayoutSummary = \"w5v1w16r1,e1\";DDG.inject('DDG.Data.languages.adLanguages', {});if (DDG.pageLayout) DDG.pageLayout.load('d',[{\"a\":\"Dataiku is a platform that lets you build, deploy, and manage data and AI projects all in one place. Whether you need to prepare data, train models, deploy models, or monitor and govern models, Dataiku has the tools and features to help you achieve your goals.\",\"ae\":null,\"c\":\"https://www.dataiku.com/\",\"d\":\"www.dataiku.com\",\"da\":\"\",\"h\":0,\"i\":\"www.dataiku.com\",\"k\":null,\"l\":[{\"snippet\":\"Dataiku saves time with quick visual analysis of columns, including the distribution of values, top values, outliers, invalids, and overall good statistics. For categorical data, the visual analysis includes the distribution by value. Martin Leijen . Business Data Architect at Action ...\",\"targetUrl\":\"https://www.dataiku.com/product/\",\"text\":\"Product\"},{\"snippet\":\"At Dataiku, we believe that diversity of people and thought is inherent to creating not only a top-quality product but an environment of inclusivity and belonging in which everyone can bring their full selves to work. It is the responsibility of every Dataiker to build a community of tolerance and open-mindedness.\",\"targetUrl\":\"https://www.dataiku.com/careers/\",\"text\":\"Careers\"},{\"snippet\":\"Dataiku lets you access and process data using the coding language of your choice, and lets you use code notebooks to prototype your recipes. Check out the use cases! Learn more Dataiku APIs . APIs in Dataiku allow coders to programmatically interact with various Dataiku objects and with the instance itself to accomplish a wide variety of tasks\",\"targetUrl\":\"https://www.dataiku.com/learn/\",\"text\":\"Learn\"},{\"snippet\":\"Thrive SPC Uses Dataiku, Snowflake, and Snow Fox Data to Improve Clinical Home Care. By moving to Dataiku and working with Dataiku partners, Snowflake and Snow Fox Data, Thrive Skilled Pediatric Care (Thrive SPC) has been able to advance from complicated spreadsheets to a central platform that provides clear insights and metrics to fuel their data-driven healthcare solutions.\",\"targetUrl\":\"https://www.dataiku.com/stories/\",\"text\":\"Stories\"},{\"snippet\":\"Dataiku was founded on the principle that in order to succeed in the world's rapidly evolving ecosystem, companies \\u2014 no matter what their industry or size \\u2014 must elevate their people to continuously innovate. Since 2013, Dataiku has been the leader in democratizing data and empowering organization-wide collaboration. We've been a part ...\",\"targetUrl\":\"https://www.dataiku.com/company/\",\"text\":\"Company\"},{\"snippet\":\"Join the Dataiku Partner Ecosystem. Become a part of the growing Dataiku service partner ecosystem or get in touch to talk integrations and technical partnerships.\",\"targetUrl\":\"https://www.dataiku.com/partners/\",\"text\":\"Partners\"}],\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku | Everyday AI, Extraordinary People\",\"u\":\"https://www.dataiku.com/\"},{\"a\":\"Dataiku is an artificial intelligence (AI) and machine learning company which was founded in 2013. In December 2019, Dataiku announced that CapitalG\\u2014the late-stage growth venture capital fund financed by Alphabet Inc.\\u2014joined Dataiku as an investor and that it had achieved unicorn status.\",\"ae\":null,\"b\":\"w\\tWikipedia\\ten.wikipedia.org\",\"c\":\"https://en.wikipedia.org/wiki/Dataiku\",\"d\":\"en.wikipedia.org/wiki/Dataiku\",\"da\":\"en_wikipedia_queries,nlp_fathead,nlp_wiki\",\"h\":0,\"i\":\"en.wikipedia.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku - Wikipedia\",\"u\":\"https://en.wikipedia.org/wiki/Dataiku\"},{\"a\":\"Dataiku is a fully managed online and installed platform that helps you build and deploy AI projects with data preparation, pipelines, AutoML, and automation. Start a 14-day free trial or download the free edition for up to 3 users and explore the features and benefits of Dataiku.\",\"ae\":null,\"c\":\"https://www.dataiku.com/product/get-started/\",\"d\":\"www.dataiku.com/product/get-started/\",\"da\":\"\",\"e\":\"2022-03-01T00:00:00.0000000\",\"h\":0,\"i\":\"www.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Get Started With Dataiku - Start an Online Trial or Download for Free\",\"u\":\"https://www.dataiku.com/product/get-started/\"},{\"a\":\"Dataiku Academy is a free online course that introduces the basics of Dataiku, a data analysis platform that allows you to create and explore data projects. You will learn how to create a project, a dataset, a connection, and a chart using Dataiku's interface and tools.\",\"ae\":null,\"c\":\"https://academy.dataiku.com/basics-101\",\"d\":\"academy.dataiku.com/basics-101\",\"da\":\"translations\",\"h\":0,\"i\":\"academy.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Basics 101 - Dataiku\",\"u\":\"https://academy.dataiku.com/basics-101\"},{\"a\":\"Dataiku Cloud is a fully managed service that lets you create AI and analytics insights from your data using modern cloud platforms and easy-to-use tools. Learn how to use Dataiku Cloud with built-in data connectors, AutoML, and online learning and support.\",\"ae\":null,\"c\":\"https://www.dataiku.com/product/dataiku-as-a-managed-service/\",\"d\":\"www.dataiku.com/product/dataiku-as-a-managed-service/\",\"da\":\"\",\"h\":0,\"i\":\"www.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku Cloud | Dataiku\",\"u\":\"https://www.dataiku.com/product/dataiku-as-a-managed-service/\"},{\"a\":\"About Dataiku# The following resources walk you through the main principles of the platform and how those core concepts can be applied to build an end-to-end solution. Concepts# Concept | The value proposition of Dataiku; Concept | Dataiku project walkthrough; Next.\",\"ae\":null,\"c\":\"https://knowledge.dataiku.com/latest/getting-started/about-dataiku/index.html\",\"d\":\"knowledge.dataiku.com/latest/getting-started/about-dataiku/index.html\",\"da\":\"\",\"h\":0,\"i\":\"knowledge.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"About Dataiku - Dataiku Knowledge Base\",\"u\":\"https://knowledge.dataiku.com/latest/getting-started/about-dataiku/index.html\"},{\"a\":\"Dataiku is a universal data, analytics, and AI platform that helps you detect and improve data quality challenges. Learn how to use Dataiku's discovery capabilities, data catalog, and data quality rules to deliver trusted data at speed across your organization.\",\"ae\":null,\"c\":\"https://discover.dataiku.com/data-quality/\",\"d\":\"discover.dataiku.com/data-quality/\",\"da\":\"\",\"h\":0,\"i\":\"discover.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Data Quality - Discover Dataiku\",\"u\":\"https://discover.dataiku.com/data-quality/\"},{\"a\":\"Dataiku 12 is a platform that connects data experts with generative AI models like OpenAI GPT and ChatGPT to create data projects. Learn how to use Dataiku 12 to do more with generative AI and data using a visual interface and natural language prompts.\",\"ae\":null,\"c\":\"https://discover.dataiku.com/dataiku-12/\",\"d\":\"discover.dataiku.com/dataiku-12/\",\"da\":\"\",\"h\":0,\"i\":\"discover.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku 12 - Discover Dataiku\",\"u\":\"https://discover.dataiku.com/dataiku-12/\"},{\"a\":\"Dataiku is the platform for Everyday AI, systemizing the use of data for exceptional business results. Organizations that use Dataiku elevate their people (whether technical and working in code or ...\",\"ae\":null,\"b\":\"li\\tLinkedIn\\twww.linkedin.com\",\"c\":\"https://www.linkedin.com/company/dataiku\",\"d\":\"www.linkedin.com/company/dataiku\",\"da\":\"\",\"h\":0,\"i\":\"www.linkedin.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku | LinkedIn\",\"u\":\"https://www.linkedin.com/company/dataiku\"},{\"a\":\"Dataiku is a platform that enables data experts and domain experts to work together to build AI into their daily operations. Learn about the key benefits and features of Dataiku, such as a visual lineage, governance, and collaboration, with this interactive data sheet.\",\"ae\":null,\"c\":\"https://pages.dataiku.com/interactive-data-sheet\",\"d\":\"pages.dataiku.com/interactive-data-sheet\",\"da\":\"\",\"h\":0,\"i\":\"pages.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku Interactive Data Sheet\",\"u\":\"https://pages.dataiku.com/interactive-data-sheet\"},{\"a\":\"Plugin development. Extend the native capabilities of Dataiku with custom-built components. This section contains tutorials which will help you learn how to use and combine programmatic features of Dataiku through step-by-step exercises. Developer tools Tooling and guidance to write code ...\",\"ae\":null,\"c\":\"https://developer.dataiku.com/latest/tutorials/index.html\",\"d\":\"developer.dataiku.com/latest/tutorials/index-html\",\"da\":\"\",\"h\":0,\"i\":\"developer.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Tutorials - Dataiku Developer Guide\",\"u\":\"https://developer.dataiku.com/latest/tutorials/index.html\"},{\"a\":\"With Dataiku's Prompt Studios. Prompt engineering is the key to developing robust interactions and reliable outputs from Generative AI services. With Dataiku's Prompt Studios, data scientists and engineers can design and operationalize high-performing, reusable prompts, complete with cost estimates across different LLM providers and models.\",\"ae\":null,\"c\":\"https://discover.dataiku.com/dataiku-for-generative-ai/\",\"d\":\"discover.dataiku.com/dataiku-for-generative-ai/\",\"da\":\"\",\"h\":0,\"i\":\"discover.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku for Generative AI - Discover Dataiku\",\"u\":\"https://discover.dataiku.com/dataiku-for-generative-ai/\"},{\"a\":\"Dataiku 12 includes new capabilities for data and IT teams to streamline MLOps and governance processes to deploy models faster, better manage production models, and improve model governance. A core principle of AI safety is keeping a human in the loop. Models don't always have the best or safest answer.\",\"ae\":null,\"c\":\"https://blog.dataiku.com/dataiku-12\",\"d\":\"blog.dataiku.com/dataiku-12\",\"da\":\"\",\"e\":\"2023-05-31T00:00:00.0000000\",\"h\":0,\"i\":\"blog.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Keep AI Under Control With Dataiku 12\",\"u\":\"https://blog.dataiku.com/dataiku-12\"},{\"a\":\"Dataiku is a platform for data science and machine learning, enabling data experts and domain experts to work together to build data into their daily operations. Read customer reviews, ratings, features, and alternatives of Dataiku from Gartner Peer Insights.\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\",\"d\":\"www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku Reviews, Ratings & Features 2024 | Gartner Peer Insights\",\"u\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\"},{\"a\":\"" Dataiku has greatly impacted my day-to-day work by streamlining and automating many of the data processing and analysis tasks that were previously time consuming and labor intensive. Overall, Dataiku has significantly increased the efficiency and effectiveness of an organization's data-driven decision-making processes.\",\"ae\":null,\"c\":\"https://blog.dataiku.com/why-users-love-dataiku\",\"d\":\"blog.dataiku.com/why-users-love-dataiku\",\"da\":\"\",\"e\":\"2023-02-22T00:00:00.0000000\",\"h\":0,\"i\":\"blog.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Why Users Love Dataiku: Stories From the Community\",\"u\":\"https://blog.dataiku.com/why-users-love-dataiku\"},{\"a\":\"Dataiku is the platform for Everyday AI, systemizing the use of data for exceptional business results. In the same way that computers or the internet have become embedded in the everyday activities of organizations, AI can help organizations transform processes and help make better and wiser decisions.\",\"ae\":null,\"c\":\"https://knowledge.dataiku.com/latest/getting-started/about-dataiku/concept-value-proposition.html\",\"d\":\"knowledge.dataiku.com/latest/getting-started/about-dataiku/concept-value-proposition.html\",\"da\":\"\",\"h\":0,\"i\":\"knowledge.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Concept | The value proposition of Dataiku\",\"u\":\"https://knowledge.dataiku.com/latest/getting-started/about-dataiku/concept-value-proposition.html\"},{\"a\":\"Dataiku. @dataiku. Dataiku is the only AI platform that connects data and doers, enabling anyone across organizations to transform business data into real business impact. Software Company New York, NY dataiku.com Joined September 2012. 690 Following.\",\"ae\":null,\"b\":\"@\\tTwitter User Page\\ttwitter.com\",\"c\":\"https://twitter.com/dataiku\",\"d\":\"twitter.com/dataiku\",\"da\":\"\",\"h\":0,\"i\":\"twitter.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku (@dataiku) | Twitter\",\"u\":\"https://twitter.com/dataiku\"},{\"a\":\"Persistent Systems. 1,142,095 followers. 2mo. We're delighted to share that we continued our growth momentum as we reported $291.71M in revenue in Q2 FY24, delivering 14.1% year-over-year revenue growth. Our focus on client-centricity has enabled us to register the highest-ever TCV with more than $475M in the current quarter.\",\"ae\":null,\"b\":\"li\\tLinkedIn\\twww.linkedin.com\",\"c\":\"https://in.linkedin.com/company/persistent-systems\",\"d\":\"in.linkedin.com/company/persistent-systems\",\"da\":\"\",\"h\":0,\"i\":\"in.linkedin.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Persistent Systems | LinkedIn\",\"u\":\"https://in.linkedin.com/company/persistent-systems\"},{\"a\":\"Dataiku\\u306f\\u3001\\u30ad\\u30fc\\u30a6\\u30a9\\u30fc\\u30ab\\u30fc\\u69d8\\u3068\\u30b3\\u30f3\\u30b5\\u30eb\\u30c6\\u30a3\\u30f3\\u30b0\\u30d1\\u30fc\\u30c8\\u30ca\\u30fc\\u5951\\u7d04\\u3092\\u7de0\\u7d50\\u3057\\u307e\\u3057\\u305f\\u3002\\u30ad\\u30fc\\u30a6\\u30a9\\u30fc\\u30ab\\u30fc\\u69d8\\u306fDataiku\\u306e\\u6d3b\\u7528\\u3092\\u901a\\u3058\\u3066\\u304a\\u5ba2\\u69d8\\u306e\\u30c7\\u30fc\\u30bf\\u6d3b\\u7528\\u652f\\u63f4\\u3084\\u5185\\u88fd\\u5316\\u652f\\u63f4\\u3092\\u884c\\u3044\\u3001\\u30b5\\u30a4\\u30ed\\u5316\\u3055\\u308c\\u305f\\u30b7\\u30b9\\u30c6\\u30e0\\u304b\\u3089\\u306e\\u8131\\u5374\\u3084\\u30c7\\u30b8\\u30bf\\u30eb\\u4eba\\u6750\\u306e\\u78ba\\u4fdd\\u3068\\u3044\\u3063\\u305f\\u8ab2\\u984c\\u306b\\u5bfe\\u5fdc\\u3057\\u307e\\u3059\\u3002\",\"ae\":null,\"b\":\"li\\tLinkedIn\\twww.linkedin.com\",\"c\":\"https://jp.linkedin.com/in/tadashi-mishima-32638445\",\"d\":\"jp.linkedin.com/in/tadashi-mishima-32638445\",\"da\":\"\",\"h\":0,\"i\":\"jp.linkedin.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Tadashi Mishima - Growth Sales Specialist - UiPath Japan | LinkedIn\",\"u\":\"https://jp.linkedin.com/in/tadashi-mishima-32638445\"},{\"a\":\"Snowflake, DBT and Dataiku Support. Open Posted 10 minutes ago \\u2022 Ends in 6 days. $10-30 USD. Paid on delivery. Project Title: Snowflake, DBT, Dataiku project Support - Urgent. I am in need of a data engineer freelancer who can provide urgent support for the project. The ideal candidate should have experience and expertise in working with ...\",\"ae\":null,\"c\":\"https://www.freelancer.com/projects/database-administration/snowflake-dbt-dataiku-support\",\"d\":\"www.freelancer.com/projects/database-administration/snowflake-dbt-dataiku-support\",\"da\":\"\",\"e\":\"2024-01-14T00:00:00.0000000\",\"h\":0,\"i\":\"www.freelancer.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Snowflake, DBT and Dataiku Support | Freelancer\",\"u\":\"https://www.freelancer.com/projects/database-administration/snowflake-dbt-dataiku-support\"},{\"a\":\"Dataiku\\u30bb\\u30df\\u30ca\\u30fc\\u300c\\u30c7\\u30fc\\u30bf\\u99c6\\u52d5\\u578b\\u30d3\\u30b8\\u30cd\\u30b9\\u306e\\u8ab2\\u984c\\u3068\\u89e3\\u6c7a\\u6cd5\\u300d\\u3092\\u5f53\\u793e\\u4e3b\\u50ac\\u3067\\u958b\\u50ac\\u3044\\u305f\\u3057\\u307e\\u3059\\u3002 \\u696d\\u52d9\\u5909\\u9769\\u306e\\u63a8\\u9032\\u3092\\u76ee\\u7684\\u3068\\u3057\\u305f\\u3001\\u30c7\\u30fc\\u30bf\\u306e\\u96c6\\u7d04\\u30fb\\u7ba1\\u7406\\u30fb\\u904b\\u7528\\u30fb\\u6d3b\\u7528\\u30d7\\u30ed\\u30bb\\u30b9\\u306e\\u5b9a\\u7740\\u3092\\u3069\\u3046\\u5b9f\\u73fe\\u3059\\u308b\\u304b\\u306f\\u3001\\u30c7\\u30fc\\u30bf\\u30c9\\u30ea\\u30d6\\u30f3\\u7d4c\\u55b6\\u306e\\u5b9f\\u73fe\\u306b\\u304a\\u3051\\u308b\\u3001\\u3088\\u304f\\u3042\\u308b\\u8ab2\\u984c\\u306e1\\u3064\\u3067\\u3059\\u3002\",\"ae\":null,\"c\":\"https://www.intellilink.co.jp/topics/seminar_event/2024/dataiku-fy2023-2h.aspx\",\"d\":\"www.intellilink.co.jp/topics/seminar_event/2024/dataiku-fy2023-2h.aspx\",\"da\":\"translations\",\"e\":\"2024-01-12T00:00:00.0000000\",\"h\":0,\"i\":\"www.intellilink.co.jp\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"\\u5f53\\u793e\\u4e3b\\u50ac\\u30bb\\u30df\\u30ca\\u30fc\\u300c\\u30c7\\u30fc\\u30bf\\u99c6\\u52d5\\u578b\\u30d3\\u30b8\\u30cd\\u30b9\\u306e\\u8ab2\\u984c\\u3068\\u89e3\\u6c7a\\u6cd5\\u300d\\u3092\\u958b\\u50ac | Ntt\\u30c7\\u30fc\\u30bf\\u5148\\u7aef\\u6280\\u8853\\u682a\\u5f0f\\u4f1a\\u793e\",\"u\":\"https://www.intellilink.co.jp/topics/seminar_event/2024/dataiku-fy2023-2h.aspx\"},{\"n\":\"/d.js?q=dataiku&kl=wt-wt&l=wt-wt&p=&s=21&ex=-1&ct=US&sp=0&vqd=4-337400409169293617055811118659485228425\"}]);DDG.duckbar.load('images');DDG.duckbar.load('news');DDG.duckbar.load('videos', {\"ads\":[],\"query\":\"dataiku\",\"queryEncoded\":\"dataiku\",\"response_type\":\"places\",\"results\":[{\"content\":\"https://www.youtube.com/watch?v=Mmt7IluxE0M\",\"description\":\"Learn more about Dataiku and how to better use your enterprise data in this 3 minute demo. CHECK OUT DATAIKU: https://bit.ly/36XBlpK BRIGHTTALK WEBINARS: htt...\",\"duration\":\"3:35\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/Mmt7IluxE0M?autoplay=1\",\"image_token\":\"9fbd7f08d3fe9c5ae80966f30b030c5de63ce962d42298ce9455edc487f55f54\",\"images\":{\"large\":\"https://tse3.mm.bing.net/th?id=OVP.TMea5u6ptVU_48mCeCUUlQEsDh&pid=Api\",\"medium\":\"https://tse3.mm.bing.net/th?id=OVP.TMea5u6ptVU_48mCeCUUlQEsDh&pid=Api\",\"motion\":\"https://tse3.mm.bing.net/th?id=OM.2qQ9AZ4EgLzxPA_1699065185&pid=Api\",\"small\":\"https://tse3.mm.bing.net/th?id=OVP.TMea5u6ptVU_48mCeCUUlQEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2021-09-23T18:53:57.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":45758},\"title\":\"Dataiku 3-Minute Demo\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=ryZRRIjQ5Z8\",\"description\":\"If you're a code-first data practitioner, Dataiku helps you efficiently build high quality data pipelines and models in a number of ways. CHECK OUT DATAIKU: https://bit.ly/36XBlpK EGG ON AIR: https://bit.ly/37GhXMY BRIGHTTALK WEBINARS: https://bit.ly/33TIRjn DATA SCIENCE PIONEERS DOCUMENTARY: https://bit.ly/36V3rBF PARTNER ECOSYSTEM: https ...\",\"duration\":\"10:43\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/ryZRRIjQ5Z8?autoplay=1\",\"image_token\":\"8a4abca8613c6680a108591849e5d7b13b86111004ae004898a7f059b64c8355\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.WoendyuZJ9qxql-n6jit5AEsDh&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.WoendyuZJ9qxql-n6jit5AEsDh&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM1.cmvppfhHVUeE4Q_1684256861&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.WoendyuZJ9qxql-n6jit5AEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2021-06-08T21:15:02.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":12391},\"title\":\"Dataiku Demo for Data Scientists and Coders\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=1IgcAAPW4fQ\",\"description\":\"Dataiku 11 is now out! This release is jam-packed with features designed to help organizations deliver on the promise of Everyday AI. Check out this video to get an introduction to V11. CHECK OUT DATAIKU: https://bit.ly/36XBlpK DATAIKU ACADEMY: https://bit.ly/2LjsEgZ DATAIKU COMMUNITY: https://bit.ly/2K8lOtV DATA SCIENCE AND ANALYTICS MEETUPS ...\",\"duration\":\"30:52\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/1IgcAAPW4fQ?autoplay=1\",\"image_token\":\"885849fd3f3285ae15a77b9c7e40acc1fbe9d37fa39ac789ecf88e4b889aa796\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.mQkABdeGdBHH8E6VyTt64AEsDh&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.mQkABdeGdBHH8E6VyTt64AEsDh&pid=Api\",\"motion\":\"https://tse1.mm.bing.net/th?id=OM1.mCQeogW3-u_iVw_1684181286&pid=Api\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.mQkABdeGdBHH8E6VyTt64AEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2022-07-15T15:35:31.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":3314},\"title\":\"Introduction to Dataiku 11!\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=FluiuHuaU8A\",\"description\":\"In this breakout session of Dataiku's Product Days 2021, you will see a demo of Dataiku's Data Science Studio, the centralized, collaborative, and end-to-end platform for data science in the enterprise. CHECK OUT DATAIKU: https://bit.ly/36XBlpK EGG ON AIR: https://bit.ly/37GhXMY BRIGHTTALK WEBINARS: https://bit.ly/33TIRjn DATA SCIENCE PIONEERS ...\",\"duration\":\"13:50\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/FluiuHuaU8A?autoplay=1\",\"image_token\":\"2943fa8c1580f2936fc11667d670c0b827b94ff3d16b897f8b5ef2e2426487b3\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.RIM-ftwDZjYP58RimJfgwwEsDh&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.RIM-ftwDZjYP58RimJfgwwEsDh&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM1.MIQ7BoQz1MVkNw_1662248868&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.RIM-ftwDZjYP58RimJfgwwEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2021-07-08T15:56:22.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":3844},\"title\":\"Introduction to Dataiku Data Science | Product Days 2021\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=gp8QeJJ4KuE\",\"description\":\"This tutorial is to quickly help users become familiar with the Dataiku platform (DSS). Links for setting up the tutorial. Step 1: https://www.dataiku.com/ Step 2: https://www.dataiku.com/product/get-started/virtualbox/ Step 3: http://127.0.0.1:10000/ Step 4: https://github.com/ageron/handson-ml Step 5: https://raw.githubusercontent.com/ageron ...\",\"duration\":\"10:24\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/gp8QeJJ4KuE?autoplay=1\",\"image_token\":\"36a6e666bdcb9e34aacad09f504181152667f35deab62b50ee48da1a76c38303\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.htgX0HRO9l8nlfoFzmlA5AHgFo&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.htgX0HRO9l8nlfoFzmlA5AHgFo&pid=Api\",\"motion\":\"https://tse1.mm.bing.net/th?id=OM2.SsfUJx35-DP9OA_1632775689&pid=Api\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.htgX0HRO9l8nlfoFzmlA5AHgFo&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2020-06-09T17:48:44.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":37512},\"title\":\"Get started with Dataiku | From data to machine learning predictions in 10 minutes\",\"uploader\":\"Jose RazGuzman\"},{\"content\":\"https://www.youtube.com/watch?v=S6AY-q_5Bd0\",\"description\":\"Learn more about Dataiku's demand forecast solution to optimize your sorting and production planning, inventory management, and much more. Without you, it's just data. Learn more at https://www.dataiku.com/without-you/ CHECK OUT DATAIKU: https://bit.ly/36XBlpK BRIGHTTALK WEBINARS: https://bit.ly/33TIRjn DATA SCIENCE PIONEERS DOCUMENTARY: https ...\",\"duration\":\"2:00\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/S6AY-q_5Bd0?autoplay=1\",\"image_token\":\"456216e1949ad91527408a297243af22822d03602cc51e3fb1c7324680e27e90\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.B1QN6Sk8tATAQDmEZgvp8wEsDh&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.B1QN6Sk8tATAQDmEZgvp8wEsDh&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM2.BiTArkALFRqLyQ_1684244069&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.B1QN6Sk8tATAQDmEZgvp8wEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2022-08-09T20:43:58.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":569},\"title\":\"Improve Your Demand Forecasting with Dataiku\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=tyd262JRo9g\",\"description\":\"In this session from Everyday AI Tech Day 2023, hear from Jacqueline Kuo, one of our solutions engineers, on how to build sustainable pipelines. Optimizing and automating data pipelines to transform, prepare, and analyze data on an ongoing basis is critical for production-ready AI projects. In this session, learn how Dataiku supports the ...\",\"duration\":\"20:35\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/tyd262JRo9g?autoplay=1\",\"image_token\":\"e946d16ff6600b2df00b4cddf4f97fa56d41df90c0a1608bcd33fedf69af63bd\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.xmckza2EYvyQk4nTqTsfZgEsDh&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.xmckza2EYvyQk4nTqTsfZgEsDh&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM1.VfASmCqEmyb4NA_1700289203&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.xmckza2EYvyQk4nTqTsfZgEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-10-20T12:35:12.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":98},\"title\":\"A Well-Oiled Machine: Create Sustainable Data Pipelines With Dataiku\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=-amc9iVauuE\",\"description\":\"Dataiku is the leading platform for Everyday AI, systemizing the use of data for exceptional business results. In today's video we will take a tour of Dataiku's end to end capabilities by exploring a real life use case around environmental impact. Let's take a look at how a data science team with different skills can work together to turn ...\",\"duration\":\"12:35\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/-amc9iVauuE?autoplay=1\",\"image_token\":\"2a05a65ad8a2727aa5c48b8daa7f9ec363a24d4336a3509016d4b200c9d003cd\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.Az9RhdSVwpXe56mGcs6FqQEsDh&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.Az9RhdSVwpXe56mGcs6FqQEsDh&pid=Api\",\"motion\":\"https://tse1.mm.bing.net/th?id=OM1.Q2OhN9DzfowU6A_1685345657&pid=Api\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.Az9RhdSVwpXe56mGcs6FqQEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-01-09T21:12:27.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":9768},\"title\":\"End to End Demo 2023\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=MxKNdVNyLJY\",\"description\":\"Simply collecting vast amounts of data isn't enough to unlock its potentially massive value to your business. In this video, we will explore Dataiku's data preparation capabilities that will help you access, cleanse, transform, and enrich data faster than ever before. Timestamps: 0:00 Introduction 0:53 The Flow 1:18 Accessing and Exploring ...\",\"duration\":\"6:12\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/MxKNdVNyLJY?autoplay=1\",\"image_token\":\"652157f0560bd0c12f1731a0c4876335e712bb986dda679c0157545e9083ab50\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.xh9SlNNNrKuJLXO5kEtsLgEsDh&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.xh9SlNNNrKuJLXO5kEtsLgEsDh&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM2.u85J8gWHLhZhSA_1680067810&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.xh9SlNNNrKuJLXO5kEtsLgEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-01-09T20:46:27.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":2948},\"title\":\"Key Capabilities: Data Preparation\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=GJA_PAnqGY8\",\"description\":\"In this video we walk through a series of real-world data analysis tasks using a Netflix movie & TV show dataset. We start by solving the tasks using the Python Pandas library. We then complete the same problems using the Dataiku Data Science Studio. Being knowledgeable about various tools in the data science space is very important to becoming ...\",\"duration\":\"58:15\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/GJA_PAnqGY8?autoplay=1\",\"image_token\":\"e00b743925487c5466b2bf1a024869f528876917c05bdd1e7cce1d78ad3d9a3a\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.D7OGs04gyoaehil3qvxX7gEsDh&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.D7OGs04gyoaehil3qvxX7gEsDh&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM1.3R2zQEuONEzSww_1664997993&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.D7OGs04gyoaehil3qvxX7gEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2022-08-03T15:00:11.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":7769},\"title\":\"Solving Real-World Data Analysis Tasks with Python Pandas & Dataiku DSS (Movie Analysis)\",\"uploader\":\"Recall by Dataiku\"}],\"vqd\":{\"dataiku\":\"4-337400409169293617055811118659485228425\"}});DDG.duckbar.loadModule('related_searches', {\"ads\":[],\"query\":\"dataiku\",\"queryEncoded\":\"dataiku\",\"response_type\":\"places\",\"results\":[{\"display_text\":\"dataiku login\",\"text\":\"dataiku login\",\"web_search_url\":\"?q=dataiku%20login\"},{\"display_text\":\"dataiku japan\",\"text\":\"dataiku japan\",\"web_search_url\":\"?q=dataiku%20japan\"},{\"display_text\":\"dataiku vs tableau\",\"text\":\"dataiku vs tableau\",\"web_search_url\":\"?q=dataiku%20vs%20tableau\"},{\"display_text\":\"dataiku vs alteryx\",\"text\":\"dataiku vs alteryx\",\"web_search_url\":\"?q=dataiku%20vs%20alteryx\"},{\"display_text\":\"dataiku vs databricks\",\"text\":\"dataiku vs databricks\",\"web_search_url\":\"?q=dataiku%20vs%20databricks\"},{\"display_text\":\"what is dataiku used for\",\"text\":\"what is dataiku used for\",\"web_search_url\":\"?q=what%20is%20dataiku%20used%20for\"},{\"display_text\":\"how to pronounce dataiku\",\"text\":\"how to pronounce dataiku\",\"web_search_url\":\"?q=how%20to%20pronounce%20dataiku\"},{\"display_text\":\"dataiku products\",\"text\":\"dataiku products\",\"web_search_url\":\"?q=dataiku%20products\"}],\"vqd\":{\"dataiku\":\"4-337400409169293617055811118659485228425\"}});if (DDG.pageLayout) DDG.pageLayout.initialize({\"mainline\":{\"items\":[[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"videos\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"related_searches\"]]},\"sidebar\":{\"items\":[[\"wikipedia_fathead\"]]}}, { start: 0 });DDG.deep.emit(\"load:completed\");", + "curl-cffi-POST-https://duckduckgo.com-{\"data\": {\"q\": \"Dataiku machine learning platform\"}}": "Dataiku machine learning platform at DuckDuckGo
", + "curl-cffi-GET-https://links.duckduckgo.com/d.js-{\"params\": {\"bing_market\": \"wt-WT\", \"df\": null, \"ex\": \"-1\", \"kl\": \"wt-wt\", \"l\": \"wt-wt\", \"q\": \"Dataiku machine learning platform\", \"s\": \"0\", \"sp\": \"0\", \"vqd\": \"4-135627661863888098952136153695171249901\"}}": "if (DDG.deep && DDG.deep.setUpstream) DDG.deep.setUpstream(\"bingv7aa\");DDG.deep.bn={'ivc':1};if (DDG.pageLayout) DDG.pageLayout.load('a',[], {\"page_load_url\":\"https://duckduckgo.com/y.js?iurl=%7B2%7DIG%3DD926DA28CBA14E6D9DA10C17531E1D6B%26CID%3D37369241D5576E2736ED8647D4286F5F%26Type%3DEvent.CPT%26DATA%3D0\"});DDG.deep.signalSummary = \"\";DDG.inject('DDG.Data.languages.resultLanguages', {\"en\":[\"https://www.dataiku.com/\",\"https://www.dataiku.com/product/key-capabilities/machine-learning/\",\"https://www.dataiku.com/product/key-capabilities/mlops/\",\"https://www.dataiku.com/product/key-capabilities/\",\"https://developer.dataiku.com/latest/tutorials/machine-learning/index.html\",\"https://knowledge.dataiku.com/latest/ml-analytics/index.html\",\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\",\"https://www.dataiku.com/product/dataiku-as-a-managed-service/\",\"https://pages.dataiku.com/dataiku-enterprise-ai-info\",\"https://blog.dataiku.com/dataiku-ml-key-capabilities\",\"https://discover.dataiku.com/data-scientists/\",\"https://academy.dataiku.com/\",\"https://academy.dataiku.com/machine-learning-basics\",\"https://www.infoworld.com/article/3618837/dataiku-review-data-science-fit-for-the-enterprise.html\",\"https://pages.dataiku.com/gartner-2021-pr\",\"https://blog.dataiku.com/what-is-machine-learning-model-deployment\",\"https://datascientest.com/en/dataiku-a-must-have-tool-for-data-science-and-ai\",\"https://blog.dataiku.com/gartner-2020\",\"https://www.infoq.com/news/2024/01/instacart-machine-learning/\",\"https://seekingalpha.com/article/4662201-c3ai-missing-the-boat\",\"https://jobs.apple.com/en-us/details/200516237/aiml-software-engineer-machine-learning-platform-infrastructure\",\"https://www.tokyodev.com/companies/rapyuta-robotics\",\"https://www.servicenow.com/partners/partner-finder/ntt-data-corp.html\",\"https://www.linkedin.com/company/maruha-nichiro-corporation\",\"https://www.gatech.edu/event/2024/01/12/access-big-data-machine-learning-workshop\",\"https://apply.workable.com/rapyuta-robotics/j/3ADFC72B04/\"]});DDG.deep.pageLayoutSummary = \"w26r1,e1\";DDG.inject('DDG.Data.languages.adLanguages', {});if (DDG.pageLayout) DDG.pageLayout.load('d',[{\"a\":\"MLOps Deploy, monitor, and maintain machine learning models, all in a single platform. Explore the Capability Collaboration With Dataiku, teams can move beyond the lab and build real and safe Generative AI applications at enterprise scale. Explore the Capability Governance\",\"ae\":null,\"c\":\"https://www.dataiku.com/\",\"d\":\"www.dataiku.com\",\"da\":\"\",\"h\":0,\"i\":\"www.dataiku.com\",\"k\":null,\"l\":[{\"snippet\":\"The Platform for Everyday AI. Empower people across your business to do more with data and AI, build projects faster, and work together, all in a shared and safe environment. With Dataiku, everyone can get involved in data and AI projects on a single platform for design and production that delivers use cases in days, not months.\",\"targetUrl\":\"https://www.dataiku.com/product/\",\"text\":\"Product\"},{\"snippet\":\"Check out Dataiku's job openings and apply to help companies transform raw data into business impacting predictions and products.\",\"targetUrl\":\"https://www.dataiku.com/careers/\",\"text\":\"Careers\"},{\"snippet\":\"A Single Platform For. Generative AI; Data Preparation; Visualization; Machine Learning ... Get started with the basics, quickly move on to advanced courses, and become a certified user on Dataiku's online learning and certification platform. Master Dataiku ... Learn how Dataiku makes it easy to build machine learning models, deploy them to a ...\",\"targetUrl\":\"https://www.dataiku.com/learn/\",\"text\":\"Learn\"},{\"snippet\":\"Thrive SPC Uses Dataiku, Snowflake, and Snow Fox Data to Improve Clinical Home Care. By moving to Dataiku and working with Dataiku partners, Snowflake and Snow Fox Data, Thrive Skilled Pediatric Care (Thrive SPC) has been able to advance from complicated spreadsheets to a central platform that provides clear insights and metrics to fuel their data-driven healthcare solutions.\",\"targetUrl\":\"https://www.dataiku.com/stories/\",\"text\":\"Stories\"},{\"snippet\":\"Dataiku was founded on the principle that in order to succeed in the world's rapidly evolving ecosystem, companies \\u2014 no matter what their industry or size \\u2014 must elevate their people to continuously innovate. Since 2013, Dataiku has been the leader in democratizing data and empowering organization-wide collaboration.\",\"targetUrl\":\"https://www.dataiku.com/company/\",\"text\":\"Company\"},{\"snippet\":\"Join the Dataiku Partner Ecosystem. Become a part of the growing Dataiku service partner ecosystem or get in touch to talk integrations and technical partnerships.\",\"targetUrl\":\"https://www.dataiku.com/partners/\",\"text\":\"Partners\"}],\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku | Everyday AI, Extraordinary People\",\"u\":\"https://www.dataiku.com/\"},{\"a\":\"AI and Machine Learning with Dataiku Build and evaluate advanced machine learning models using AutoML and the latest AI techniques. See Dataiku ML in Action START FOR FREE Visualization DataOps Feature Engineering\",\"ae\":null,\"c\":\"https://www.dataiku.com/product/key-capabilities/machine-learning/\",\"d\":\"www.dataiku.com/product/key-capabilities/machine-learning/\",\"da\":\"\",\"h\":0,\"i\":\"www.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"AI and Machine Learning with Dataiku | Dataiku\",\"u\":\"https://www.dataiku.com/product/key-capabilities/machine-learning/\"},{\"a\":\"Product Dataiku Key Capabilities MLOps with Dataiku MLOps with Dataiku Deploy, monitor, and manage machine learning models and projects in production. See MLOps in Action START FOR FREE DataOps Analytic Apps Deploying Projects to Production\",\"ae\":null,\"c\":\"https://www.dataiku.com/product/key-capabilities/mlops/\",\"d\":\"www.dataiku.com/product/key-capabilities/mlops/\",\"da\":\"\",\"h\":0,\"i\":\"www.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MLOps with Dataiku | Dataiku\",\"u\":\"https://www.dataiku.com/product/key-capabilities/mlops/\"},{\"a\":\"AI & Machine Learning Dataiku AutoML accelerates the model development process with a guided framework for AI and machine learning including prompt engineering, prediction, clustering, time series forecasting, computer vision tasks, causal ML, and more.\",\"ae\":null,\"c\":\"https://www.dataiku.com/product/key-capabilities/\",\"d\":\"www.dataiku.com/product/key-capabilities/\",\"da\":\"\",\"h\":0,\"i\":\"www.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku Key Capabilities | Dataiku\",\"u\":\"https://www.dataiku.com/product/key-capabilities/\"},{\"a\":\"This tutorial section contains learning material on programmatically training, managing and deploying machine learning models in Dataiku. Generative AI - NLP Programmatic RAG with Dataiku's LLM Mesh and Langchain Using LLM Mesh to benchmark zero-shot classification models GPT-based zero-shot text classification with the OpenAI API\",\"ae\":null,\"c\":\"https://developer.dataiku.com/latest/tutorials/machine-learning/index.html\",\"d\":\"developer.dataiku.com/latest/tutorials/machine-learning/index.html\",\"da\":\"\",\"h\":0,\"i\":\"developer.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Machine Learning - Dataiku Developer Guide\",\"u\":\"https://developer.dataiku.com/latest/tutorials/machine-learning/index.html\"},{\"a\":\"Dataiku supports a wide range of machine learning and analytic tasks, such as prediction, clustering, time series, image classification and much more. Explore the resources here for improving your building machine learning models and analytics tasks. Tip\",\"ae\":null,\"c\":\"https://knowledge.dataiku.com/latest/ml-analytics/index.html\",\"d\":\"knowledge.dataiku.com/latest/ml-analytics/index.html\",\"da\":\"\",\"h\":0,\"i\":\"knowledge.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Machine Learning & Analytics - Dataiku Knowledge Base\",\"u\":\"https://knowledge.dataiku.com/latest/ml-analytics/index.html\"},{\"a\":\"by Dataiku in Data Science and Machine Learning Platforms 4.8 504 Ratings compare_arrows Compare rate_review Write a Review download_2 Download PDF Related markets: Dataiku in Data Preparation Tools (18 Reviews), Dataiku in Cloud AI Developer Services (14 Reviews) Overview Reviews Alternatives Likes and Dislikes Dataiku Ratings Overview\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\",\"d\":\"www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku Reviews, Ratings & Features 2024 | Gartner Peer Insights\",\"u\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\"},{\"a\":\"The fully managed data science and machine learning platform for your team to create AI and analytics insights. "Dataiku Cloud allows us to focus on analysis, not server administration. Data insights fuel our growth, and Dataiku Cloud enables us to develop insights faster than our competitors." Scott Walker, Managing Partner Sarissa Partners\",\"ae\":null,\"c\":\"https://www.dataiku.com/product/dataiku-as-a-managed-service/\",\"d\":\"www.dataiku.com/product/dataiku-as-a-managed-service/\",\"da\":\"\",\"h\":0,\"i\":\"www.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku Cloud | Dataiku\",\"u\":\"https://www.dataiku.com/product/dataiku-as-a-managed-service/\"},{\"a\":\"Dataiku is the end-to-end platform democratizing access to data. Manage the entire data science workflow from data prep to auto ML to model maintenance. ... Dataiku offers the latest machine learning technologies all in one place, including: Automated machine learning (AutoML) - choose between several ML backends to train models. ...\",\"ae\":null,\"c\":\"https://pages.dataiku.com/dataiku-enterprise-ai-info\",\"d\":\"pages.dataiku.com/dataiku-enterprise-ai-info\",\"da\":\"\",\"h\":0,\"i\":\"pages.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku: Your Path to Enterprise AI\",\"u\":\"https://pages.dataiku.com/dataiku-enterprise-ai-info\"},{\"a\":\"Dataiku Makes Machine Learning Customizable, Accessible, & Transparent May 17, 2023 Dataiku Product Lauren Anderson It only takes a quick look around to see that the use of machine learning (ML) is more prevalent across industries than ever before!\",\"ae\":null,\"c\":\"https://blog.dataiku.com/dataiku-ml-key-capabilities\",\"d\":\"blog.dataiku.com/dataiku-ml-key-capabilities\",\"da\":\"\",\"e\":\"2023-05-17T00:00:00.0000000\",\"h\":0,\"i\":\"blog.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku Makes Machine Learning Customizable, Accessible, & Transparent\",\"u\":\"https://blog.dataiku.com/dataiku-ml-key-capabilities\"},{\"a\":\"Jump Right In Dataiku is an end-to-end data and machine learning platform. Build and maintain predictive models throughout their entire lifecycles while pushing computation to the most efficient engines.\",\"ae\":null,\"c\":\"https://discover.dataiku.com/data-scientists/\",\"d\":\"discover.dataiku.com/data-scientists/\",\"da\":\"\",\"h\":0,\"i\":\"discover.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Data Scientists - Discover Dataiku\",\"u\":\"https://discover.dataiku.com/data-scientists/\"},{\"a\":\"Academy Your Path to Dataiku Mastery Quick Starts Follow our quick starts that introduce using Dataiku for different tasks View More Learning Paths From novice to expert, follow guided sets of curriculums to master Dataiku View More Certifications Test your Dataiku knowledge in key thematic areas View More Crash Course\",\"ae\":null,\"c\":\"https://academy.dataiku.com/\",\"d\":\"academy.dataiku.com\",\"da\":\"\",\"h\":0,\"i\":\"academy.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku Academy\",\"u\":\"https://academy.dataiku.com/\"},{\"a\":\"The Machine Learning Course is designed to provide a first hands-on overview of basic Dataiku DSS machine learning concepts so that you can easily create and evaluate your first models in DSS. Completion of this course will enable you to move on to more advanced courses. In this course, we'll work with two use cases.\",\"ae\":null,\"c\":\"https://academy.dataiku.com/machine-learning-basics\",\"d\":\"academy.dataiku.com/machine-learning-basics\",\"da\":\"\",\"h\":0,\"i\":\"academy.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Machine Learning Basics - Dataiku\",\"u\":\"https://academy.dataiku.com/machine-learning-basics\"},{\"a\":\"Dataiku Data Science Studio (DSS) is a platform that tries to span the needs of data scientists, data engineers, business analysts, and AI consumers. It mostly succeeds. In addition, Dataiku...\",\"ae\":null,\"c\":\"https://www.infoworld.com/article/3618837/dataiku-review-data-science-fit-for-the-enterprise.html\",\"d\":\"www.infoworld.com/article/3618837/dataiku-review-data-science-fit-for-the-enterprise.html\",\"da\":\"\",\"h\":0,\"i\":\"www.infoworld.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku review: Data science fit for the enterprise | InfoWorld\",\"u\":\"https://www.infoworld.com/article/3618837/dataiku-review-data-science-fit-for-the-enterprise.html\"},{\"a\":\"NEW YORK - March 4, 2021 - Today Dataiku, the world's most advanced Enterprise AI platform, was named a Leader in the Gartner 2021 Magic Quadrant for Data Science and Machine-Learning Platforms, marking its second consecutive year in the Leaders quadrant.Dataiku believes the placement amid the fast-moving market for AI tools cements its position as the driving force behind breakthroughs in ...\",\"ae\":null,\"c\":\"https://pages.dataiku.com/gartner-2021-pr\",\"d\":\"pages.dataiku.com/gartner-2021-pr\",\"da\":\"translations\",\"h\":0,\"i\":\"pages.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku Again Named a Leader in the Gartner 2021 Magic Quadrant for ...\",\"u\":\"https://pages.dataiku.com/gartner-2021-pr\"},{\"a\":\"An ML model is considered in production once it's been successfully deployed and being used by end users to realize business value. This article will shed more light on what exactly model deployment means and how Dataiku's end-to-end platform makes the model deployment process seamless. Why Is Model Deployment So Important (and So Hard)?\",\"ae\":null,\"c\":\"https://blog.dataiku.com/what-is-machine-learning-model-deployment\",\"d\":\"blog.dataiku.com/what-is-machine-learning-model-deployment\",\"da\":\"\",\"e\":\"2023-04-10T00:00:00.0000000\",\"h\":0,\"i\":\"blog.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"What Is Machine Learning Model Deployment? - Dataiku\",\"u\":\"https://blog.dataiku.com/what-is-machine-learning-model-deployment\"},{\"a\":\"A visual interface makes it very easy to apply Machine Learning models. Additionally, the platform-as-a-service approach eliminates the need for infrastructure. Furthermore, Dataiku is also compatible with Bayesian search. This allows running a second AI model in a loop to test different settings and parameters until the optimal configuration ...\",\"ae\":null,\"c\":\"https://datascientest.com/en/dataiku-a-must-have-tool-for-data-science-and-ai\",\"d\":\"datascientest.com/en/dataiku-a-must-have-tool-for-data-science-and-ai\",\"da\":\"\",\"e\":\"2023-11-28T00:00:00.0000000\",\"h\":0,\"i\":\"datascientest.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku: A must-have tool for Data Science and AI\",\"u\":\"https://datascientest.com/en/dataiku-a-must-have-tool-for-data-science-and-ai\"},{\"a\":\"Dataiku: A Gartner Magic Quadrant Leader in Data Science and Machine-Learning Platforms February 17, 2020 Dataiku Company, Dataiku Product Lynn Heidmann Our 2019 ended with a bang with the announcement that Dataiku became a unicorn valued at $1.4 billion and gained a new investor (CapitalG).\",\"ae\":null,\"c\":\"https://blog.dataiku.com/gartner-2020\",\"d\":\"blog.dataiku.com/gartner-2020\",\"da\":\"translations\",\"h\":0,\"i\":\"blog.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku: A Gartner Magic Quadrant Leader in Data Science and Machine ...\",\"u\":\"https://blog.dataiku.com/gartner-2020\"},{\"a\":\"Instacart introduced its original Griffin platform in 2022 to support its journey toward leveraging machine learning for product development. Using a unified platform helped triple the number of ...\",\"ae\":null,\"c\":\"https://www.infoq.com/news/2024/01/instacart-machine-learning/\",\"d\":\"www.infoq.com/news/2024/01/instacart-machine-learning/\",\"da\":\"translations\",\"e\":\"2024-01-01T08:02:59.0000000\",\"h\":0,\"i\":\"www.infoq.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Griffin 2.0: Instacart Revamps Its Machine Learning Platform - InfoQ\",\"u\":\"https://www.infoq.com/news/2024/01/instacart-machine-learning/\"},{\"a\":\"Their core product is Data Science Studio, which is focused on cross-discipline collaboration and ease of use and enables users to start machine-learning projects rapidly. Dataiku is focused on ...\",\"ae\":null,\"c\":\"https://seekingalpha.com/article/4662201-c3ai-missing-the-boat\",\"d\":\"seekingalpha.com/article/4662201-c3ai-missing-the-boat\",\"da\":\"translations\",\"e\":\"2024-01-10T19:38:00.0000000\",\"h\":0,\"i\":\"seekingalpha.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"C3.ai: Missing The Boat (NYSE:AI) | Seeking Alpha\",\"u\":\"https://seekingalpha.com/article/4662201-c3ai-missing-the-boat\"},{\"a\":\"The Information Intelligence teams are building groundbreaking technology for algorithmic search, machine learning, natural language processing, and artificial intelligence. The features we build are redefining how hundreds of millions of people use their computers and mobile devices to search and find what they are looking for.\",\"ae\":null,\"b\":\"apple\\tApple\\twww.apple.com\",\"c\":\"https://jobs.apple.com/en-us/details/200516237/aiml-software-engineer-machine-learning-platform-infrastructure\",\"d\":\"jobs.apple.com/en-us/details/200516237/aiml-software-engineer-machine-learning-platform-infrastructure\",\"da\":\"translations\",\"e\":\"2024-01-09T00:00:00.0000000\",\"h\":0,\"i\":\"jobs.apple.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Software Engineer, Machine Learning Platform & Infrastructure - Apple\",\"u\":\"https://jobs.apple.com/en-us/details/200516237/aiml-software-engineer-machine-learning-platform-infrastructure\"},{\"a\":\"One platform for all your robotics needs. Rapyuta Robotics aims at building low\\u00ad cost, lightweight autonomous mobile robots with high-level intelligence distributed in the cloud, enabling such robots to offload some of their heavy computation and seamlessly learn and share experiences with one another. Live your best life - at work and outside\",\"ae\":null,\"c\":\"https://www.tokyodev.com/companies/rapyuta-robotics\",\"d\":\"www.tokyodev.com/companies/rapyuta-robotics\",\"da\":\"\",\"h\":0,\"i\":\"www.tokyodev.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Rapyuta Robotics | TokyoDev\",\"u\":\"https://www.tokyodev.com/companies/rapyuta-robotics\"},{\"a\":\"NTT DATA - a part of NTT Group - is a trusted global innovator of IT and business services headquartered in Tokyo. We help clients transform through consulting, industry solutions, business process services, IT modernization and managed services. NTT DATA enables clients, as well as society, to move confidently into the digital future. We are committed to our clients' long-term success ...\",\"ae\":null,\"c\":\"https://www.servicenow.com/partners/partner-finder/ntt-data-corp.html\",\"d\":\"www.servicenow.com/partners/partner-finder/ntt-data-corp.html\",\"da\":\"\",\"h\":0,\"i\":\"www.servicenow.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"NTT DATA Corporation - ServiceNow\",\"u\":\"https://www.servicenow.com/partners/partner-finder/ntt-data-corp.html\"},{\"a\":\"Maruha Nichiro Corporation Food Production Toyosu, Koto-ku, Tokyo 1,941 followers "Bringing Delicious Delight to the World."\",\"ae\":null,\"b\":\"li\\tLinkedIn\\twww.linkedin.com\",\"c\":\"https://www.linkedin.com/company/maruha-nichiro-corporation\",\"d\":\"www.linkedin.com/company/maruha-nichiro-corporation\",\"da\":\"\",\"h\":0,\"i\":\"www.linkedin.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Maruha Nichiro Corporation | LinkedIn\",\"u\":\"https://www.linkedin.com/company/maruha-nichiro-corporation\"},{\"a\":\"PACE and SoX in collaboration with ACCESS and the Pittsburgh Supercomputing Center are pleased to host an HPC workshop on Big Data & Machine Learning, to be held on January 29 and 31, 2024. This workshop will focus on topics including big data analytics and machine learning with Spark, and deep learning using Tensorflow. It will have a hands-on component using the Bridges-2 computing platform ...\",\"ae\":null,\"c\":\"https://www.gatech.edu/event/2024/01/12/access-big-data-machine-learning-workshop\",\"d\":\"www.gatech.edu/event/2024/01/12/access-big-data-machine-learning-workshop\",\"da\":\"translations\",\"e\":\"2024-01-12T00:00:00.0000000\",\"h\":0,\"i\":\"www.gatech.edu\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"ACCESS Big Data & Machine Learning Workshop - Georgia Institute of ...\",\"u\":\"https://www.gatech.edu/event/2024/01/12/access-big-data-machine-learning-workshop\"},{\"a\":\"Start date: January 2024 or later. Our Tokyo engineering team is looking for robotics software interns for a minimum duration of six months capable of supporting the team to build state-of-the-art, scalable, autonomous mobile robots. The team works closely with some of the leading Japanese companies to build pioneering robotics solutions by leveraging rapyuta.io, our cloud robotics platform.\",\"ae\":null,\"c\":\"https://apply.workable.com/rapyuta-robotics/j/3ADFC72B04/\",\"d\":\"apply.workable.com/rapyuta-robotics/j/3ADFC72B04/\",\"da\":\"translations\",\"h\":0,\"i\":\"apply.workable.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Robotics Software Intern 2024 - Rapyuta Robotics\",\"u\":\"https://apply.workable.com/rapyuta-robotics/j/3ADFC72B04/\"},{\"n\":\"/d.js?q=Dataiku%20machine%20learning%20platform&kl=wt-wt&l=wt-wt&p=&s=26&ex=-1&ct=US&sp=0&vqd=4-135627661863888098952136153695171249901\"}]);DDG.duckbar.load('images');DDG.duckbar.load('news');DDG.duckbar.load('videos');DDG.duckbar.loadModule('related_searches', {\"ads\":[],\"query\":\"Dataiku machine learning platform\",\"queryEncoded\":\"Dataiku%20machine%20learning%20platform\",\"response_type\":\"places\",\"results\":[{\"display_text\":\"dataiku online machine learning\",\"text\":\"dataiku online machine learning\",\"web_search_url\":\"?q=dataiku%20online%20machine%20learning\"},{\"display_text\":\"dataiku machine learning plugin\",\"text\":\"dataiku machine learning plugin\",\"web_search_url\":\"?q=dataiku%20machine%20learning%20plugin\"},{\"display_text\":\"dataiku machine learning model\",\"text\":\"dataiku machine learning model\",\"web_search_url\":\"?q=dataiku%20machine%20learning%20model\"},{\"display_text\":\"dataiku machine learning extension\",\"text\":\"dataiku machine learning extension\",\"web_search_url\":\"?q=dataiku%20machine%20learning%20extension\"},{\"display_text\":\"automated machine learning dataiku\",\"text\":\"automated machine learning dataiku\",\"web_search_url\":\"?q=automated%20machine%20learning%20dataiku\"},{\"display_text\":\"dataiku production server\",\"text\":\"dataiku production server\",\"web_search_url\":\"?q=dataiku%20production%20server\"},{\"display_text\":\"dataiku automated automation\",\"text\":\"dataiku automated automation\",\"web_search_url\":\"?q=dataiku%20automated%20automation\"},{\"display_text\":\"dataiku key capabilities\",\"text\":\"dataiku key capabilities\",\"web_search_url\":\"?q=dataiku%20key%20capabilities\"}],\"vqd\":{\"Dataiku%20machine%20learning%20platform\":\"4-135627661863888098952136153695171249901\"}});if (DDG.pageLayout) DDG.pageLayout.initialize({\"mainline\":{\"items\":[[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"related_searches\"]]},\"sidebar\":{\"items\":[[\"wikipedia_fathead\"]]}}, { start: 0 });DDG.deep.emit(\"load:completed\");", + "curl-cffi-POST-https://duckduckgo.com-{\"data\": {\"q\": \"DataRobot AI platform comparison\"}}": "DataRobot AI platform comparison at DuckDuckGo
", + "curl-cffi-GET-https://links.duckduckgo.com/d.js-{\"params\": {\"bing_market\": \"wt-WT\", \"df\": null, \"ex\": \"-1\", \"kl\": \"wt-wt\", \"l\": \"wt-wt\", \"q\": \"DataRobot AI platform comparison\", \"s\": \"0\", \"sp\": \"0\", \"vqd\": \"4-58620545585474558767320902709740831322\"}}": "if (DDG.deep && DDG.deep.setUpstream) DDG.deep.setUpstream(\"bingv7aa\");DDG.deep.bn={'ivc':1};if (DDG.pageLayout) DDG.pageLayout.load('a',[{\"a\":\"\\u9ad8\\u7cbe\\u5ea6\\u306a\\u6a5f\\u68b0\\u5b66\\u7fd2\\u30e2\\u30c7\\u30eb\\u3092\\u69cb\\u7bc9\\u3001\\u5b9f\\u88c5\\u3001\\u904b\\u7528\\u3002DataRobot\\u306f\\u793e\\u5185\\u30c7\\u30fc\\u30bf\\u304b\\u3089\\u65b0\\u3057\\u3044\\u4fa1\\u5024\\u3092\\u5275\\u9020\\u3057\\u307e\\u3059. DataRobot\\u306f\\u7c21\\u5358\\u306a\\u64cd\\u4f5c\\u3067\\u30c7\\u30fc\\u30bf\\u304b\\u3089\\u4fa1\\u5024\\u3092\\u5275\\u51fa\",\"adext\":{\"filterlinks\":{\"l\":[],\"tid\":\"\"},\"sitelinks\":{\"l\":[{\"snippet\":\"Explore the DataRobot AI Platform Get Started With a 30-Day Trial\",\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=TADjssf2xUPiUP4Z%2DpL%2Djw%3D%3D&rut=458d772e8fcb4e4324d9389389d604bf4a83994e8046495904402de9aadd8689&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8wZWcT1GcY01mZtMuvlFYRDVUCUwR59UrUKaRMOBuANnCWi%2D8iLso5PuAoywij1cMeNLxieP5AAeMQUBqIlxZTsdWNA7YZoBicc1jtvLW_ZEmp6X0lumVtbFw9IJCDFojWdEcfYE0O0SvTWErWCBN9jCLQwEegRDrKirFobgUYBqEYLfhMVAeD3x862y3EMIPxcrug60dWItb0_gnTv06GzMdT9Q%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZnRyaWFsJTJmJTNmdXRtX21lZGl1bSUzZHNlYXJjaCUyNnV0bV9zb3VyY2UlM2RiaW5nJTI2dXRtX2NhbXBhaWduJTNkRnJlZVRyaWFsMjAyM1dXMDgxNkdQU2FkZXh0JTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDgwNjM0Y2YzMGRlMDE3MTAyNjVmMjk1MGYyZTYxNzM1%26rlid%3D80634cf30de01710265f2950f2e61735&vqd=4-266956621161894169747609047079670999441&iurl=%7B1%7DIG%3D4E234A2A70BD47BA8D9437C2FE20102A%26CID%3D0DBF2147217B62AE10B83541204E63FB%26ID%3DDevEx%2C5065.1\",\"text\":\"DataRobot Free Trial\"},{\"snippet\":\"Unlock Your AI Success in 2023 Tips on the Path of Value-Driven AI\",\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=TADjssf2xUPiUP4Z%2DpL%2Djw%3D%3D&rut=d527db3345d9139883b504b6a057be69be3347eeb5acd23b8e64f7449bb73b50&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8UTprN2eQMdFB5SJFU5fAVjVUCUxyH9ey14F3ix7IMGUN9R8j4XI%2DxHFXyG6wW8QyDclA1ah53V6Dl1LRU3JgQHXtprRWsm0zG%2DDqcpZf1i6kJFAmi315DCmvKoT6C3z97QkhAnr4yX%2Dv3glHLhN9uc3yL9wfU5U7nv5YTzG9UKxaD_%2DK2eubvLD7ldJaBI4tjPKQUhliUQqV4yr72OBpGoew774%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZnJlc291cmNlcyUyZmFpc3VjY2VzczIwMjMlMmYlM2Z1dG1fbWVkaXVtJTNkc2VhcmNoJTI2dXRtX3NvdXJjZSUzZGJpbmclMjZ1dG1fY2FtcGFpZ24lM2RDb250ZW50MTBLZXlzdG9BSVN1Y2Nlc3MyMDIzV1cwNTIyR1BTYWRleHQlMjZ1dG1fdGVybSUzZGRhdGFyb2JvdCUyNnV0bV9jb250ZW50JTNkYWRfZXh0JTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDRiOWQwYTViOGQ4YTE4YTNkOGI1NmZmODcyOGM1Yzg4%26rlid%3D4b9d0a5b8d8a18a3d8b56ff8728c5c88&vqd=4-186891061025271488176703891649000666566&iurl=%7B1%7DIG%3D4E234A2A70BD47BA8D9437C2FE20102A%26CID%3D0DBF2147217B62AE10B83541204E63FB%26ID%3DDevEx%2C5067.1\",\"text\":\"10 Keys to AI Success\"},{\"snippet\":\"Our Platform Includes Four Fully Integrated Products. Read More.\",\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=TADjssf2xUPiUP4Z%2DpL%2Djw%3D%3D&rut=9fb136d3bde9c28bb5c474789d38421625142c03b6cd89976b66ce5517d4b669&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8ouxsAouiEsi%2DDc9BM8u61DVUCUxad20UaEBujK70scJAQPZlPSbbKQxos2Uiw4fxi21%2DVgvVutJWxTj1GAp5dA40ea3WyEU8c7sfEzgUyRqLe5kCWLFg_dSdKKL5y1cUUcQ8Vz7ZK25elf6NLz9GTXdqOHZ9m5%2D1nK%2DKxXXXJEwnP9Hq6S9AujOSKuU63ixP2CmCTMdq9C64CzxUWU_R17nOAG0%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZnByb2R1Y3QlMmYlM2ZjYW1wYWlnbmlkJTNkNTMwNzA4MDk5JTI2YWRncm91cGlkJTNkMTM1MDIwMjc3NDIxNzY5OCUyNmFkaWQlM2QlMjZtc2Nsa2lkJTNkM2E2NzBlMjdhODcxMThhODkzNDQ2Yjg0NTc3Nzk1YmQ%26rlid%3D3a670e27a87118a893446b84577795bd&vqd=4-73641448877716277028608780106696479949&iurl=%7B1%7DIG%3D4E234A2A70BD47BA8D9437C2FE20102A%26CID%3D0DBF2147217B62AE10B83541204E63FB%26ID%3DDevEx%2C5069.1\",\"text\":\"Product Overview\"}],\"tid\":\"6\\t8[7]\\t10[9]\\t12[11]\",\"type\":\"EnhancedSiteLink\"},\"tid\":\"1\"},\"ae\":null,\"c\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=TADjssf2xUPiUP4Z%2DpL%2Djw%3D%3D&rut=489d897f192221406105931c23952ee9ddfcf9255a24130474c891f263e96e00&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De839_LMH5pa8tva7WIdtsEfDVUCUwdFj2%2D%2DKtKdG6HDyt85Ce7V%2DiiQ2w5qD19CAl57L1dYymA6REaydrRBR2k46ZVmaiPv9HjtdlGliBcpsrqORKeHvMrkxqdZFZpqnPhGXg22zPoUr7K1CebeDBNfuES4v6ILDlFk4%2DMyDHiYvcYYoW2JyhgHVssKxbFEZG7OHwmGw%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZmpwJTJmbHAlMmZhaS1mb3ItYnVzaW5lc3MlMmYlM2Z1dG1fbWVkaXVtJTNkc2VhcmNoJTI2dXRtX3NvdXJjZSUzZGJpbmclMjZ1dG1fY2FtcGFpZ24lM2RERU1PMjAyM0FsbFByb2R1Y3RzSlAwNjI2QlBTJTI2dXRtX3Rlcm0lM2RkYXRhcm9ib3QlMjZ1dG1fY29udGVudCUzZERSX2JyYW5kZWRfcnNhJTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDQ3ZTc1ZGU1Y2FjYzFlODRlOTUzMzg0NjM1Y2FjNTc2%26rlid%3D47e75de5cacc1e84e953384635cac576&vqd=4-261134921179772841597192846410308597281&iurl=%7B1%7DIG%3D4E234A2A70BD47BA8D9437C2FE20102A%26CID%3D0DBF2147217B62AE10B83541204E63FB%26ID%3DDevEx%2C5061.1\",\"d\":\"datarobot.com\",\"h\":0,\"i\":\"\",\"k\":0,\"m\":0,\"o\":\"\",\"p\":1,\"relevancy\":{\"abstract\":\"%E9%AB%98%E7%B2%BE%E5%BA%A6%E3%81%AA%E6%A9%9F%E6%A2%B0%E5%AD%A6%E7%BF%92%E3%83%A2%E3%83%87%E3%83%AB%E3%82%92%E6%A7%8B%E7%AF%89%E3%80%81%E5%AE%9F%E8%A3%85%E3%80%81%E9%81%8B%E7%94%A8%E3%80%82%3Cb%3EDataRobot%3C%2Fb%3E%E3%81%AF%E7%A4%BE%E5%86%85%E3%83%87%E3%83%BC%E3%82%BF%E3%81%8B%E3%82%89%E6%96%B0%E3%81%97%E3%81%84%E4%BE%A1%E5%80%A4%E3%82%92%E5%89%B5%E9%80%A0%E3%81%97%E3%81%BE%E3%81%99.%20%3Cb%3EDataRobot%3C%2Fb%3E%E3%81%AF%E7%B0%A1%E5%8D%98%E3%81%AA%E6%93%8D%E4%BD%9C%E3%81%A7%E3%83%87%E3%83%BC%E3%82%BF%E3%81%8B%E3%82%89%E4%BE%A1%E5%80%A4%E3%82%92%E5%89%B5%E5%87%BA\",\"adx_name\":\"none\",\"is_good_v10\":1,\"organic_ranks\":[\"0\",12,15,20,23],\"q\":\"DataRobot%20AI%20platform%20comparison\",\"q_words\":4,\"q_words_fuzzy\":0.25,\"q_words_in_ad\":1,\"root_domain\":\"datarobot.com\",\"start\":\"0\",\"title\":\"%E3%83%93%E3%83%83%E3%82%B0%E3%83%87%E3%83%BC%E3%82%BF%E5%88%86%E6%9E%90%E3%82%92%E9%AB%98%E9%80%9F%E5%8C%96%20%2D%20%E3%83%87%E3%83%BC%E3%82%BF%E3%81%8B%E3%82%89%E6%96%B0%E3%81%97%E3%81%84%E4%BE%A1%E5%80%A4%E3%82%92\"},\"s\":\"bingv7aa\",\"t\":\"\\u30d3\\u30c3\\u30b0\\u30c7\\u30fc\\u30bf\\u5206\\u6790\\u3092\\u9ad8\\u901f\\u5316 - \\u30c7\\u30fc\\u30bf\\u304b\\u3089\\u65b0\\u3057\\u3044\\u4fa1\\u5024\\u3092\",\"tid\":\"1,6,8[7],10[9],12[11]\",\"u\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=TADjssf2xUPiUP4Z%2DpL%2Djw%3D%3D&rut=489d897f192221406105931c23952ee9ddfcf9255a24130474c891f263e96e00&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De839_LMH5pa8tva7WIdtsEfDVUCUwdFj2%2D%2DKtKdG6HDyt85Ce7V%2DiiQ2w5qD19CAl57L1dYymA6REaydrRBR2k46ZVmaiPv9HjtdlGliBcpsrqORKeHvMrkxqdZFZpqnPhGXg22zPoUr7K1CebeDBNfuES4v6ILDlFk4%2DMyDHiYvcYYoW2JyhgHVssKxbFEZG7OHwmGw%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZmpwJTJmbHAlMmZhaS1mb3ItYnVzaW5lc3MlMmYlM2Z1dG1fbWVkaXVtJTNkc2VhcmNoJTI2dXRtX3NvdXJjZSUzZGJpbmclMjZ1dG1fY2FtcGFpZ24lM2RERU1PMjAyM0FsbFByb2R1Y3RzSlAwNjI2QlBTJTI2dXRtX3Rlcm0lM2RkYXRhcm9ib3QlMjZ1dG1fY29udGVudCUzZERSX2JyYW5kZWRfcnNhJTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDQ3ZTc1ZGU1Y2FjYzFlODRlOTUzMzg0NjM1Y2FjNTc2%26rlid%3D47e75de5cacc1e84e953384635cac576&vqd=4-261134921179772841597192846410308597281&iurl=%7B1%7DIG%3D4E234A2A70BD47BA8D9437C2FE20102A%26CID%3D0DBF2147217B62AE10B83541204E63FB%26ID%3DDevEx%2C5061.1\"}], {\"page_load_url\":\"https://duckduckgo.com/y.js?ifu=%7B3%7Dappid%3D055AAD1BA669BEB8B048128DC89A107C678B527B%26rguid%3D0716358df9934510b6d5d49119d2d6d3&iurl=%7B2%7DIG%3D4E234A2A70BD47BA8D9437C2FE20102A%26CID%3D0DBF2147217B62AE10B83541204E63FB%26Type%3DEvent.CPT%26DATA%3D0\",\"visibility_url\":\"https://duckduckgo.com/y.js?ivu=%7B4%7Dtype%3Dmv%26reqver%3D1.0%26rg%3D0716358df9934510b6d5d49119d2d6d3\"});DDG.deep.signalSummary = \"\";DDG.inject('DDG.Data.languages.resultLanguages', {\"en\":[\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/datarobot/product/datarobot-ai-platform\",\"https://www.gartner.com/reviews/market/data-preparation-tools/vendor/datarobot/product/datarobot-ai-platform\",\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/compare/datarobot-vs-h2o-ai\",\"https://www.trustradius.com/compare-products/datarobot-vs-google-cloud-ai\",\"https://www.trustradius.com/compare-products/dataiku-dss-vs-datarobot\",\"https://www.trustradius.com/compare-products/datarobot-vs-h2o\",\"https://www.eweek.com/big-data-and-analytics/c3-ai-vs-datarobot/\",\"https://research.aimultiple.com/automl-comparison/\",\"https://valohai.com/mlops-platforms-compared/\",\"https://www.gartner.com/reviews/market/augmented-data-quality-solutions/vendor/datarobot/product/datarobot-ai-platform\",\"https://internetstack.com/comparison/datarobot/vs/h2o-ai/\",\"https://www.datarobot.com/\",\"https://www.datarevenue.com/en-blog/ml-platforms-dataiku-vs-alteryx-vs-sagemaker\",\"https://solutionsreview.com/business-intelligence/the-best-ai-tools-for-data-science/\",\"https://docs.datarobot.com/en/docs/modeling/analyze-models/other/model-compare.html\",\"https://www.g2.com/products/datarobot/competitors/alternatives\",\"https://openai.com/blog/introducing-chatgpt-team\",\"https://www.datarobot.com/blog/big-data-and-artificial-intelligence-a-quick-comparison/\",\"https://www.gartner.com/reviews/market/data-preparation-tools/vendor/datarobot/product/datarobot-ai-platform/alternatives\",\"https://nvidianews.nvidia.com/news/geforce-rtx-40-super-series\",\"https://www.datarobot.com/blog/2023-a-year-of-innovation-and-impact/\"]});DDG.deep.pageLayoutSummary = \"a1w24r1\";DDG.inject('DDG.Data.languages.adLanguages', {});if (DDG.pageLayout) DDG.pageLayout.load('d',[{\"a\":\"AI APIs AND FRAMEWORKS DATA PLATFORMS Custom Chat APPLICATIONS Compose and Compare Compose and Compare Train and Tune Train and Tune Analyze and Transform Analyze and Transform BUILD BUILD Document and Comply Document and Comply Audit and Approve Audit and Approve Register and Manage Register and Manage GOVERN GOVERN Learn and Optimize Learn and...\",\"ae\":null,\"c\":\"https://www.datarobot.com/platform/\",\"d\":\"www.datarobot.com/platform/\",\"da\":\"\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Platform Overview | DataRobot AI Platform\",\"u\":\"https://www.datarobot.com/platform/\"},{\"a\":\"Reviewed in Last 12 Months mail_outline Email Page 4.6 508 Ratings (All Time) Rating Distribution 5 Star 63% 4 Star 33% 3 Star 3% 2 Star 0% 1 Star 0% Distribution based on 508 ratings Customer Experience Evaluation & Contracting 4.5 Integration & Deployment 4.5 Service & Support 4.7 Product Capabilities 4.6 FREE\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/datarobot/product/datarobot-ai-platform\",\"d\":\"www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/datarobot/product/datarobot-ai-platform\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot AI Platform Reviews - Gartner\",\"u\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/datarobot/product/datarobot-ai-platform\"},{\"a\":\"4 Star 42% 3 Star 3% 2 Star 0% 1 Star 0% Distribution based on 36 ratings Customer Experience Evaluation & Contracting 4.6 Integration & Deployment 4.4 Service & Support 4.6 Product Capabilities 4.3 FREE View and Download Peer Insights About DataRobot AI Platform\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/data-preparation-tools/vendor/datarobot/product/datarobot-ai-platform\",\"d\":\"www.gartner.com/reviews/market/data-preparation-tools/vendor/datarobot/product/datarobot-ai-platform\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot AI Platform Reviews - Gartner\",\"u\":\"https://www.gartner.com/reviews/market/data-preparation-tools/vendor/datarobot/product/datarobot-ai-platform\"},{\"a\":\"DataRobot vs H2O.ai Based on verified reviews from real users in the Data Science and Machine Learning Platforms market. DataRobot has a rating of 4.6 stars with 508 reviews. H2O.ai has a rating of 4.4 stars with 108 reviews.\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/compare/datarobot-vs-h2o-ai\",\"d\":\"www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/compare/datarobot-vs-h2o-ai\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot vs H2O.ai 2024 | Gartner Peer Insights\",\"u\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/compare/datarobot-vs-h2o-ai\"},{\"a\":\"84 Reviews and Ratings Path to AI Success Google Cloud AI 84 Reviews and Ratings Have you used any of these products before? No, I use something else Compare DataRobot vs Google Cloud AI. 168 verified user reviews and ratings of features, pros, cons, pricing, support and more.\",\"ae\":null,\"c\":\"https://www.trustradius.com/compare-products/datarobot-vs-google-cloud-ai\",\"d\":\"www.trustradius.com/compare-products/datarobot-vs-google-cloud-ai\",\"da\":\"\",\"h\":0,\"i\":\"www.trustradius.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot vs Google Cloud AI | TrustRadius\",\"u\":\"https://www.trustradius.com/compare-products/datarobot-vs-google-cloud-ai\"},{\"a\":\"DataRobot 84 Reviews and Ratings Path to AI Success Compare Dataiku DSS vs DataRobot. 103 verified user reviews and ratings of features, pros, cons, pricing, support and more.\",\"ae\":null,\"c\":\"https://www.trustradius.com/compare-products/dataiku-dss-vs-datarobot\",\"d\":\"www.trustradius.com/compare-products/dataiku-dss-vs-datarobot\",\"da\":\"\",\"h\":0,\"i\":\"www.trustradius.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku DSS vs DataRobot | TrustRadius\",\"u\":\"https://www.trustradius.com/compare-products/dataiku-dss-vs-datarobot\"},{\"a\":\"The DataRobot AI Platform is presented as a solution that accelerates and democratizes data science by automating the end-to-end journey from data to value and allows users to deploy AI applications at scale. DataRobot provides a centrally governed platform that gives users AI to drive business outcomes, that is available on the user's cloud ...\",\"ae\":null,\"c\":\"https://www.trustradius.com/compare-products/datarobot-vs-h2o\",\"d\":\"www.trustradius.com/compare-products/datarobot-vs-h2o\",\"da\":\"\",\"h\":0,\"i\":\"www.trustradius.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot vs H2O | TrustRadius\",\"u\":\"https://www.trustradius.com/compare-products/datarobot-vs-h2o\"},{\"a\":\"C3 AI and DataRobot are two of the leading AI cloud platforms. As such, this is a close comparison. Each has an extensive set of artificial intelligence features. Which is best for your...\",\"ae\":null,\"c\":\"https://www.eweek.com/big-data-and-analytics/c3-ai-vs-datarobot/\",\"d\":\"www.eweek.com/big-data-and-analytics/c3-ai-vs-datarobot/\",\"da\":\"\",\"e\":\"2022-12-02T00:00:00.0000000\",\"h\":0,\"i\":\"www.eweek.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"C3 AI vs. DataRobot: Top AI CloudPlatforms | eWEEK\",\"u\":\"https://www.eweek.com/big-data-and-analytics/c3-ai-vs-datarobot/\"},{\"a\":\"Performance: H2O.ai has greater performance measures in classification and regression tasks. Automation: Tazi.ai and DataRobot offer greater automation rates. Popularity: Along with the Google Cloud AutoML platform, H2O.ai is also the most searched autoML vendor. DataRobot, H2O.ai, and Google Cloud AutoML are the leading vendors. However, you ...\",\"ae\":null,\"c\":\"https://research.aimultiple.com/automl-comparison/\",\"d\":\"research.aimultiple.com/automl-comparison/\",\"da\":\"\",\"e\":\"2023-12-14T00:00:00.0000000\",\"h\":0,\"i\":\"research.aimultiple.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"AutoML Tech / Products Comparison & Market Landscape in 2024 - AIMultiple\",\"u\":\"https://research.aimultiple.com/automl-comparison/\"},{\"a\":\"The platforms we've chosen for our analysis are ClearML, cnvrg.io, Dataiku, Datarobot, Iguazio, Sagemaker, Seldon and Valohai from the managed side, and Flyte, Kubeflow, MLflow and Metaflow from the open-source side. This is by no means an exhaustive list of all the MLOps tools out there. Most of these are tools that describe themselves as ...\",\"ae\":null,\"c\":\"https://valohai.com/mlops-platforms-compared/\",\"d\":\"valohai.com/mlops-platforms-compared/\",\"da\":\"\",\"h\":0,\"i\":\"valohai.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MLOps Platforms Compared - Valohai\",\"u\":\"https://valohai.com/mlops-platforms-compared/\"},{\"a\":\"5 Star 33% 4 Star 67% 3 Star 0% 2 Star 0% 1 Star 0% Distribution based on 3 ratings Customer Experience Evaluation & Contracting 4.5 Integration & Deployment 4.7 Service & Support 4.7 Product Capabilities 4.7 FREE View and Download Peer Insights About DataRobot AI Platform\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/augmented-data-quality-solutions/vendor/datarobot/product/datarobot-ai-platform\",\"d\":\"www.gartner.com/reviews/market/augmented-data-quality-solutions/vendor/datarobot/product/datarobot-ai-platform\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot AI Platform Reviews - Gartner\",\"u\":\"https://www.gartner.com/reviews/market/augmented-data-quality-solutions/vendor/datarobot/product/datarobot-ai-platform\"},{\"a\":\"H2O.ai. H2O.ai is an open source platform for machine learning and predictive analytics. It is designed to help businesses and organizations make better decisions by leveraging the power of data. H2O.ai is used by data scientists, engineers, and business analysts to build and deploy machine learning models quickly and easily.\",\"ae\":null,\"c\":\"https://internetstack.com/comparison/datarobot/vs/h2o-ai/\",\"d\":\"internetstack.com/comparison/datarobot/vs/h2o-ai/\",\"da\":\"\",\"h\":0,\"i\":\"internetstack.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot vs H2O.ai - Which is better? (Comparison)\",\"u\":\"https://internetstack.com/comparison/datarobot/vs/h2o-ai/\"},{\"a\":\"75% faster from start to implementation with AI automation 18X greater likelihood to buy for the highest-scored leads See the Story\",\"ae\":null,\"c\":\"https://www.datarobot.com/\",\"d\":\"www.datarobot.com\",\"da\":\"\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot AI Platform | Deliver Value from AI\",\"u\":\"https://www.datarobot.com/\"},{\"a\":\"Dataiku vs. Alteryx. Dataiku and Alteryx are both managed machine learning platforms, but Dataiku focuses on the engineering aspects, while Alteryx focuses on analytics and presentation. Dataiku provides Data Science Studio (DSS), a cross-platform desktop application that includes a notebook (similar to Jupyter Notebook) for engineers to write ...\",\"ae\":null,\"c\":\"https://www.datarevenue.com/en-blog/ml-platforms-dataiku-vs-alteryx-vs-sagemaker\",\"d\":\"www.datarevenue.com/en-blog/ml-platforms-dataiku-vs-alteryx-vs-sagemaker\",\"da\":\"\",\"h\":0,\"i\":\"www.datarevenue.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"ML Platforms: Dataiku vs. Alteryx vs. Sagemaker vs. Datarobot\",\"u\":\"https://www.datarevenue.com/en-blog/ml-platforms-dataiku-vs-alteryx-vs-sagemaker\"},{\"a\":\"DataRobot. Platform: DataRobot Enterprise AI Platform Related products: Paxata Data Preparation, Automated Machine Learning, Automated Time Series, MLOps Description: DataRobot offers an enterprise AI platform that automates the end-to-end process for building, deploying, and maintaining AI. The product is powered by open-source algorithms and can be leveraged on-prem, in the cloud or as a ...\",\"ae\":null,\"c\":\"https://solutionsreview.com/business-intelligence/the-best-ai-tools-for-data-science/\",\"d\":\"solutionsreview.com/business-intelligence/the-best-ai-tools-for-data-science/\",\"da\":\"\",\"e\":\"2024-01-11T00:00:00.0000000\",\"h\":0,\"i\":\"solutionsreview.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"The 11 Best AI Tools for Data Science to Consider in 2024\",\"u\":\"https://solutionsreview.com/business-intelligence/the-best-ai-tools-for-data-science/\"},{\"a\":\"Compare models. To compare models in a project with at least two models built, either: Select the Model Comparison tab. Select two models from the Leaderboard and use the Leaderboard menu's Compare Selected option. Once on the page, select models from the dropdown. The associated model statistics update to reflect the currently selected model ...\",\"ae\":null,\"c\":\"https://docs.datarobot.com/en/docs/modeling/analyze-models/other/model-compare.html\",\"d\":\"docs.datarobot.com/en/docs/modeling/analyze-models/other/model-compare.html\",\"da\":\"\",\"e\":\"2022-11-01T00:00:00.0000000\",\"h\":0,\"i\":\"docs.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Model Comparison: DataRobot docs - DataRobot AI Platform\",\"u\":\"https://docs.datarobot.com/en/docs/modeling/analyze-models/other/model-compare.html\"},{\"a\":\"Top DataRobot AI Platform Alternatives (All Time) How alternatives are selected Dataiku MATLAB Alteryx Designer IBM SPSS Statistics RapidMiner Studio Base SAS Anaconda Enterprise Databricks Data Intelligence Platform Considering alternatives to DataRobot AI Platform?\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/datarobot/product/datarobot-ai-platform/alternatives\",\"d\":\"www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/datarobot/product/datarobot-ai-platform/alternatives\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot AI Platform Alternatives - Gartner\",\"u\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/datarobot/product/datarobot-ai-platform/alternatives\"},{\"a\":\"Top Alternatives to DataRobot AI Platform MathWorks Matlab Databricks Lakehouse Platform Dataiku TensorFlow TFX Google Cloud Vertex AI Alteryx View All Alternatives Best Alternatives and Competitors to DataRobot AI Platform\",\"ae\":null,\"c\":\"https://www.softwarereviews.com/categories/200/products/6813/alternatives\",\"d\":\"www.softwarereviews.com/categories/200/products/6813/alternatives\",\"da\":\"translations\",\"h\":0,\"i\":\"www.softwarereviews.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot AI Platform Alternatives and Competitors | Machine ...\",\"u\":\"https://www.softwarereviews.com/categories/200/products/6813/alternatives\"},{\"a\":\"#1 Alteryx (458) 4.6 out of 5 Alteryx drives transformational business outcomes through unified analytics, data science, and process automation. Categories in common with DataRobot: Data Science and Machine Learning Platforms Predictive Analytics Try for free Reviewers say compared to DataRobot, Alteryx is: Easier to set up More expensive\",\"ae\":null,\"c\":\"https://www.g2.com/products/datarobot/competitors/alternatives\",\"d\":\"www.g2.com/products/datarobot/competitors/alternatives\",\"da\":\"\",\"h\":0,\"i\":\"www.g2.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Top 10 DataRobot Alternatives & Competitors (Free/Paid) - G2\",\"u\":\"https://www.g2.com/products/datarobot/competitors/alternatives\"},{\"a\":\"Today, we're adding a new self-serve plan: ChatGPT Team. ChatGPT Team offers access to our advanced models like GPT-4 and DALL\\u00b7E 3, and tools like Advanced Data Analysis. It additionally includes a dedicated collaborative workspace for your team and admin tools for team management. As with ChatGPT Enterprise, you own and control your ...\",\"ae\":null,\"c\":\"https://openai.com/blog/introducing-chatgpt-team\",\"d\":\"openai.com/blog/introducing-chatgpt-team\",\"da\":\"\",\"e\":\"2024-01-10T00:00:00.0000000\",\"h\":0,\"i\":\"openai.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Introducing ChatGPT Team - OpenAI\",\"u\":\"https://openai.com/blog/introducing-chatgpt-team\"},{\"a\":\"Big data and artificial intelligence: a quick comparison | DataRobot AI Platform Blog Big data and artificial intelligence: a quick comparison Big data and artificial intelligence: a quick comparison March 3, 2020 by DataRobot \\u00b7 3 min read This article was originally published at Algorithimia's website.\",\"ae\":null,\"c\":\"https://www.datarobot.com/blog/big-data-and-artificial-intelligence-a-quick-comparison/\",\"d\":\"www.datarobot.com/blog/big-data-and-artificial-intelligence-a-quick-comparison/\",\"da\":\"\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Big data and artificial intelligence: a quick comparison | DataRobot AI ...\",\"u\":\"https://www.datarobot.com/blog/big-data-and-artificial-intelligence-a-quick-comparison/\"},{\"a\":\"36 Ratings compare_arrows Compare rate_review Write a Review download_2 Download PDF Related markets: DataRobot AI Platform in Data Science and Machine Learning Platforms (508 Reviews), DataRobot AI Platform in Augmented Data Quality Solutions (3 Reviews), DataRobot AI Platform in Predictive Analytics Software (1 Review)\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/data-preparation-tools/vendor/datarobot/product/datarobot-ai-platform/alternatives\",\"d\":\"www.gartner.com/reviews/market/data-preparation-tools/vendor/datarobot/product/datarobot-ai-platform/alternatives\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot AI Platform Alternatives - Gartner\",\"u\":\"https://www.gartner.com/reviews/market/data-preparation-tools/vendor/datarobot/product/datarobot-ai-platform/alternatives\"},{\"a\":\"An AI-Powered Leap in PC Computing The new GeForce RTX SUPER GPUs are the ultimate way to experience AI on PCs. Specialized AI Tensor Cores deliver up to 836 AI TOPS to deliver transformative capabilities for AI in gaming, creating and everyday productivity. The rich software stack built on top of RTX GPUs further accelerates AI.\",\"ae\":null,\"c\":\"https://nvidianews.nvidia.com/news/geforce-rtx-40-super-series\",\"d\":\"nvidianews.nvidia.com/news/geforce-rtx-40-super-series\",\"da\":\"translations\",\"e\":\"2024-01-08T00:00:00.0000000\",\"h\":0,\"i\":\"nvidianews.nvidia.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"GeForce RTX 40 SUPER Series: New Heroes Debut in the Gaming and ...\",\"u\":\"https://nvidianews.nvidia.com/news/geforce-rtx-40-super-series\"},{\"a\":\"We unveiled new enterprise-grade generative AI functionality to close the confidence gap and accelerate adoption, including generative AI application cost and performance monitoring, a unified observability console and registry for governance, multi-provider comparison playground and other enhancements to deliver greater transparency and governa...\",\"ae\":null,\"c\":\"https://www.datarobot.com/blog/2023-a-year-of-innovation-and-impact/\",\"d\":\"www.datarobot.com/blog/2023-a-year-of-innovation-and-impact/\",\"da\":\"translations\",\"e\":\"2023-12-21T00:00:00.0000000\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"2023: A Year of Innovation and Impact | DataRobot AI Platform\",\"u\":\"https://www.datarobot.com/blog/2023-a-year-of-innovation-and-impact/\"},{\"n\":\"/d.js?q=DataRobot%20AI%20platform%20comparison&kl=wt-wt&l=wt-wt&p=&s=24&ex=-1&ct=US&sp=0&vqd=4-58620545585474558767320902709740831322\"}]);DDG.duckbar.load('images');DDG.duckbar.load('news');DDG.duckbar.load('videos');DDG.duckbar.loadModule('related_searches', {\"ads\":[],\"query\":\"DataRobot AI platform comparison\",\"queryEncoded\":\"DataRobot%20AI%20platform%20comparison\",\"response_type\":\"places\",\"results\":[{\"display_text\":\"data robot ai platform\",\"text\":\"data robot ai platform\",\"web_search_url\":\"?q=data%20robot%20ai%20platform\"},{\"display_text\":\"datarobot ai partners\",\"text\":\"datarobot ai partners\",\"web_search_url\":\"?q=datarobot%20ai%20partners\"},{\"display_text\":\"data robot platforms\",\"text\":\"data robot platforms\",\"web_search_url\":\"?q=data%20robot%20platforms\"},{\"display_text\":\"datarobot partner portal\",\"text\":\"datarobot partner portal\",\"web_search_url\":\"?q=datarobot%20partner%20portal\"},{\"display_text\":\"data robot partners\",\"text\":\"data robot partners\",\"web_search_url\":\"?q=data%20robot%20partners\"},{\"display_text\":\"data robot data warehouse\",\"text\":\"data robot data warehouse\",\"web_search_url\":\"?q=data%20robot%20data%20warehouse\"}],\"vqd\":{\"DataRobot%20AI%20platform%20comparison\":\"4-58620545585474558767320902709740831322\"}});if (DDG.pageLayout) DDG.pageLayout.initialize({\"mainline\":{\"items\":[[\"ad\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"related_searches\"]]}}, { start: 0 });DDG.deep.emit(\"load:completed\");", + "curl-cffi-POST-https://duckduckgo.com-{\"data\": {\"q\": \"Dataiku vs DataRobot features\"}}": "Dataiku vs DataRobot features at DuckDuckGo
", + "curl-cffi-GET-https://links.duckduckgo.com/d.js-{\"params\": {\"bing_market\": \"wt-WT\", \"df\": null, \"ex\": \"-1\", \"kl\": \"wt-wt\", \"l\": \"wt-wt\", \"q\": \"Dataiku vs DataRobot features\", \"s\": \"0\", \"sp\": \"0\", \"vqd\": \"4-334935250614046875026454141242803242982\"}}": "if (DDG.deep && DDG.deep.setUpstream) DDG.deep.setUpstream(\"bingv7aa\");DDG.deep.bn={'ivc':1};if (DDG.pageLayout) DDG.pageLayout.load('a',[{\"a\":\"\\u9ad8\\u7cbe\\u5ea6\\u306a\\u6a5f\\u68b0\\u5b66\\u7fd2\\u30e2\\u30c7\\u30eb\\u3092\\u69cb\\u7bc9\\u3001\\u5b9f\\u88c5\\u3001\\u904b\\u7528\\u3002DataRobot\\u306f\\u793e\\u5185\\u30c7\\u30fc\\u30bf\\u304b\\u3089\\u65b0\\u3057\\u3044\\u4fa1\\u5024\\u3092\\u5275\\u9020\\u3057\\u307e\\u3059. DataRobot\\u306f\\u4f01\\u696d\\u306e\\u8ab2\\u984c\\u89e3\\u6c7a\\u306b\\u7279\\u5316\\u3002\\u610f\\u601d\\u6c7a\\u5b9a\\u306e\\u81ea\\u52d5\\u5316\\u304b\\u3089\\u9700\\u8981\\u4e88\\u6e2c\\u3001\\u8981\\u56e0\\u5206\\u6790\\u307e\\u3067\\u3053\\u306a\\u3059AI\\u30c4\\u30fc\\u30eb\",\"adext\":{\"callout\":{\"t\":\"Data Science Guardrails \\u00b7 Applied AI Expertise \\u00b7 Trusted by Fortune 50\",\"tid\":\"6\"},\"filterlinks\":{\"l\":[],\"tid\":\"\"},\"sitelinks\":{\"l\":[{\"snippet\":\"Explore the DataRobot AI Platform Get Started With a 30-Day Trial\",\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=uchwI3Eul8XsE%2DSUlPqxXg%3D%3D&rut=2381550f96a087800d427735905717264a1a708643136f2736a970e740068621&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8BGV0WifLHqlNArHdJt3WDTVUCUzDyrVI_ULomBTgn_xk1MKGRFElGY7vQ8fpE4l__S3CnH6%2D2cXlBQayeIz9CbLU7C4XEu8BgG6oZNQ6EtjG6vrYe5hjw1GZN7VBIkj6nn%2DsoUXy14mVbvkM5ojXVf8oeoz8pwdOc4ANH2TiL9vqJe6Lud2IZXvxJf1I%2DA935XcPQobPZKQaFNFMyygI3Y4TW8k%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZnRyaWFsJTJmJTNmdXRtX21lZGl1bSUzZHNlYXJjaCUyNnV0bV9zb3VyY2UlM2RiaW5nJTI2dXRtX2NhbXBhaWduJTNkRnJlZVRyaWFsMjAyM1dXMDgxNkdQU2FkZXh0JTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDFmMzU0ODE0ODNmMTEyM2Y5NGMzMmRiNzdjZjk5OWFm%26rlid%3D1f35481483f1123f94c32db77cf999af&vqd=4-25671318592048362755712261648304518289&iurl=%7B1%7DIG%3D3EB403B8C4EA42F4B7FF0CE90CB46EF0%26CID%3D2F20CB6F269D6DD02331DF69279D6C12%26ID%3DDevEx%2C5064.1\",\"text\":\"DataRobot Free Trial\"},{\"snippet\":\"Unlock Your AI Success in 2023 Tips on the Path of Value-Driven AI\",\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=uchwI3Eul8XsE%2DSUlPqxXg%3D%3D&rut=08def2477dd7311fbcffe4c409d28fcdbe68925a50cd2894a7502f8a11785352&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8lYdQlfjG0%2Dh77MMyzT0CuDVUCUyAuuZDH6K8NWyD2XSLoABvrUNVChVbIVOVgzl4xdT3EEUvHgd9P_FWLUDT2My42qKUP3iV87B7hLXXHLdGf7yjst8tWjp%2DcaQz3uiI0c5oom%2DRo8D7A4nohZAtS9199RQLYbNcbOpJnrNMCFmz6EiWk7JqMQ9DE1t9AjaMUWEkEV%2D3W2e8XmBq5bKtRsWnT0E%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZnJlc291cmNlcyUyZmFpc3VjY2VzczIwMjMlMmYlM2Z1dG1fbWVkaXVtJTNkc2VhcmNoJTI2dXRtX3NvdXJjZSUzZGJpbmclMjZ1dG1fY2FtcGFpZ24lM2RDb250ZW50MTBLZXlzdG9BSVN1Y2Nlc3MyMDIzV1cwNTIyR1BTYWRleHQlMjZ1dG1fdGVybSUzZGRhdGFyb2JvdCUyNnV0bV9jb250ZW50JTNkYWRfZXh0JTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDI5Zjc0NWY1MzNiNzE2NDU5ZGY0MjA1NmNjYmYyYWU0%26rlid%3D29f745f533b716459df42056ccbf2ae4&vqd=4-333465595216651803104351585568313334233&iurl=%7B1%7DIG%3D3EB403B8C4EA42F4B7FF0CE90CB46EF0%26CID%3D2F20CB6F269D6DD02331DF69279D6C12%26ID%3DDevEx%2C5066.1\",\"text\":\"10 Keys to AI Success\"},{\"snippet\":\"Our Platform Includes Four Fully Integrated Products. Read More.\",\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=uchwI3Eul8XsE%2DSUlPqxXg%3D%3D&rut=fbe7591a97a4b400635f8cfafd71893553c70fc90218355b7d5622310d9567db&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8cB2vIW6%2D5rxeC5vl08jFZjVUCUw2oN7vfXdo8rlxVmZIfw2bF94_ya9lvPQwUYXJFtTGXBslf_XCcVTiFtj2KJzp9yzLPOdWafvxxwBzn2iwextOSL%2Daq20iQ8nZNktMLYBD1xp3WjThLdejbBCFrR_RvD1YZcHcKf5y5auyV04F_V6x_D6nUwdRYFDmdyciLcpT7JO12EZkmM%2D1buahlzuiBmw%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZnByb2R1Y3QlMmYlM2ZjYW1wYWlnbmlkJTNkNTMwNzA4MDk5JTI2YWRncm91cGlkJTNkMTM1MDIwMjc3NDIxNzY5OCUyNmFkaWQlM2QlMjZtc2Nsa2lkJTNkMGZhOTg4ZjJkYWU2MWE3MGJhOTVlZDUxMjVlZWFlNDA%26rlid%3D0fa988f2dae61a70ba95ed5125eeae40&vqd=4-211419575679328898707892660118042825990&iurl=%7B1%7DIG%3D3EB403B8C4EA42F4B7FF0CE90CB46EF0%26CID%3D2F20CB6F269D6DD02331DF69279D6C12%26ID%3DDevEx%2C5068.1\",\"text\":\"Product Overview\"}],\"tid\":\"7\\t9[8]\\t11[10]\\t13[12]\",\"type\":\"EnhancedSiteLink\"},\"tid\":\"1\"},\"ae\":{\"callout\":[\"Data Science Guardrails \\u00b7 Applied AI Expertise \\u00b7 Trusted by Fortune 50\"]},\"c\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=uchwI3Eul8XsE%2DSUlPqxXg%3D%3D&rut=94a279ed1549c0107c5c13f21161fd5aaa0d3f08d19e7afd2ed4a19463b69d7d&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8XX6qufLbIkEZRIFo_zgmlDVUCUwOnCSpTtxK0dn2QInSfOGU5eU24GjiRwhmSr89Qa92PcEtK2h6KVoghC%2DNwNrkANG4L6sVirCfv5kl7GPWO9gqgcdw8x5ELjGH7N2HWgbdtH%2D7TWKtxZVdVIFwYJUQDUgM_ODwTspzwBbKKLHD4EPAO5U3RDO3R_igFUlsxkeFXA%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZmpwJTJmbHAlMmZhaS1mb3ItYnVzaW5lc3MlMmYlM2Z1dG1fbWVkaXVtJTNkc2VhcmNoJTI2dXRtX3NvdXJjZSUzZGJpbmclMjZ1dG1fY2FtcGFpZ24lM2RERU1PMjAyM0FsbFByb2R1Y3RzSlAwNjI2QlBTJTI2dXRtX3Rlcm0lM2RkYXRhcm9ib3QlMjZ1dG1fY29udGVudCUzZERSX2JyYW5kZWRfcnNhJTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZGQxMGY4ZjY4ZDYxZjFiOTg2NTc1ZWFjYjI5MTczYTQ1%26rlid%3Dd10f8f68d61f1b986575eacb29173a45&vqd=4-152568096679810917558416500867559274982&iurl=%7B1%7DIG%3D3EB403B8C4EA42F4B7FF0CE90CB46EF0%26CID%3D2F20CB6F269D6DD02331DF69279D6C12%26ID%3DDevEx%2C5059.1\",\"d\":\"datarobot.com\",\"h\":0,\"i\":\"\",\"k\":0,\"m\":0,\"o\":\"\",\"p\":1,\"relevancy\":{\"abstract\":\"%E9%AB%98%E7%B2%BE%E5%BA%A6%E3%81%AA%E6%A9%9F%E6%A2%B0%E5%AD%A6%E7%BF%92%E3%83%A2%E3%83%87%E3%83%AB%E3%82%92%E6%A7%8B%E7%AF%89%E3%80%81%E5%AE%9F%E8%A3%85%E3%80%81%E9%81%8B%E7%94%A8%E3%80%82%3Cb%3EDataRobot%3C%2Fb%3E%E3%81%AF%E7%A4%BE%E5%86%85%E3%83%87%E3%83%BC%E3%82%BF%E3%81%8B%E3%82%89%E6%96%B0%E3%81%97%E3%81%84%E4%BE%A1%E5%80%A4%E3%82%92%E5%89%B5%E9%80%A0%E3%81%97%E3%81%BE%E3%81%99.%20DataRobot%E3%81%AF%E4%BC%81%E6%A5%AD%E3%81%AE%E8%AA%B2%E9%A1%8C%E8%A7%A3%E6%B1%BA%E3%81%AB%E7%89%B9%E5%8C%96%E3%80%82%E6%84%8F%E6%80%9D%E6%B1%BA%E5%AE%9A%E3%81%AE%E8%87%AA%E5%8B%95%E5%8C%96%E3%81%8B%E3%82%89%E9%9C%80%E8%A6%81%E4%BA%88%E6%B8%AC%E3%80%81%E8%A6%81%E5%9B%A0%E5%88%86%E6%9E%90%E3%81%BE%E3%81%A7%E3%81%93%E3%81%AA%E3%81%99AI%E3%83%84%E3%83%BC%E3%83%AB\",\"adx_name\":\"none\",\"is_good_v10\":0,\"q\":\"Dataiku%20vs%20DataRobot%20features\",\"q_words\":4,\"q_words_fuzzy\":0.25,\"q_words_in_ad\":1,\"root_domain\":\"datarobot.com\",\"start\":\"0\",\"title\":\"%E3%83%87%E3%83%BC%E3%82%BF%E3%81%8B%E3%82%89%E6%96%B0%E3%81%97%E3%81%84%E4%BE%A1%E5%80%A4%E3%82%92%20%2D%20%E7%A4%BE%E5%86%85%E3%83%87%E3%83%BC%E3%82%BF%E3%81%8B%E3%82%89%E4%BE%A1%E5%80%A4%E5%89%B5%E5%87%BA\"},\"s\":\"bingv7aa\",\"t\":\"\\u30c7\\u30fc\\u30bf\\u304b\\u3089\\u65b0\\u3057\\u3044\\u4fa1\\u5024\\u3092 - \\u793e\\u5185\\u30c7\\u30fc\\u30bf\\u304b\\u3089\\u4fa1\\u5024\\u5275\\u51fa\",\"tid\":\"1,6,7,9[8],11[10],13[12]\",\"u\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=uchwI3Eul8XsE%2DSUlPqxXg%3D%3D&rut=94a279ed1549c0107c5c13f21161fd5aaa0d3f08d19e7afd2ed4a19463b69d7d&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8XX6qufLbIkEZRIFo_zgmlDVUCUwOnCSpTtxK0dn2QInSfOGU5eU24GjiRwhmSr89Qa92PcEtK2h6KVoghC%2DNwNrkANG4L6sVirCfv5kl7GPWO9gqgcdw8x5ELjGH7N2HWgbdtH%2D7TWKtxZVdVIFwYJUQDUgM_ODwTspzwBbKKLHD4EPAO5U3RDO3R_igFUlsxkeFXA%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZmpwJTJmbHAlMmZhaS1mb3ItYnVzaW5lc3MlMmYlM2Z1dG1fbWVkaXVtJTNkc2VhcmNoJTI2dXRtX3NvdXJjZSUzZGJpbmclMjZ1dG1fY2FtcGFpZ24lM2RERU1PMjAyM0FsbFByb2R1Y3RzSlAwNjI2QlBTJTI2dXRtX3Rlcm0lM2RkYXRhcm9ib3QlMjZ1dG1fY29udGVudCUzZERSX2JyYW5kZWRfcnNhJTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZGQxMGY4ZjY4ZDYxZjFiOTg2NTc1ZWFjYjI5MTczYTQ1%26rlid%3Dd10f8f68d61f1b986575eacb29173a45&vqd=4-152568096679810917558416500867559274982&iurl=%7B1%7DIG%3D3EB403B8C4EA42F4B7FF0CE90CB46EF0%26CID%3D2F20CB6F269D6DD02331DF69279D6C12%26ID%3DDevEx%2C5059.1\"}], {\"page_load_url\":\"https://duckduckgo.com/y.js?ifu=%7B3%7Dappid%3D055AAD1BA669BEB8B048128DC89A107C678B527B%26rguid%3D280881b97b9245e6a74bddebc1a6cbda&iurl=%7B2%7DIG%3D3EB403B8C4EA42F4B7FF0CE90CB46EF0%26CID%3D2F20CB6F269D6DD02331DF69279D6C12%26Type%3DEvent.CPT%26DATA%3D0\",\"visibility_url\":\"https://duckduckgo.com/y.js?ivu=%7B4%7Dtype%3Dmv%26reqver%3D1.0%26rg%3D280881b97b9245e6a74bddebc1a6cbda\"});DDG.deep.signalSummary = \"\";DDG.inject('DDG.Data.languages.resultLanguages', {\"en\":[\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/compare/dataiku-vs-datarobot\",\"https://www.trustradius.com/compare-products/dataiku-dss-vs-datarobot\",\"https://community.dataiku.com/t5/General-Discussion/Dataiku-vs-DataRobot/m-p/9315\",\"https://www.g2.com/compare/datarobot-vs-dataiku-dss\",\"https://www.datarevenue.com/en-blog/ml-platforms-dataiku-vs-alteryx-vs-sagemaker\",\"https://comparisons.financesonline.com/datarobot-vs-dataiku-dss\",\"https://slashdot.org/software/comparison/DataRobot-vs-Dataiku-DSS/\",\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\",\"https://www.gartner.com/reviews/market/dsml-engineering-platforms/compare/dataiku-vs-datarobot\",\"https://www.linkedin.com/pulse/managed-machine-learning-platforms-comparative-analysis/\",\"https://www.trustradius.com/products/datarobot/reviews?qs=pros-and-cons\",\"https://www.getapp.com/emerging-technology-software/a/dataiku-dss/compare/datarobot/\",\"https://www.softwarereviews.com/categories/machine-learning-platforms/compare/dataiku-vs-datarobot-ai-platform\",\"https://slashdot.org/software/comparison/Alteryx-vs-DataRobot-vs-Dataiku-DSS/\",\"https://slashdot.org/software/comparison/DataRobot-vs-Databricks-vs-Dataiku-DSS/\",\"https://valohai.com/mlops-platforms-compared/\",\"https://www.dataiku.com/product/plans-and-features/\",\"https://slashdot.org/software/comparison/DataRobot-vs-Databricks-vs-Dataiku-DSS-vs-datagym/\",\"https://sourceforge.net/software/compare/C3-AI-Suite-vs-DataRobot-vs-Dataiku-DSS/\",\"https://www.softwarereviews.com/categories/machine-learning-platforms/compare/datarobot-ai-platform-vs-dataiku\",\"https://slashdot.org/software/comparison/Amazon-SageMaker-vs-DataRobot-vs-Dataiku-DSS/\",\"https://sourceforge.net/software/compare/Analance-vs-DataRobot-vs-Dataiku-DSS/\"]});DDG.deep.pageLayoutSummary = \"a1w23r1,e1\";DDG.inject('DDG.Data.languages.adLanguages', {});if (DDG.pageLayout) DDG.pageLayout.load('d',[{\"a\":\"1 Star 0% Ratings breakdown Overall Capability Score Overall Rating 4.7 ( 504 reviews) 4.7 (20) Data Access and Manipulation 4.5 (224) Data Exploration and Visualization 4.7\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/compare/dataiku-vs-datarobot\",\"d\":\"www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/compare/dataiku-vs-datarobot\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku vs DataRobot 2024 | Gartner Peer Insights\",\"u\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/compare/dataiku-vs-datarobot\"},{\"a\":\"Path to AI Success Compare Dataiku DSS vs DataRobot. 103 verified user reviews and ratings of features, pros, cons, pricing, support and more.\",\"ae\":null,\"c\":\"https://www.trustradius.com/compare-products/dataiku-dss-vs-datarobot\",\"d\":\"www.trustradius.com/compare-products/dataiku-dss-vs-datarobot\",\"da\":\"\",\"h\":0,\"i\":\"www.trustradius.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku DSS vs DataRobot | TrustRadius\",\"u\":\"https://www.trustradius.com/compare-products/dataiku-dss-vs-datarobot\"},{\"a\":\"General Discussion Dataiku vs DataRobot Solved! Raja Level 2 08-22-2020 03:16 AM Please enlighten me, What distinguishes Dataiku from tools like DataRobot? They appear to be similar, trying to know how dataiku has an upper hand, would make it easy for placing option to customers. 1 Reply 2 Solutions Solutions shown first - Read whole discussion\",\"ae\":null,\"c\":\"https://community.dataiku.com/t5/General-Discussion/Dataiku-vs-DataRobot/m-p/9315\",\"d\":\"community.dataiku.com/t5/General-Discussion/Dataiku-vs-DataRobot/m-p/9315\",\"da\":\"\",\"h\":0,\"i\":\"community.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Solved: Dataiku vs DataRobot - Dataiku Community\",\"u\":\"https://community.dataiku.com/t5/General-Discussion/Dataiku-vs-DataRobot/m-p/9315\"},{\"a\":\"DataRobot vs Dataiku DSS When assessing the two solutions, reviewers found Dataiku DSS easier to use and administer. However, reviewers preferred the ease of set up, and doing business with DataRobot overall. Reviewers felt that DataRobot meets the needs of their business better than Dataiku DSS.\",\"ae\":null,\"c\":\"https://www.g2.com/compare/datarobot-vs-dataiku-dss\",\"d\":\"www.g2.com/compare/datarobot-vs-dataiku-dss\",\"da\":\"\",\"h\":0,\"i\":\"www.g2.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Compare DataRobot vs. Dataiku DSS | G2\",\"u\":\"https://www.g2.com/compare/datarobot-vs-dataiku-dss\"},{\"a\":\"Quick overview Before we get into a detailed comparison, here's a quick overview of each platform. Dataiku is a cross-platform desktop application that includes a broad range of tools, such as notebooks (similar to Jupyter Notebook), workflow management (similar to Apache Airflow), and automated machine learning.\",\"ae\":null,\"c\":\"https://www.datarevenue.com/en-blog/ml-platforms-dataiku-vs-alteryx-vs-sagemaker\",\"d\":\"www.datarevenue.com/en-blog/ml-platforms-dataiku-vs-alteryx-vs-sagemaker\",\"da\":\"\",\"h\":0,\"i\":\"www.datarevenue.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"ML Platforms: Dataiku vs. Alteryx vs. Sagemaker vs. Datarobot\",\"u\":\"https://www.datarevenue.com/en-blog/ml-platforms-dataiku-vs-alteryx-vs-sagemaker\"},{\"a\":\"Home Predictive Analysis Software DataRobot Dataiku DSS Why is FinancesOnline free Compare DataRobot vs Dataiku DSS What is better DataRobot or Dataiku DSS? Examining products to find the best Predictive Analysis Software does not always have to be tough.\",\"ae\":null,\"c\":\"https://comparisons.financesonline.com/datarobot-vs-dataiku-dss\",\"d\":\"comparisons.financesonline.com/datarobot-vs-dataiku-dss\",\"da\":\"\",\"h\":0,\"i\":\"comparisons.financesonline.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot vs Dataiku DSS 2024 Comparison | FinancesOnline\",\"u\":\"https://comparisons.financesonline.com/datarobot-vs-dataiku-dss\"},{\"a\":\"Machine Learning Software Dataiku vs DataRobot Dataiku vs DataRobot Share How Capterra Verifies Reviews Pricing Best for Screenshots Features Reviews Pros & Cons Deployment & Support Alternatives Company Details Dataiku VISIT PROFILE DataRobot VISIT PROFILE Pricing Starting from $ 0.01 /Year Pricing Model: Not provided by vendor Free Trial\",\"ae\":null,\"c\":\"https://www.capterra.com/machine-learning-software/compare/142192-179303/Data-Science-Studio-DSS-vs-DataRobot\",\"d\":\"www.capterra.com/machine-learning-software/compare/142192-179303/Data-Science-Studio-DSS-vs-DataRobot\",\"da\":\"translations\",\"h\":0,\"i\":\"www.capterra.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Compare Dataiku vs DataRobot 2024 | Capterra\",\"u\":\"https://www.capterra.com/machine-learning-software/compare/142192-179303/Data-Science-Studio-DSS-vs-DataRobot\"},{\"a\":\"What's the difference between DataRobot and Dataiku DSS? Compare DataRobot vs. Dataiku DSS in 2023 by cost, reviews, features, integrations, deployment, target market, support options, trial offers, training options, years in business, region, and more using the chart below.\",\"ae\":null,\"b\":\"/.\\tSlashdot\\tslashdot.org\",\"c\":\"https://slashdot.org/software/comparison/DataRobot-vs-Dataiku-DSS/\",\"d\":\"slashdot.org/software/comparison/DataRobot-vs-Dataiku-DSS/\",\"da\":\"\",\"h\":0,\"i\":\"slashdot.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Compare DataRobot vs. Dataiku DSS in 2023 - Slashdot\",\"u\":\"https://slashdot.org/software/comparison/DataRobot-vs-Dataiku-DSS/\"},{\"a\":\"1 Star 0% Distribution based on 504 ratings Customer Experience Evaluation & Contracting 4.6 Integration & Deployment 4.7 Service & Support 4.8 Product Capabilities 4.8 FREE View and Download Peer Insights About Dataiku\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\",\"d\":\"www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku Reviews, Ratings & Features 2024 | Gartner Peer Insights\",\"u\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\"},{\"a\":\"1329 reviews on 16 vendors. chevron_right. Yard Management. 25 reviews on 28 vendors. chevron_right. Zero Trust Network Access. 733 reviews on 47 vendors. chevron_right. Read the latest Gartner-verified reviews covering over 500+ software categories and find the best enterprise software or services for your organization.\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/dsml-engineering-platforms/compare/dataiku-vs-datarobot\",\"d\":\"www.gartner.com/reviews/market/dsml-engineering-platforms/compare/dataiku-vs-datarobot\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Explore Enterprise Software Categories | Gartner Peer Insights\",\"u\":\"https://www.gartner.com/reviews/market/dsml-engineering-platforms/compare/dataiku-vs-datarobot\"},{\"a\":\"1. Dataiku is a versatile desktop application comprised of a wide range of tools, including automated machine learning, notebooks, and workflow management. It aims to replace pre-existing tools...\",\"ae\":null,\"b\":\"li\\tLinkedIn\\twww.linkedin.com\",\"c\":\"https://www.linkedin.com/pulse/managed-machine-learning-platforms-comparative-analysis/\",\"d\":\"www.linkedin.com/pulse/managed-machine-learning-platforms-comparative-analysis/\",\"da\":\"\",\"e\":\"2023-08-11T00:00:00.0000000\",\"h\":0,\"i\":\"www.linkedin.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Managed Machine Learning Platforms: A Comparative Analysis - LinkedIn\",\"u\":\"https://www.linkedin.com/pulse/managed-machine-learning-platforms-comparative-analysis/\"},{\"a\":\"Dataiku DSS, H2O, and Google Cloud AI are common alternatives for DataRobot. What is DataRobot's best feature? Reviewers rate Automated Machine Learning highest, with a score of 9.3. Who uses DataRobot? The most common users of DataRobot are from Mid-sized Companies (51-1,000 employees).\",\"ae\":null,\"c\":\"https://www.trustradius.com/products/datarobot/reviews?qs=pros-and-cons\",\"d\":\"www.trustradius.com/products/datarobot/reviews?qs=pros-and-cons\",\"da\":\"\",\"h\":0,\"i\":\"www.trustradius.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Pros and Cons of DataRobot 2024 - TrustRadius\",\"u\":\"https://www.trustradius.com/products/datarobot/reviews?qs=pros-and-cons\"},{\"a\":\"Compare Dataiku and DataRobot based on features, pricing, verified reviews, integrations & more. Find out which software is best for your business today. 0. App comparison. Add up to 4 apps below to see how they compare. You can also use the "Compare" buttons while browsing.\",\"ae\":null,\"c\":\"https://www.getapp.com/emerging-technology-software/a/dataiku-dss/compare/datarobot/\",\"d\":\"www.getapp.com/emerging-technology-software/a/dataiku-dss/compare/datarobot/\",\"da\":\"\",\"h\":0,\"i\":\"www.getapp.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku vs DataRobot Comparison | GetApp\",\"u\":\"https://www.getapp.com/emerging-technology-software/a/dataiku-dss/compare/datarobot/\"},{\"a\":\"Dataiku vs DataRobot AI Platform Compare Dataiku and DataRobot AI Platform using real user data focused on features, satisfaction, business value, and the vendor relationship. What is Machine Learning Platforms (ML) Software?\",\"ae\":null,\"c\":\"https://www.softwarereviews.com/categories/machine-learning-platforms/compare/dataiku-vs-datarobot-ai-platform\",\"d\":\"www.softwarereviews.com/categories/machine-learning-platforms/compare/dataiku-vs-datarobot-ai-platform\",\"da\":\"\",\"h\":0,\"i\":\"www.softwarereviews.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku vs DataRobot AI Platform - Machine Learning Platforms\",\"u\":\"https://www.softwarereviews.com/categories/machine-learning-platforms/compare/dataiku-vs-datarobot-ai-platform\"},{\"a\":\"What's the difference between Alteryx, DataRobot, and Dataiku DSS? Compare Alteryx vs. DataRobot vs. Dataiku DSS in 2024 by cost, reviews, features, integrations, deployment, target market, support options, trial offers, training options, years in business, region, and more using the chart below. Alteryx View Product DataRobot View Product\",\"ae\":null,\"b\":\"/.\\tSlashdot\\tslashdot.org\",\"c\":\"https://slashdot.org/software/comparison/Alteryx-vs-DataRobot-vs-Dataiku-DSS/\",\"d\":\"slashdot.org/software/comparison/Alteryx-vs-DataRobot-vs-Dataiku-DSS/\",\"da\":\"\",\"h\":0,\"i\":\"slashdot.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Compare Alteryx vs. DataRobot vs. Dataiku DSS in 2023 - Slashdot\",\"u\":\"https://slashdot.org/software/comparison/Alteryx-vs-DataRobot-vs-Dataiku-DSS/\"},{\"a\":\"What's the difference between DataRobot, Databricks Lakehouse, and Dataiku DSS? Compare DataRobot vs. Databricks Lakehouse vs. Dataiku DSS in 2023 by cost, reviews, features, integrations, deployment, target market, support options, trial offers, training options, years in business, region, and more using the chart below.\",\"ae\":null,\"b\":\"/.\\tSlashdot\\tslashdot.org\",\"c\":\"https://slashdot.org/software/comparison/DataRobot-vs-Databricks-vs-Dataiku-DSS/\",\"d\":\"slashdot.org/software/comparison/DataRobot-vs-Databricks-vs-Dataiku-DSS/\",\"da\":\"\",\"h\":0,\"i\":\"slashdot.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Compare DataRobot vs. Databricks Lakehouse vs. Dataiku DSS - Slashdot\",\"u\":\"https://slashdot.org/software/comparison/DataRobot-vs-Databricks-vs-Dataiku-DSS/\"},{\"a\":\"The platforms we've chosen for our analysis are ClearML, cnvrg.io, Dataiku, Datarobot, Iguazio, Sagemaker, Seldon and Valohai from the managed side, and Flyte, Kubeflow, MLflow and Metaflow from the open-source side. This is by no means an exhaustive list of all the MLOps tools out there. Most of these are tools that describe themselves as ...\",\"ae\":null,\"c\":\"https://valohai.com/mlops-platforms-compared/\",\"d\":\"valohai.com/mlops-platforms-compared/\",\"da\":\"\",\"h\":0,\"i\":\"valohai.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MLOps Platforms Compared - Valohai\",\"u\":\"https://valohai.com/mlops-platforms-compared/\"},{\"a\":\"Visual Machine Learning and automated features preprocessing: Builtin charts and dashboards: Code notebooks and recipes: Custom web applications and plugins: Collaboration: DEPLOYMENT OPTIONS; ... Dataiku Scores an overall 4.8 out of 5 rating Based on 249 ratings for the DSMLP market, as of March 1, 2022\",\"ae\":null,\"c\":\"https://www.dataiku.com/product/plans-and-features/\",\"d\":\"www.dataiku.com/product/plans-and-features/\",\"da\":\"\",\"h\":0,\"i\":\"www.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Explore Dataiku Plans and Features | Online or Installed\",\"u\":\"https://www.dataiku.com/product/plans-and-features/\"},{\"a\":\"What's the difference between DataRobot, Databricks Lakehouse, Dataiku DSS, and DATAGYM? Compare DataRobot vs. Databricks Lakehouse vs. Dataiku DSS vs. DATAGYM in 2024 by cost, reviews, features, integrations, deployment, target market, support options, trial offers, training options, years in business, region, and more using the chart below.\",\"ae\":null,\"b\":\"/.\\tSlashdot\\tslashdot.org\",\"c\":\"https://slashdot.org/software/comparison/DataRobot-vs-Databricks-vs-Dataiku-DSS-vs-datagym/\",\"d\":\"slashdot.org/software/comparison/DataRobot-vs-Databricks-vs-Dataiku-DSS-vs-datagym/\",\"da\":\"\",\"h\":0,\"i\":\"slashdot.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Compare DataRobot vs. Databricks Lakehouse vs. Dataiku DSS vs. DATAGYM ...\",\"u\":\"https://slashdot.org/software/comparison/DataRobot-vs-Databricks-vs-Dataiku-DSS-vs-datagym/\"},{\"a\":\"Claim Dataiku DSS and update features and information. Compare C3 AI Suite vs. DataRobot vs. Dataiku DSS using this comparison chart. Compare price, features, and reviews of the software side-by-side to make the best choice for your business.\",\"ae\":null,\"b\":\"srcforge\\tSourceForge\\tsourceforge.net\",\"c\":\"https://sourceforge.net/software/compare/C3-AI-Suite-vs-DataRobot-vs-Dataiku-DSS/\",\"d\":\"sourceforge.net/software/compare/C3-AI-Suite-vs-DataRobot-vs-Dataiku-DSS/\",\"da\":\"\",\"h\":0,\"i\":\"sourceforge.net\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"C3 AI Suite vs. DataRobot vs. Dataiku DSS Comparison - SourceForge\",\"u\":\"https://sourceforge.net/software/compare/C3-AI-Suite-vs-DataRobot-vs-Dataiku-DSS/\"},{\"a\":\"Compare DataRobot AI Platform and Dataiku using real user data focused on features, satisfaction, business value, and the vendor relationship. What is Machine Learning Platforms (ML) Software?\",\"ae\":null,\"c\":\"https://www.softwarereviews.com/categories/machine-learning-platforms/compare/datarobot-ai-platform-vs-dataiku\",\"d\":\"www.softwarereviews.com/categories/machine-learning-platforms/compare/datarobot-ai-platform-vs-dataiku\",\"da\":\"\",\"h\":0,\"i\":\"www.softwarereviews.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"DataRobot AI Platform vs Dataiku - Machine Learning Platforms\",\"u\":\"https://www.softwarereviews.com/categories/machine-learning-platforms/compare/datarobot-ai-platform-vs-dataiku\"},{\"a\":\"What's the difference between Amazon SageMaker, DataRobot, and Dataiku DSS? Compare Amazon SageMaker vs. DataRobot vs. Dataiku DSS in 2024 by cost, reviews, features, integrations, deployment, target market, support options, trial offers, training options, years in business, region, and more using the chart below.\",\"ae\":null,\"b\":\"/.\\tSlashdot\\tslashdot.org\",\"c\":\"https://slashdot.org/software/comparison/Amazon-SageMaker-vs-DataRobot-vs-Dataiku-DSS/\",\"d\":\"slashdot.org/software/comparison/Amazon-SageMaker-vs-DataRobot-vs-Dataiku-DSS/\",\"da\":\"\",\"h\":0,\"i\":\"slashdot.org\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Compare Amazon SageMaker vs. DataRobot vs. Dataiku DSS in 2024 - Slashdot\",\"u\":\"https://slashdot.org/software/comparison/Amazon-SageMaker-vs-DataRobot-vs-Dataiku-DSS/\"},{\"a\":\"Compare Analance vs. DataRobot vs. Dataiku DSS using this comparison chart. Compare price, features, and reviews of the software side-by-side to make the best choice for your business.\",\"ae\":null,\"b\":\"srcforge\\tSourceForge\\tsourceforge.net\",\"c\":\"https://sourceforge.net/software/compare/Analance-vs-DataRobot-vs-Dataiku-DSS/\",\"d\":\"sourceforge.net/software/compare/Analance-vs-DataRobot-vs-Dataiku-DSS/\",\"da\":\"\",\"h\":0,\"i\":\"sourceforge.net\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Analance vs. DataRobot vs. Dataiku DSS Comparison - SourceForge\",\"u\":\"https://sourceforge.net/software/compare/Analance-vs-DataRobot-vs-Dataiku-DSS/\"},{\"n\":\"/d.js?q=Dataiku%20vs%20DataRobot%20features&kl=wt-wt&l=wt-wt&p=&s=23&ex=-1&ct=US&sp=0&vqd=4-334935250614046875026454141242803242982\"}]);DDG.duckbar.load('images');DDG.duckbar.load('news');DDG.duckbar.load('videos');DDG.duckbar.loadModule('related_searches', {\"ads\":[],\"query\":\"Dataiku vs DataRobot features\",\"queryEncoded\":\"Dataiku%20vs%20DataRobot%20features\",\"response_type\":\"places\",\"results\":[{\"display_text\":\"dataiku vs datarobot review\",\"text\":\"dataiku vs datarobot review\",\"web_search_url\":\"?q=dataiku%20vs%20datarobot%20review\"},{\"display_text\":\"dataiku vs alteryx\",\"text\":\"dataiku vs alteryx\",\"web_search_url\":\"?q=dataiku%20vs%20alteryx\"},{\"display_text\":\"gartner dataiku reviews\",\"text\":\"gartner dataiku reviews\",\"web_search_url\":\"?q=gartner%20dataiku%20reviews\"},{\"display_text\":\"alteryx vs dataiku knime\",\"text\":\"alteryx vs dataiku knime\",\"web_search_url\":\"?q=alteryx%20vs%20dataiku%20knime\"},{\"display_text\":\"dataiku vs rapidminer\",\"text\":\"dataiku vs rapidminer\",\"web_search_url\":\"?q=dataiku%20vs%20rapidminer\"},{\"display_text\":\"dataiku vs azure ml\",\"text\":\"dataiku vs azure ml\",\"web_search_url\":\"?q=dataiku%20vs%20azure%20ml\"},{\"display_text\":\"sagemaker vs dataiku\",\"text\":\"sagemaker vs dataiku\",\"web_search_url\":\"?q=sagemaker%20vs%20dataiku\"},{\"display_text\":\"dataiku reviews\",\"text\":\"dataiku reviews\",\"web_search_url\":\"?q=dataiku%20reviews\"}],\"vqd\":{\"Dataiku%20vs%20DataRobot%20features\":\"4-334935250614046875026454141242803242982\"}});if (DDG.pageLayout) DDG.pageLayout.initialize({\"mainline\":{\"items\":[[\"ad\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"related_searches\"]]},\"sidebar\":{\"items\":[[\"wikipedia_fathead\"]]}}, { start: 0 });DDG.deep.emit(\"load:completed\");", + "curl-cffi-POST-https://duckduckgo.com-{\"data\": {\"q\": \"Dataiku and DataRobot use cases\"}}": "Dataiku and DataRobot use cases at DuckDuckGo
", + "curl-cffi-GET-https://links.duckduckgo.com/d.js-{\"params\": {\"bing_market\": \"wt-WT\", \"df\": null, \"ex\": \"-1\", \"kl\": \"wt-wt\", \"l\": \"wt-wt\", \"q\": \"Dataiku and DataRobot use cases\", \"s\": \"0\", \"sp\": \"0\", \"vqd\": \"4-60481969350525797892441552954401970387\"}}": "if (DDG.deep && DDG.deep.setUpstream) DDG.deep.setUpstream(\"bingv7aa\");DDG.deep.bn={'ivc':1};if (DDG.pageLayout) DDG.pageLayout.load('a',[{\"a\":\"\\u9ad8\\u7cbe\\u5ea6\\u306a\\u6a5f\\u68b0\\u5b66\\u7fd2\\u30e2\\u30c7\\u30eb\\u3092\\u69cb\\u7bc9\\u3001\\u5b9f\\u88c5\\u3001\\u904b\\u7528\\u3002DataRobot\\u306f\\u793e\\u5185\\u30c7\\u30fc\\u30bf\\u304b\\u3089\\u65b0\\u3057\\u3044\\u4fa1\\u5024\\u3092\\u5275\\u9020\\u3057\\u307e\\u3059. AI\\u3092\\u6d3b\\u7528\\u3057\\u30c7\\u30fc\\u30bf\\u3092\\u5206\\u6790\\u3001\\u5b9f\\u7528\\u7684\\u306a\\u30a4\\u30f3\\u30b5\\u30a4\\u30c8\\u3092\\u660e\\u3089\\u304b\\u306b\\u3002\\u30d3\\u30b8\\u30cd\\u30b9\\u306e\\u8ab2\\u984c\\u3092\\u3088\\u308a\\u65e9\\u304f\\u89e3\\u6c7a\",\"adext\":{\"callout\":{\"t\":\"30-Day Free Trial \\u00b7 Trusted by Fortune 50 \\u00b7 No Vendor Lock-in\",\"tid\":\"6\"},\"filterlinks\":{\"l\":[],\"tid\":\"\"},\"sitelinks\":{\"l\":[{\"snippet\":\"Explore the DataRobot AI Platform Get Started With a 30-Day Trial\",\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=2_trBPli7jgDj1WnqJbnww%3D%3D&rut=d0faee2c8c1aae9ac3a012e21d37352a1181970dce9edeba4107839fbfbf097a&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De81Q_rqdj1ZxH5XXGh4PG6pjVUCUzdB7rGpyykWEihNc_sSp5n%2DJ9jIyTjOSnXg0OUazrpKgDJrNvBOdNa5PjBGtyLGt23nrBAabI6opJXrliWQ4o%2DTyxIsqOeCXqzLOOJ3jJb74k6KEx20zilzwKmzSg3nBop2A9JqsasC17VVDPc3_i3EzPbWeRNS4nhxXWJqBKd55GfhuEOg2RZUbmmuAUhWvM%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZnRyaWFsJTJmJTNmdXRtX21lZGl1bSUzZHNlYXJjaCUyNnV0bV9zb3VyY2UlM2RiaW5nJTI2dXRtX2NhbXBhaWduJTNkRnJlZVRyaWFsMjAyM1dXMDgxNkdQU2FkZXh0JTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDc2YmMwNmFmNTA0NDFjOGVjOGYxNjMwY2FmNGU4ZTVk%26rlid%3D76bc06af50441c8ec8f1630caf4e8e5d&vqd=4-164177780916400746369660096493208330918&iurl=%7B1%7DIG%3D5E053B32922A4B5781ED405D9621559B%26CID%3D0176CEA622686E9D34D1DAA0235D6F30%26ID%3DDevEx%2C5063.1\",\"text\":\"DataRobot Free Trial\"},{\"snippet\":\"Unlock Your AI Success in 2023 Tips on the Path of Value-Driven AI\",\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=2_trBPli7jgDj1WnqJbnww%3D%3D&rut=fdb107a4de6fffdec2bdf43b561b2c63ca700daaef68f0e683547361efbbc2b0&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8%2DT0j3GTQEgr%2DmtHPM1LzNzVUCUyRxvVKYHe6LbNa2mmCfCZh3Ept1NM%2DP%2DM1AAluh_OL3VQw_FWI0A3YxC3pzzqthf3gpxan_Lv7CjKenge%2DwMYUz3bRFoFyHtQBMdgqv6T7gMGfyYwN3UCj6FNYwVVn9UNN0h1dIQanHNB6Ya9gRrPBACknA8qtsf6A2oUG1xhq7AOF98NzGphnfQ_38fySnRU%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZnJlc291cmNlcyUyZmFpc3VjY2VzczIwMjMlMmYlM2Z1dG1fbWVkaXVtJTNkc2VhcmNoJTI2dXRtX3NvdXJjZSUzZGJpbmclMjZ1dG1fY2FtcGFpZ24lM2RDb250ZW50MTBLZXlzdG9BSVN1Y2Nlc3MyMDIzV1cwNTIyR1BTYWRleHQlMjZ1dG1fdGVybSUzZGRhdGFyb2JvdCUyNnV0bV9jb250ZW50JTNkYWRfZXh0JTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZGQzNmQ2MzlkMmFlNTEwMTM3ZTIwMDYzZWQ1ZWY3M2Yz%26rlid%3Dd36d639d2ae510137e20063ed5ef73f3&vqd=4-117927704271333462986714580056949079639&iurl=%7B1%7DIG%3D5E053B32922A4B5781ED405D9621559B%26CID%3D0176CEA622686E9D34D1DAA0235D6F30%26ID%3DDevEx%2C5065.1\",\"text\":\"10 Keys to AI Success\"},{\"snippet\":\"Our Platform Includes Four Fully Integrated Products. Read More.\",\"targetUrl\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=2_trBPli7jgDj1WnqJbnww%3D%3D&rut=4f06bd3312172b8e61d65ee2626dea6e26d941c3a16aa546b4e11b79e8bf027f&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8885tVmNmhi65Jmp3f2wYSzVUCUyFey1LCmrSNpGfkWzQnoC7QIbU3ztthJ%2DqKpgCmRfxudhbLK927YN84jvZlV2zTKo9DOULVj5wB8mcGXy_F42SnsrO1jZpY9NnMnzqMYPb5xZTTdgrTO1_w3Bgpd0e0VzO81_O3%2Dfo2z4UiLuVETFVqfACqR6NEwz0yfjzJe6ED9tvi_gPDiUL9iWATrNIrsw%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZnByb2R1Y3QlMmYlM2ZjYW1wYWlnbmlkJTNkNTMwNzA4MDk5JTI2YWRncm91cGlkJTNkMTM1MDIwMjc3NDIxNzY5OCUyNmFkaWQlM2QlMjZtc2Nsa2lkJTNkY2U4NzQ1ZDViODBlMTJmNjQ2N2QyMDc2NDcwNDY2YjI%26rlid%3Dce8745d5b80e12f6467d2076470466b2&vqd=4-169069202740993895017985472268973083525&iurl=%7B1%7DIG%3D5E053B32922A4B5781ED405D9621559B%26CID%3D0176CEA622686E9D34D1DAA0235D6F30%26ID%3DDevEx%2C5067.1\",\"text\":\"Product Overview\"}],\"tid\":\"7\\t9[8]\\t11[10]\\t13[12]\",\"type\":\"EnhancedSiteLink\"},\"tid\":\"1\"},\"ae\":{\"callout\":[\"30-Day Free Trial \\u00b7 Trusted by Fortune 50 \\u00b7 No Vendor Lock-in\"]},\"c\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=2_trBPli7jgDj1WnqJbnww%3D%3D&rut=e744d99a8df00b24df71f821ad4d1332080aa03267e50f0e988d284f58d9d2ef&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8tT9soRYLZabP1ukFkRsgNzVUCUzl89Y8xEqpxoqHqIlCI5wWbydNnN_PoAKHAa2Vsio83mXA_ax16t6rJ7XGkBv0Cg7_D1eg2QAuJgPKEam4VWI3rW40B03r1p11ZXN1Gd1847Vj05bAnJnPfgVyC8ZzFQxLxONmOI0Hg182z2bZUVII26BUAlUHaVZ7O_9FEXLJWw%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZmpwJTJmbHAlMmZhaS1mb3ItYnVzaW5lc3MlMmYlM2Z1dG1fbWVkaXVtJTNkc2VhcmNoJTI2dXRtX3NvdXJjZSUzZGJpbmclMjZ1dG1fY2FtcGFpZ24lM2RERU1PMjAyM0FsbFByb2R1Y3RzSlAwNjI2QlBTJTI2dXRtX3Rlcm0lM2RkYXRhcm9ib3QlMjZ1dG1fY29udGVudCUzZERSX2JyYW5kZWRfcnNhJTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDA2MTIwYzhmMTAxNzEwYTZiNmRiNjkyY2VmMWRiOTY1%26rlid%3D06120c8f101710a6b6db692cef1db965&vqd=4-91027509783546726889708070523412001433&iurl=%7B1%7DIG%3D5E053B32922A4B5781ED405D9621559B%26CID%3D0176CEA622686E9D34D1DAA0235D6F30%26ID%3DDevEx%2C5058.1\",\"d\":\"datarobot.com\",\"h\":0,\"i\":\"\",\"k\":0,\"m\":0,\"o\":\"\",\"p\":1,\"relevancy\":{\"abstract\":\"%E9%AB%98%E7%B2%BE%E5%BA%A6%E3%81%AA%E6%A9%9F%E6%A2%B0%E5%AD%A6%E7%BF%92%E3%83%A2%E3%83%87%E3%83%AB%E3%82%92%E6%A7%8B%E7%AF%89%E3%80%81%E5%AE%9F%E8%A3%85%E3%80%81%E9%81%8B%E7%94%A8%E3%80%82%3Cb%3EDataRobot%3C%2Fb%3E%E3%81%AF%E7%A4%BE%E5%86%85%E3%83%87%E3%83%BC%E3%82%BF%E3%81%8B%E3%82%89%E6%96%B0%E3%81%97%E3%81%84%E4%BE%A1%E5%80%A4%E3%82%92%E5%89%B5%E9%80%A0%E3%81%97%E3%81%BE%E3%81%99.%20AI%E3%82%92%E6%B4%BB%E7%94%A8%E3%81%97%E3%83%87%E3%83%BC%E3%82%BF%E3%82%92%E5%88%86%E6%9E%90%E3%80%81%E5%AE%9F%E7%94%A8%E7%9A%84%E3%81%AA%E3%82%A4%E3%83%B3%E3%82%B5%E3%82%A4%E3%83%88%E3%82%92%E6%98%8E%E3%82%89%E3%81%8B%E3%81%AB%E3%80%82%E3%83%93%E3%82%B8%E3%83%8D%E3%82%B9%E3%81%AE%E8%AA%B2%E9%A1%8C%E3%82%92%E3%82%88%E3%82%8A%E6%97%A9%E3%81%8F%E8%A7%A3%E6%B1%BA\",\"adx_name\":\"none\",\"is_good_v10\":0,\"organic_ranks\":[5,11,12,13],\"q\":\"Dataiku%20and%20DataRobot%20use%20cases\",\"q_words\":4,\"q_words_fuzzy\":0.25,\"q_words_in_ad\":1,\"root_domain\":\"datarobot.com\",\"start\":\"0\",\"title\":\"%E3%83%93%E3%83%83%E3%82%B0%E3%83%87%E3%83%BC%E3%82%BF%E5%88%86%E6%9E%90%E3%82%92%E9%AB%98%E9%80%9F%E5%8C%96%20%2D%20%E3%83%87%E3%83%BC%E3%82%BF%E3%81%8B%E3%82%89%E6%96%B0%E3%81%97%E3%81%84%E4%BE%A1%E5%80%A4%E3%82%92\"},\"s\":\"bingv7aa\",\"t\":\"\\u30d3\\u30c3\\u30b0\\u30c7\\u30fc\\u30bf\\u5206\\u6790\\u3092\\u9ad8\\u901f\\u5316 - \\u30c7\\u30fc\\u30bf\\u304b\\u3089\\u65b0\\u3057\\u3044\\u4fa1\\u5024\\u3092\",\"tid\":\"1,6,7,9[8],11[10],13[12]\",\"u\":\"https://duckduckgo.com/y.js?ad_domain=datarobot.com&ad_provider=bingv7aa&ad_type=txad&eddgt=2_trBPli7jgDj1WnqJbnww%3D%3D&rut=e744d99a8df00b24df71f821ad4d1332080aa03267e50f0e988d284f58d9d2ef&u3=https%3A%2F%2Fwww.bing.com%2Faclick%3Fld%3De8tT9soRYLZabP1ukFkRsgNzVUCUzl89Y8xEqpxoqHqIlCI5wWbydNnN_PoAKHAa2Vsio83mXA_ax16t6rJ7XGkBv0Cg7_D1eg2QAuJgPKEam4VWI3rW40B03r1p11ZXN1Gd1847Vj05bAnJnPfgVyC8ZzFQxLxONmOI0Hg182z2bZUVII26BUAlUHaVZ7O_9FEXLJWw%26u%3DaHR0cHMlM2ElMmYlMmZ3d3cuZGF0YXJvYm90LmNvbSUyZmpwJTJmbHAlMmZhaS1mb3ItYnVzaW5lc3MlMmYlM2Z1dG1fbWVkaXVtJTNkc2VhcmNoJTI2dXRtX3NvdXJjZSUzZGJpbmclMjZ1dG1fY2FtcGFpZ24lM2RERU1PMjAyM0FsbFByb2R1Y3RzSlAwNjI2QlBTJTI2dXRtX3Rlcm0lM2RkYXRhcm9ib3QlMjZ1dG1fY29udGVudCUzZERSX2JyYW5kZWRfcnNhJTI2Y2FtcGFpZ25pZCUzZDUzMDcwODA5OSUyNmFkZ3JvdXBpZCUzZDEzNTAyMDI3NzQyMTc2OTglMjZhZGlkJTNkJTI2bXNjbGtpZCUzZDA2MTIwYzhmMTAxNzEwYTZiNmRiNjkyY2VmMWRiOTY1%26rlid%3D06120c8f101710a6b6db692cef1db965&vqd=4-91027509783546726889708070523412001433&iurl=%7B1%7DIG%3D5E053B32922A4B5781ED405D9621559B%26CID%3D0176CEA622686E9D34D1DAA0235D6F30%26ID%3DDevEx%2C5058.1\"}], {\"page_load_url\":\"https://duckduckgo.com/y.js?ifu=%7B3%7Dappid%3D055AAD1BA669BEB8B048128DC89A107C678B527B%26rguid%3D309794dc72f748f6a2b95ce5c34fbcec&iurl=%7B2%7DIG%3D5E053B32922A4B5781ED405D9621559B%26CID%3D0176CEA622686E9D34D1DAA0235D6F30%26Type%3DEvent.CPT%26DATA%3D0\",\"visibility_url\":\"https://duckduckgo.com/y.js?ivu=%7B4%7Dtype%3Dmv%26reqver%3D1.0%26rg%3D309794dc72f748f6a2b95ce5c34fbcec\"});DDG.deep.signalSummary = \"\";DDG.inject('DDG.Data.languages.resultLanguages', {\"en\":[\"https://knowledge.dataiku.com/latest/use-cases/index.html\",\"https://community.dataiku.com/t5/Dataiku-Use-Cases-Success/tkb-p/use-cases\",\"https://www.datarevenue.com/en-blog/ml-platforms-dataiku-vs-alteryx-vs-sagemaker\",\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/compare/dataiku-vs-datarobot\",\"https://community.dataiku.com/t5/General-Discussion/Dataiku-vs-DataRobot/m-p/9315\",\"https://www.datarobot.com/use-cases/\",\"https://academy.dataiku.com/page/use-cases\",\"https://www.trustradius.com/compare-products/dataiku-dss-vs-datarobot\",\"https://www.g2.com/compare/datarobot-vs-dataiku-dss\",\"https://www.linkedin.com/pulse/managed-machine-learning-platforms-comparative-analysis/\",\"https://londondataconsulting.medium.com/dataiku-what-is-it-how-to-use-it-ultimate-guide-2023-47602c85a48b\",\"https://docs.datarobot.com/en/docs/api/guide/common-case/index.html\",\"https://www.datarobot.com/blog/introducing-the-datarobot-use-case-value-tracker/\",\"https://docs.datarobot.com/en/docs/workbench/wb-usecase/wb-build-usecase.html\",\"https://blog.dataiku.com/topic/use-cases-projects\",\"https://valohai.com/mlops-platforms-compared/\",\"https://www.capterra.com/machine-learning-software/compare/142192-179303/Data-Science-Studio-DSS-vs-DataRobot\",\"https://pages.dataiku.com/experience-a-dataiku-demo\",\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\",\"https://www.dataiku.com/stories/\",\"https://www.dataiku.com/\",\"https://techcrunch.com/2022/12/13/ai-and-analytics-platform-dataiku-raises-200m-at-a-reduced-valuation/\",\"https://www.globenewswire.com/news-release/2022/11/17/2558152/0/en/Ben-Taylor-Joins-Dataiku-as-Chief-AI-Strategist.html\"]});DDG.deep.pageLayoutSummary = \"a1w4v1w19,w1\";DDG.inject('DDG.Data.languages.adLanguages', {});if (DDG.pageLayout) DDG.pageLayout.load('d',[{\"a\":\"Use Cases - Dataiku Knowledge Base Use Cases # These use cases allow you to practice what you've learned by building simplified, but complete use cases in Dataiku. Topics # Data Preparation Use Cases Classification Use Cases Clustering Use Cases Plugin Use Cases\",\"ae\":null,\"c\":\"https://knowledge.dataiku.com/latest/use-cases/index.html\",\"d\":\"knowledge.dataiku.com/latest/use-cases/index.html\",\"da\":\"\",\"h\":0,\"i\":\"knowledge.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Use Cases - Dataiku Knowledge Base\",\"u\":\"https://knowledge.dataiku.com/latest/use-cases/index.html\"},{\"a\":\"Community Dataiku Use Cases & Success Stories \\u26a0\\ufe0f Discover pioneering Dataiku use cases and success stories shared by customers, partners, academics, and nonprofits participating in the Dataiku Frontrunner Awards. Use the following labels to filter submissions by industry:\",\"ae\":null,\"c\":\"https://community.dataiku.com/t5/Dataiku-Use-Cases-Success/tkb-p/use-cases\",\"d\":\"community.dataiku.com/t5/Dataiku-Use-Cases-Success/tkb-p/use-cases\",\"da\":\"\",\"h\":0,\"i\":\"community.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku Use Cases & Success Stories - Dataiku Community\",\"u\":\"https://community.dataiku.com/t5/Dataiku-Use-Cases-Success/tkb-p/use-cases\"},{\"a\":\"Dataiku is a cross-platform desktop application that includes a broad range of tools, such as notebooks (similar to Jupyter Notebook), workflow management (similar to Apache Airflow), and automated machine learning. In general, Dataiku aims to replace many of your existing tools rather than to integrate with them.\",\"ae\":null,\"c\":\"https://www.datarevenue.com/en-blog/ml-platforms-dataiku-vs-alteryx-vs-sagemaker\",\"d\":\"www.datarevenue.com/en-blog/ml-platforms-dataiku-vs-alteryx-vs-sagemaker\",\"da\":\"\",\"h\":0,\"i\":\"www.datarevenue.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"ML Platforms: Dataiku vs. Alteryx vs. Sagemaker vs. Datarobot\",\"u\":\"https://www.datarevenue.com/en-blog/ml-platforms-dataiku-vs-alteryx-vs-sagemaker\"},{\"a\":\"Dataiku has a rating of 4.8 stars with 504 reviews. DataRobot has a rating of 4.6 stars with 508 reviews. See side-by-side comparisons of product capabilities, customer experience, pros and cons, and reviewer demographics to find the best fit for your organization. See more companies in the Data Science and Machine Learning Platforms market. PDF.\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/compare/dataiku-vs-datarobot\",\"d\":\"www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/compare/dataiku-vs-datarobot\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku vs DataRobot 2024 | Gartner Peer Insights\",\"u\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/compare/dataiku-vs-datarobot\"},{\"a\":\"In my humble opinion DSS is a more a 'toolbox', where as DataRobot is an autoML platform. DataRobot is really good at what it does - if you have non-technical team who want to drop in data and leave everything to autoML then this may be the option for them.\",\"ae\":null,\"c\":\"https://community.dataiku.com/t5/General-Discussion/Dataiku-vs-DataRobot/m-p/9315\",\"d\":\"community.dataiku.com/t5/General-Discussion/Dataiku-vs-DataRobot/m-p/9315\",\"da\":\"\",\"h\":0,\"i\":\"community.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Solved: Dataiku vs DataRobot - Dataiku Community\",\"u\":\"https://community.dataiku.com/t5/General-Discussion/Dataiku-vs-DataRobot/m-p/9315\"},{\"a\":\"Use cases AI Use Cases AI-driven organizations around the world use DataRobot to solve their most pressing business problems. Build with Free Trial Recent Popular Filters Ready to Get Started? See how a value-driven approach to AI can accelerate time to impact. Start Free Trial\",\"ae\":null,\"c\":\"https://www.datarobot.com/use-cases/\",\"d\":\"www.datarobot.com/use-cases/\",\"da\":\"\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Machine Learning Use Cases | DataRobot AI Platform\",\"u\":\"https://www.datarobot.com/use-cases/\"},{\"a\":\"With Dataiku's AI Prepare assistant, you can work smarter, not harder. Simply describe the transformation you want to apply in natural language and the AI assistant automatically generates the necessary data preparation steps. The ability to modify both your prompt and the resulting steps means you can prepare data faster than ever, yet still ...\",\"ae\":null,\"c\":\"https://academy.dataiku.com/page/use-cases\",\"d\":\"academy.dataiku.com/page/use-cases\",\"da\":\"\",\"h\":0,\"i\":\"academy.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Use Cases - Dataiku\",\"u\":\"https://academy.dataiku.com/page/use-cases\"},{\"a\":\"84 Reviews and Ratings Path to AI Success Compare Dataiku DSS vs DataRobot. 103 verified user reviews and ratings of features, pros, cons, pricing, support and more.\",\"ae\":null,\"c\":\"https://www.trustradius.com/compare-products/dataiku-dss-vs-datarobot\",\"d\":\"www.trustradius.com/compare-products/dataiku-dss-vs-datarobot\",\"da\":\"\",\"h\":0,\"i\":\"www.trustradius.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku DSS vs DataRobot | TrustRadius\",\"u\":\"https://www.trustradius.com/compare-products/dataiku-dss-vs-datarobot\"},{\"a\":\"side-by-side comparison of DataRobot vs. Dataiku DSS. based on preference data from user reviews. DataRobot rates 4.4/5 stars with 26 reviews. By contrast, Dataiku DSS rates 4.3/5 stars with 36 reviews. Each product's score is calculated with real-time data from verified user reviews, to help you make the best choice between these two options ...\",\"ae\":null,\"c\":\"https://www.g2.com/compare/datarobot-vs-dataiku-dss\",\"d\":\"www.g2.com/compare/datarobot-vs-dataiku-dss\",\"da\":\"\",\"h\":0,\"i\":\"www.g2.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Compare DataRobot vs. Dataiku DSS | G2\",\"u\":\"https://www.g2.com/compare/datarobot-vs-dataiku-dss\"},{\"a\":\"Use case: Choose Datarobot if you have data stored in spreadsheets and are seeking a platform that is the simplest, albeit one with limited flexibility, ... Dataiku vs. Datarobot .\",\"ae\":null,\"b\":\"li\\tLinkedIn\\twww.linkedin.com\",\"c\":\"https://www.linkedin.com/pulse/managed-machine-learning-platforms-comparative-analysis/\",\"d\":\"www.linkedin.com/pulse/managed-machine-learning-platforms-comparative-analysis/\",\"da\":\"\",\"e\":\"2023-08-11T00:00:00.0000000\",\"h\":0,\"i\":\"www.linkedin.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Managed Machine Learning Platforms: A Comparative Analysis - LinkedIn\",\"u\":\"https://www.linkedin.com/pulse/managed-machine-learning-platforms-comparative-analysis/\"},{\"a\":\"Jan 11, 2023 Dataiku is an artificial intelligence platform created in France in 2013. It has since become one of the world's benchmarks for data science and machine learning studios. What is...\",\"ae\":null,\"c\":\"https://londondataconsulting.medium.com/dataiku-what-is-it-how-to-use-it-ultimate-guide-2023-47602c85a48b\",\"d\":\"londondataconsulting.medium.com/dataiku-what-is-it-how-to-use-it-ultimate-guide-2023-47602c85a48b\",\"da\":\"translations\",\"e\":\"2023-01-11T00:00:00.0000000\",\"h\":0,\"i\":\"londondataconsulting.medium.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku: What is it? How to use it? Ultimate Guide 2023\",\"u\":\"https://londondataconsulting.medium.com/dataiku-what-is-it-how-to-use-it-ultimate-guide-2023-47602c85a48b\"},{\"a\":\"Use cases for version 2.x. Notebooks for uses cases that use methods for 2.x versions of DataRobot's Python client. Measure price elasticity of demand. A use case to identify relationships between price and demand, maximize revenue by properly pricing products, and monitor price elasticities for changes in price and demand. Insurance claim triage.\",\"ae\":null,\"c\":\"https://docs.datarobot.com/en/docs/api/guide/common-case/index.html\",\"d\":\"docs.datarobot.com/en/docs/api/guide/common-case/index.html\",\"da\":\"\",\"h\":0,\"i\":\"docs.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Common use cases: DataRobot docs - DataRobot AI Platform\",\"u\":\"https://docs.datarobot.com/en/docs/api/guide/common-case/index.html\"},{\"a\":\"With the Use Case Value Tracker, you can manage the project lifecycle and understand the value associated with each step. It also enables you to associate and organize all your DataRobot artifacts (e.g., datasets, models, deployments, applications, etc.) around a given use case for a holistic view. In addition to the project management aspects ...\",\"ae\":null,\"c\":\"https://www.datarobot.com/blog/introducing-the-datarobot-use-case-value-tracker/\",\"d\":\"www.datarobot.com/blog/introducing-the-datarobot-use-case-value-tracker/\",\"da\":\"\",\"h\":0,\"i\":\"www.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Introducing the DataRobot Use Case Value Tracker\",\"u\":\"https://www.datarobot.com/blog/introducing-the-datarobot-use-case-value-tracker/\"},{\"a\":\"Use Cases are folder-like containers inside of DataRobot Workbench that allow you to group everything related to solving a specific business problem\\u2014datasets, models, experiments, No-Code AI Apps, and notebooks\\u2014inside of a single, manageable entity. You can share whole Use Cases as well as the individual assets they contain.\",\"ae\":null,\"c\":\"https://docs.datarobot.com/en/docs/workbench/wb-usecase/wb-build-usecase.html\",\"d\":\"docs.datarobot.com/en/docs/workbench/wb-usecase/wb-build-usecase.html\",\"da\":\"\",\"e\":\"2023-09-15T00:00:00.0000000\",\"h\":0,\"i\":\"docs.datarobot.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Use Cases: DataRobot docs\",\"u\":\"https://docs.datarobot.com/en/docs/workbench/wb-usecase/wb-build-usecase.html\"},{\"a\":\"January 2, 2024 Use Cases & Projects, Featured Sophie Dionnet Leveraging AI to Cut Costs December 29, 2023 Data Basics, Featured\",\"ae\":null,\"c\":\"https://blog.dataiku.com/topic/use-cases-projects\",\"d\":\"blog.dataiku.com/topic/use-cases-projects\",\"da\":\"\",\"h\":0,\"i\":\"blog.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Blog - Dataiku | Use Cases & Projects\",\"u\":\"https://blog.dataiku.com/topic/use-cases-projects\"},{\"a\":\"The platforms we've chosen for our analysis are ClearML, cnvrg.io, Dataiku, Datarobot, Iguazio, Sagemaker, Seldon and Valohai from the managed side, and Flyte, Kubeflow, MLflow and Metaflow from the open-source side. This is by no means an exhaustive list of all the MLOps tools out there.\",\"ae\":null,\"c\":\"https://valohai.com/mlops-platforms-compared/\",\"d\":\"valohai.com/mlops-platforms-compared/\",\"da\":\"\",\"h\":0,\"i\":\"valohai.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"MLOps Platforms Compared - Valohai\",\"u\":\"https://valohai.com/mlops-platforms-compared/\"},{\"a\":\"DataRobot. DSS is for all companies, whatever their expertise, industry or size, that want to create their own data-driven strategic advantages by transforming their raw data into business impacting predictions. Cloud based machine learning platform which helps enterprises scale data science capabilities through deploying machine learning ...\",\"ae\":null,\"c\":\"https://www.capterra.com/machine-learning-software/compare/142192-179303/Data-Science-Studio-DSS-vs-DataRobot\",\"d\":\"www.capterra.com/machine-learning-software/compare/142192-179303/Data-Science-Studio-DSS-vs-DataRobot\",\"da\":\"translations\",\"h\":0,\"i\":\"www.capterra.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Compare Dataiku vs DataRobot 2024 | Capterra\",\"u\":\"https://www.capterra.com/machine-learning-software/compare/142192-179303/Data-Science-Studio-DSS-vs-DataRobot\"},{\"a\":\"For Every Industry & Use Case. Organizations that use Dataiku elevate their people (whether technical and working in code or on the business side and low- or no-code) to extraordinary, arming them with the ability to make better day-to-day decisions with data across: Banking & Insurance. Pharmaceuticals. Manufacturing. Telecommunications.\",\"ae\":null,\"c\":\"https://pages.dataiku.com/experience-a-dataiku-demo\",\"d\":\"pages.dataiku.com/experience-a-dataiku-demo\",\"da\":\"\",\"h\":0,\"i\":\"pages.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Check Out This Dataiku Demo\",\"u\":\"https://pages.dataiku.com/experience-a-dataiku-demo\"},{\"a\":\"4 Star 24% 3 Star 1% 2 Star 0% 1 Star 0% Distribution based on 504 ratings Customer Experience Evaluation & Contracting 4.6 Integration & Deployment 4.7 Service & Support 4.8 Product Capabilities 4.8 FREE View and Download Peer Insights About Dataiku\",\"ae\":null,\"c\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\",\"d\":\"www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\",\"da\":\"\",\"h\":0,\"i\":\"www.gartner.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku Reviews, Ratings & Features 2024 | Gartner Peer Insights\",\"u\":\"https://www.gartner.com/reviews/market/data-science-and-machine-learning-platforms/vendor/dataiku/product/dataiku\"},{\"a\":\"Read The Full Case Study U.S. Venture + Dataiku: Upskilling Analysts to Save Thousands of Hours The Data and Analytics team at U.S. Venture was built to usher the company into the future of data science and AI.\",\"ae\":null,\"c\":\"https://www.dataiku.com/stories/\",\"d\":\"www.dataiku.com/stories/\",\"da\":\"\",\"h\":0,\"i\":\"www.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Stories | Dataiku\",\"u\":\"https://www.dataiku.com/stories/\"},{\"a\":\"MLOps Deploy, monitor, and maintain machine learning models, all in a single platform. Explore the Capability Collaboration With Dataiku, teams can move beyond the lab and build real and safe Generative AI applications at enterprise scale. Explore the Capability Governance\",\"ae\":null,\"c\":\"https://www.dataiku.com/\",\"d\":\"www.dataiku.com\",\"da\":\"\",\"h\":0,\"i\":\"www.dataiku.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Dataiku | Everyday AI, Extraordinary People\",\"u\":\"https://www.dataiku.com/\"},{\"a\":\"The company today announced that it raised $200 million in a Series F round led by Wellington Management at a $3.7 billion valuation, down from the $4.6 billion that Dataiku received in August ...\",\"ae\":null,\"b\":\"tc\\tTechcrunch\\ttechcrunch.com\",\"c\":\"https://techcrunch.com/2022/12/13/ai-and-analytics-platform-dataiku-raises-200m-at-a-reduced-valuation/\",\"d\":\"techcrunch.com/2022/12/13/ai-and-analytics-platform-dataiku-raises-200m-at-a-reduced-valuation/\",\"da\":\"translations\",\"e\":\"2022-12-13T17:10:00.0000000\",\"h\":0,\"i\":\"techcrunch.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"AI and analytics platform Dataiku raises $200M at a reduced valuation\",\"u\":\"https://techcrunch.com/2022/12/13/ai-and-analytics-platform-dataiku-raises-200m-at-a-reduced-valuation/\"},{\"a\":\"Today, more than 500 companies worldwide use Dataiku to integrate and streamline their use of data, analytics, and AI, driving diverse use cases from fraud detection and customer churn prevention ...\",\"ae\":null,\"c\":\"https://www.globenewswire.com/news-release/2022/11/17/2558152/0/en/Ben-Taylor-Joins-Dataiku-as-Chief-AI-Strategist.html\",\"d\":\"www.globenewswire.com/news-release/2022/11/17/2558152/0/en/Ben-Taylor-Joins-Dataiku-as-Chief-AI-Strategist.html\",\"da\":\"translations\",\"e\":\"2022-11-17T13:00:00.0000000\",\"h\":0,\"i\":\"www.globenewswire.com\",\"k\":null,\"m\":0,\"o\":0,\"p\":0,\"s\":\"bingv7aa\",\"t\":\"Ben Taylor Joins Dataiku as Chief AI Strategist - GlobeNewswire\",\"u\":\"https://www.globenewswire.com/news-release/2022/11/17/2558152/0/en/Ben-Taylor-Joins-Dataiku-as-Chief-AI-Strategist.html\"},{\"n\":\"/d.js?q=Dataiku%20and%20DataRobot%20use%20cases&kl=wt-wt&l=wt-wt&p=&s=23&ex=-1&ct=US&sp=0&vqd=4-60481969350525797892441552954401970387\"}]);DDG.duckbar.load('images');DDG.duckbar.load('news');DDG.duckbar.load('videos', {\"ads\":[],\"query\":\"Dataiku and DataRobot use cases\",\"queryEncoded\":\"Dataiku%20and%20DataRobot%20use%20cases\",\"response_type\":\"places\",\"results\":[{\"content\":\"https://www.youtube.com/watch?v=ryZRRIjQ5Z8\",\"description\":\"If you're a code-first data practitioner, Dataiku helps you efficiently build high quality data pipelines and models in a number of ways. CHECK OUT DATAIKU: https://bit.ly/36XBlpK EGG ON AIR: https://bit.ly/37GhXMY BRIGHTTALK WEBINARS: https://bit.ly/33TIRjn DATA SCIENCE PIONEERS DOCUMENTARY: https://bit.ly/36V3rBF PARTNER ECOSYSTEM: https ...\",\"duration\":\"10:43\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/ryZRRIjQ5Z8?autoplay=1\",\"image_token\":\"8a4abca8613c6680a108591849e5d7b13b86111004ae004898a7f059b64c8355\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.WoendyuZJ9qxql-n6jit5AEsDh&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.WoendyuZJ9qxql-n6jit5AEsDh&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM1.cmvppfhHVUeE4Q_1684256861&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.WoendyuZJ9qxql-n6jit5AEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2021-06-08T21:15:02.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":12391},\"title\":\"Dataiku Demo for Data Scientists and Coders\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=jKL_I0SCl_E\",\"description\":\"This video showcases the Clinical Trial Explorer use case from the Dataiku Generative AI Use Case Collection. Learn more about Dataiku for Generative AI | https://www.dataiku.com/product/generative-ai/ Explore more Generative AI use cases | https://experience.dataiku.com/generative-ai To explore more about Dataiku, check out the rest of our ...\",\"duration\":\"1:50\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/jKL_I0SCl_E?autoplay=1\",\"image_token\":\"7b19602fe6d9b761aa3cc138448cc632ddbed31da3abf2687f36705f5945973d\",\"images\":{\"large\":\"https://tse3.mm.bing.net/th?id=OVP.wfgHp53woiVosZ37-1HtnwEsDh&pid=Api\",\"medium\":\"https://tse3.mm.bing.net/th?id=OVP.wfgHp53woiVosZ37-1HtnwEsDh&pid=Api\",\"motion\":\"https://tse3.mm.bing.net/th?id=OM2.ZX_yq0xmyCGZBg_1696372683&pid=Api\",\"small\":\"https://tse3.mm.bing.net/th?id=OVP.wfgHp53woiVosZ37-1HtnwEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-06-22T12:19:00.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":150},\"title\":\"Clinical Trial Explorer\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=lASesA4gNFI\",\"description\":\"This video showcases the CO2 Forecast Analyzer use case from the Dataiku Generative AI Use Case Collection. Learn more about Dataiku for Generative AI | https://www.dataiku.com/product/generative-ai/ Explore more Generative AI use cases | https://experience.dataiku.com/generative-ai To explore more about Dataiku, check out the rest of our ...\",\"duration\":\"1:50\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/lASesA4gNFI?autoplay=1\",\"image_token\":\"a09328adca01a788783d759561c2f9c9d4d214e5a26f1462d2b6b69f21a2d478\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.ZhQI7z-IMlcVnyeMJuGlAQEsDh&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.ZhQI7z-IMlcVnyeMJuGlAQEsDh&pid=Api\",\"motion\":\"\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.ZhQI7z-IMlcVnyeMJuGlAQEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-06-22T12:16:20.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":49},\"title\":\"CO2 Forecast Analyzer\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=RecpD6Vtzj4\",\"description\":\"This video showcases the LLM-Enhanced ESG Document Intelligence use case from the Dataiku Generative AI Use Case Collection. Learn more about Dataiku for Generative AI | https://www.dataiku.com/product/generative-ai/ Explore more Generative AI use cases | https://experience.dataiku.com/generative-ai To explore more about Dataiku, check out the ...\",\"duration\":\"1:20\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/RecpD6Vtzj4?autoplay=1\",\"image_token\":\"6f797accb167e2e6ff7265e35116cdeb9f1c641b1df47932d9597b61b0108614\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.bm4gAiJOOmKV7uup6LU9pgEsDh&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.bm4gAiJOOmKV7uup6LU9pgEsDh&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM1.M8WXwCQ79nrqEA_1691502936&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.bm4gAiJOOmKV7uup6LU9pgEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-06-22T12:30:00.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":382},\"title\":\"LLM-Enhanced ESG Document Intelligence\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=zLW0TkJoHLw\",\"description\":\"This video showcases the Demand Forecast Analyzer use case from the Dataiku Generative AI Use Case Collection. Learn more about Dataiku for Generative AI | https://www.dataiku.com/product/generative-ai/ Explore more Generative AI use cases | https://experience.dataiku.com/generative-ai To explore more about Dataiku, check out the rest of our ...\",\"duration\":\"1:42\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/zLW0TkJoHLw?autoplay=1\",\"image_token\":\"524eb9572bf9342b859509285d39ec4661fc572cb1452307acc5341b56bab921\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.yIekQ2cMUesOPJTfsYIZzQHgFo&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.yIekQ2cMUesOPJTfsYIZzQHgFo&pid=Api\",\"motion\":\"\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.yIekQ2cMUesOPJTfsYIZzQHgFo&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-06-22T12:15:02.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":4},\"title\":\"LLM-Enhanced Demand Forecast\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=L-Yys0fzuVY\",\"description\":\"This video showcases the Production Quality Data Explorer use case from the Dataiku Generative AI Use Case Collection. Learn more about Dataiku for Generative AI | https://www.dataiku.com/product/generative-ai/ Explore more Generative AI use cases | https://experience.dataiku.com/generative-ai To explore more about Dataiku, check out the rest ...\",\"duration\":\"1:47\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/L-Yys0fzuVY?autoplay=1\",\"image_token\":\"82924713be1dba83d67124fcaa6cc6afd163900a0c40f25fcf6c144ed0e36536\",\"images\":{\"large\":\"https://tse4.mm.bing.net/th?id=OVP.teiC0mX9nKCbH8qeo52udwEsDh&pid=Api\",\"medium\":\"https://tse4.mm.bing.net/th?id=OVP.teiC0mX9nKCbH8qeo52udwEsDh&pid=Api\",\"motion\":\"https://tse4.mm.bing.net/th?id=OM2.IwRaoLRWcQXzag_1691419996&pid=Api\",\"small\":\"https://tse4.mm.bing.net/th?id=OVP.teiC0mX9nKCbH8qeo52udwEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-06-22T12:28:29.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":175},\"title\":\"Production Quality Data Explorer\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=FluiuHuaU8A\",\"description\":\"In this breakout session of Dataiku's Product Days 2021, you will see a demo of Dataiku's Data Science Studio, the centralized, collaborative, and end-to-end platform for data science in the enterprise. CHECK OUT DATAIKU: https://bit.ly/36XBlpK EGG ON AIR: https://bit.ly/37GhXMY BRIGHTTALK WEBINARS: https://bit.ly/33TIRjn DATA SCIENCE PIONEERS ...\",\"duration\":\"13:50\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/FluiuHuaU8A?autoplay=1\",\"image_token\":\"2943fa8c1580f2936fc11667d670c0b827b94ff3d16b897f8b5ef2e2426487b3\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.RIM-ftwDZjYP58RimJfgwwEsDh&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.RIM-ftwDZjYP58RimJfgwwEsDh&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM1.MIQ7BoQz1MVkNw_1662248868&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.RIM-ftwDZjYP58RimJfgwwEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2021-07-08T15:56:22.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":3844},\"title\":\"Introduction to Dataiku Data Science | Product Days 2021\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=6TEU5JboP7k\",\"description\":\"This video showcases the LLM-Enhanced Next Best Offer use case from the Dataiku Generative AI Use Case Collection. Learn more about Dataiku for Generative AI | https://www.dataiku.com/product/generative-ai/ Explore more Generative AI use cases | https://experience.dataiku.com/generative-ai To explore more about Dataiku, check out the rest of ...\",\"duration\":\"1:47\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/6TEU5JboP7k?autoplay=1\",\"image_token\":\"a3bc327ff2f099462935a8979bb599655c7a88a44e25a64bfea7e5973f773158\",\"images\":{\"large\":\"https://tse2.mm.bing.net/th?id=OVP.Q6SP0MmL89M_TnLvNPG4oQEsDh&pid=Api\",\"medium\":\"https://tse2.mm.bing.net/th?id=OVP.Q6SP0MmL89M_TnLvNPG4oQEsDh&pid=Api\",\"motion\":\"https://tse2.mm.bing.net/th?id=OM2.wXNo1CUgYV4Flg_1694065487&pid=Api\",\"small\":\"https://tse2.mm.bing.net/th?id=OVP.Q6SP0MmL89M_TnLvNPG4oQEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-06-22T12:34:32.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":462},\"title\":\"LLM-Enhanced Next Best Offer\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=UVbrpX8Zkn8\",\"description\":\"Move beyond the lab and build real and safe Generative AI applications at enterprise scale. Dataiku brings enterprise-grade development tools, pre-built use cases, and AI-powered assistants throughout the platform. Learn more about Dataiku for Generative AI | https://www.dataiku.com/product/generative-ai/ Explore Generative AI use cases | https ...\",\"duration\":\"2:07\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/UVbrpX8Zkn8?autoplay=1\",\"image_token\":\"3968d2d01ff722efa156290344ab0b37164e57d7efa50905c346ea1cc1a5d369\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.F-xH3-wKfTjM3YMshnjWwwEsDh&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.F-xH3-wKfTjM3YMshnjWwwEsDh&pid=Api\",\"motion\":\"https://tse1.mm.bing.net/th?id=OM1.z-FRwxQ_NByK_A_1689135755&pid=Api\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.F-xH3-wKfTjM3YMshnjWwwEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-06-22T12:25:16.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":1100},\"title\":\"Dataiku for Generative AI: Real Applications, Real Safety\",\"uploader\":\"Dataiku\"},{\"content\":\"https://www.youtube.com/watch?v=-amc9iVauuE\",\"description\":\"Dataiku is the leading platform for Everyday AI, systemizing the use of data for exceptional business results. In today's video we will take a tour of Dataiku's end to end capabilities by exploring a real life use case around environmental impact. Let's take a look at how a data science team with different skills can work together to turn ...\",\"duration\":\"12:35\",\"embed_html\":\"\",\"embed_url\":\"http://www.youtube.com/embed/-amc9iVauuE?autoplay=1\",\"image_token\":\"2a05a65ad8a2727aa5c48b8daa7f9ec363a24d4336a3509016d4b200c9d003cd\",\"images\":{\"large\":\"https://tse1.mm.bing.net/th?id=OVP.Az9RhdSVwpXe56mGcs6FqQEsDh&pid=Api\",\"medium\":\"https://tse1.mm.bing.net/th?id=OVP.Az9RhdSVwpXe56mGcs6FqQEsDh&pid=Api\",\"motion\":\"https://tse1.mm.bing.net/th?id=OM1.Q2OhN9DzfowU6A_1685345657&pid=Api\",\"small\":\"https://tse1.mm.bing.net/th?id=OVP.Az9RhdSVwpXe56mGcs6FqQEsDh&pid=Api\"},\"provider\":\"Bing\",\"published\":\"2023-01-09T21:12:27.0000000\",\"publisher\":\"YouTube\",\"statistics\":{\"viewCount\":9768},\"title\":\"End to End Demo 2023\",\"uploader\":\"Dataiku\"}],\"vqd\":{\"Dataiku%20and%20DataRobot%20use%20cases\":\"4-60481969350525797892441552954401970387\"}});DDG.duckbar.loadModule('related_searches');if (DDG.pageLayout) DDG.pageLayout.initialize({\"mainline\":{\"items\":[[\"ad\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"videos\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"],[\"organic\"]]},\"sidebar\":{\"items\":[[\"organic\"]]}}, { start: 0 });DDG.deep.emit(\"load:completed\");" +} \ No newline at end of file diff --git a/tests/metagpt/actions/test_research.py b/tests/metagpt/actions/test_research.py index dfbcce4ae..8c5ed0c7c 100644 --- a/tests/metagpt/actions/test_research.py +++ b/tests/metagpt/actions/test_research.py @@ -9,10 +9,12 @@ import pytest from metagpt.actions import research +from metagpt.tools import SearchEngineType +from metagpt.tools.search_engine import SearchEngine @pytest.mark.asyncio -async def test_collect_links(mocker): +async def test_collect_links(mocker, search_engine_mocker): async def mock_llm_ask(self, prompt: str, system_msgs): if "Please provide up to 2 necessary keywords" in prompt: return '["metagpt", "llm"]' @@ -26,13 +28,15 @@ async def test_collect_links(mocker): return "[1,2]" mocker.patch("metagpt.provider.base_llm.BaseLLM.aask", mock_llm_ask) - resp = await research.CollectLinks().run("The application of MetaGPT") + resp = await research.CollectLinks(search_engine=SearchEngine(SearchEngineType.DUCK_DUCK_GO)).run( + "The application of MetaGPT" + ) for i in ["MetaGPT use cases", "The roadmap of MetaGPT", "The function of MetaGPT", "What llm MetaGPT support"]: assert i in resp @pytest.mark.asyncio -async def test_collect_links_with_rank_func(mocker): +async def test_collect_links_with_rank_func(mocker, search_engine_mocker): rank_before = [] rank_after = [] url_per_query = 4 @@ -45,7 +49,9 @@ async def test_collect_links_with_rank_func(mocker): return results mocker.patch("metagpt.provider.base_llm.BaseLLM.aask", mock_collect_links_llm_ask) - resp = await research.CollectLinks(rank_func=rank_func).run("The application of MetaGPT") + resp = await research.CollectLinks( + search_engine=SearchEngine(SearchEngineType.DUCK_DUCK_GO), rank_func=rank_func + ).run("The application of MetaGPT") for x, y, z in zip(rank_before, rank_after, resp.values()): assert x[::-1] == y assert [i["link"] for i in y] == z diff --git a/tests/metagpt/roles/test_researcher.py b/tests/metagpt/roles/test_researcher.py index 891befa38..7d0ec450d 100644 --- a/tests/metagpt/roles/test_researcher.py +++ b/tests/metagpt/roles/test_researcher.py @@ -4,7 +4,10 @@ from tempfile import TemporaryDirectory import pytest +from metagpt.actions.research import CollectLinks from metagpt.roles import researcher +from metagpt.tools import SearchEngineType +from metagpt.tools.search_engine import SearchEngine async def mock_llm_ask(self, prompt: str, system_msgs): @@ -25,12 +28,16 @@ async def mock_llm_ask(self, prompt: str, system_msgs): @pytest.mark.asyncio -async def test_researcher(mocker): +async def test_researcher(mocker, search_engine_mocker): with TemporaryDirectory() as dirname: topic = "dataiku vs. datarobot" mocker.patch("metagpt.provider.base_llm.BaseLLM.aask", mock_llm_ask) researcher.RESEARCH_PATH = Path(dirname) - await researcher.Researcher().run(topic) + role = researcher.Researcher() + for i in role.actions: + if isinstance(i, CollectLinks): + i.search_engine = SearchEngine(SearchEngineType.DUCK_DUCK_GO) + await role.run(topic) assert (researcher.RESEARCH_PATH / f"{topic}.md").read_text().startswith("# Research Report") diff --git a/tests/metagpt/tools/test_search_engine.py b/tests/metagpt/tools/test_search_engine.py index 1cdecb3e9..966f53a38 100644 --- a/tests/metagpt/tools/test_search_engine.py +++ b/tests/metagpt/tools/test_search_engine.py @@ -7,20 +7,15 @@ """ from __future__ import annotations -import json -from pathlib import Path from typing import Callable import pytest -import tests.data.search from metagpt.config2 import config from metagpt.logs import logger from metagpt.tools import SearchEngineType from metagpt.tools.search_engine import SearchEngine -search_cache_path = Path(tests.data.search.__path__[0]) - class MockSearchEnine: async def run(self, query: str, max_results: int = 8, as_string: bool = True) -> str | list[dict[str, str]]: @@ -46,24 +41,28 @@ class MockSearchEnine: (SearchEngineType.CUSTOM_ENGINE, MockSearchEnine().run, 6, False), ], ) -async def test_search_engine(search_engine_type, run_func: Callable, max_results: int, as_string: bool, aiohttp_mocker): +async def test_search_engine( + search_engine_type, + run_func: Callable, + max_results: int, + as_string: bool, + search_engine_mocker, +): # Prerequisites - cache_json_path = None - # FIXME: 不能使用全局的config，而是要自己实例化对应的config + search_engine_config = {} + if search_engine_type is SearchEngineType.SERPAPI_GOOGLE: assert config.search - cache_json_path = search_cache_path / f"serpapi-metagpt-{max_results}.json" + search_engine_config["serpapi_api_key"] = "mock-serpapi-key" elif search_engine_type is SearchEngineType.DIRECT_GOOGLE: assert config.search + search_engine_config["google_api_key"] = "mock-google-key" + search_engine_config["google_cse_id"] = "mock-google-cse" elif search_engine_type is SearchEngineType.SERPER_GOOGLE: assert config.search - cache_json_path = search_cache_path / f"serper-metagpt-{max_results}.json" + search_engine_config["serper_api_key"] = "mock-serper-key" - if cache_json_path: - with open(cache_json_path) as f: - data = json.load(f) - aiohttp_mocker.set_json(data) - search_engine = SearchEngine(search_engine_type, run_func) + search_engine = SearchEngine(search_engine_type, run_func, **search_engine_config) rsp = await search_engine.run("metagpt", max_results, as_string) logger.info(rsp) if as_string: diff --git a/tests/mock/mock_aiohttp.py b/tests/mock/mock_aiohttp.py new file mode 100644 index 000000000..4690bf4b5 --- /dev/null +++ b/tests/mock/mock_aiohttp.py @@ -0,0 +1,41 @@ +import json +from typing import Callable + +from aiohttp.client import ClientSession + +origin_request = ClientSession.request + + +class MockAioResponse: + check_funcs: dict[tuple[str, str], Callable[[dict], str]] = {} + rsp_cache: dict[str, str] = {} + name = "aiohttp" + + def __init__(self, session, method, url, **kwargs) -> None: + fn = self.check_funcs.get((method, url)) + self.key = f"{self.name}-{method}-{url}-{fn(kwargs) if fn else json.dumps(kwargs, sort_keys=True)}" + self.mng = self.response = None + if self.key not in self.rsp_cache: + self.mng = origin_request(session, method, url, **kwargs) + + async def __aenter__(self): + if self.response: + await self.response.__aenter__() + elif self.mng: + self.response = await self.mng.__aenter__() + return self + + async def __aexit__(self, *args, **kwargs): + if self.response: + await self.response.__aexit__(*args, **kwargs) + self.response = None + elif self.mng: + await self.mng.__aexit__(*args, **kwargs) + self.mng = None + + async def json(self, *args, **kwargs): + if self.key in self.rsp_cache: + return self.rsp_cache[self.key] + data = await self.response.json(*args, **kwargs) + self.rsp_cache[self.key] = data + return data diff --git a/tests/mock/mock_curl_cffi.py b/tests/mock/mock_curl_cffi.py new file mode 100644 index 000000000..3f2bea4a7 --- /dev/null +++ b/tests/mock/mock_curl_cffi.py @@ -0,0 +1,22 @@ +import json +from typing import Callable + +from curl_cffi import requests + +origin_request = requests.Session.request + + +class MockCurlCffiResponse(requests.Response): + check_funcs: dict[tuple[str, str], Callable[[dict], str]] = {} + rsp_cache: dict[str, str] = {} + name = "curl-cffi" + + def __init__(self, session, method, url, **kwargs) -> None: + super().__init__() + fn = self.check_funcs.get((method, url)) + self.key = f"{self.name}-{method}-{url}-{fn(kwargs) if fn else json.dumps(kwargs, sort_keys=True)}" + self.response = None + if self.key not in self.rsp_cache: + response = origin_request(session, method, url, **kwargs) + self.rsp_cache[self.key] = response.content.decode() + self.content = self.rsp_cache[self.key].encode() diff --git a/tests/mock/mock_httplib2.py b/tests/mock/mock_httplib2.py new file mode 100644 index 000000000..b6dd0b77b --- /dev/null +++ b/tests/mock/mock_httplib2.py @@ -0,0 +1,29 @@ +import json +from typing import Callable +from urllib.parse import parse_qsl, urlparse + +import httplib2 + +origin_request = httplib2.Http.request + + +class MockHttplib2Response(httplib2.Response): + check_funcs: dict[tuple[str, str], Callable[[dict], str]] = {} + rsp_cache: dict[str, str] = {} + name = "httplib2" + + def __init__(self, http, uri, method="GET", **kwargs) -> None: + url = uri.split("?")[0] + result = urlparse(uri) + params = dict(parse_qsl(result.query)) + fn = self.check_funcs.get((method, uri)) + new_kwargs = {"params": params} + key = f"{self.name}-{method}-{url}-{fn(new_kwargs) if fn else json.dumps(new_kwargs)}" + if key not in self.rsp_cache: + _, self.content = origin_request(http, uri, method, **kwargs) + self.rsp_cache[key] = self.content.decode() + self.content = self.rsp_cache[key] + + def __iter__(self): + yield self + yield self.content.encode() From 7c3ac6a3503e4bedf5004399a6db6c89ab2a0118 Mon Sep 17 00:00:00 2001 From: shenchucheng Date: Mon, 15 Jan 2024 13:20:13 +0800 Subject: [PATCH 61/61] fix test_scrape_web_page error --- metagpt/tools/web_browser_engine.py | 2 +- metagpt/tools/web_browser_engine_selenium.py | 2 +- tests/conftest.py | 2 +- tests/metagpt/tools/test_web_browser_engine_playwright.py | 4 ++-- tests/metagpt/tools/test_web_browser_engine_selenium.py | 4 ++-- 5 files changed, 7 insertions(+), 7 deletions(-) diff --git a/metagpt/tools/web_browser_engine.py b/metagpt/tools/web_browser_engine.py index 61d29688b..411c1604b 100644 --- a/metagpt/tools/web_browser_engine.py +++ b/metagpt/tools/web_browser_engine.py @@ -13,7 +13,7 @@ from metagpt.utils.parse_html import WebPage class WebBrowserEngine: def __init__( self, - engine: WebBrowserEngineType | None = WebBrowserEngineType.PLAYWRIGHT, + engine: WebBrowserEngineType = WebBrowserEngineType.PLAYWRIGHT, run_func: Callable[..., Coroutine[Any, Any, WebPage | list[WebPage]]] | None = None, ): if engine is None: diff --git a/metagpt/tools/web_browser_engine_selenium.py b/metagpt/tools/web_browser_engine_selenium.py index 7988358ff..02dd5c173 100644 --- a/metagpt/tools/web_browser_engine_selenium.py +++ b/metagpt/tools/web_browser_engine_selenium.py @@ -33,7 +33,7 @@ class SeleniumWrapper: def __init__( self, - browser_type: Literal["chrome", "firefox", "edge", "ie"] | None = None, + browser_type: Literal["chrome", "firefox", "edge", "ie"] = "chrome", launch_kwargs: dict | None = None, *, loop: asyncio.AbstractEventLoop | None = None, diff --git a/tests/conftest.py b/tests/conftest.py index f20c261a4..42b460357 100644 --- a/tests/conftest.py +++ b/tests/conftest.py @@ -127,7 +127,7 @@ def proxy(): server = await asyncio.start_server(handle_client, "127.0.0.1", 0) return server, "http://{}:{}".format(*server.sockets[0].getsockname()) - return proxy_func() + return proxy_func # see https://github.com/Delgan/loguru/issues/59#issuecomment-466591978 diff --git a/tests/metagpt/tools/test_web_browser_engine_playwright.py b/tests/metagpt/tools/test_web_browser_engine_playwright.py index 053f1782d..0e838a2f8 100644 --- a/tests/metagpt/tools/test_web_browser_engine_playwright.py +++ b/tests/metagpt/tools/test_web_browser_engine_playwright.py @@ -22,8 +22,8 @@ async def test_scrape_web_page(browser_type, use_proxy, kwagrs, url, urls, proxy global_proxy = config.proxy try: if use_proxy: - server, proxy = await proxy - config.proxy = proxy + server, proxy_url = await proxy() + config.proxy = proxy_url browser = web_browser_engine_playwright.PlaywrightWrapper(browser_type=browser_type, **kwagrs) result = await browser.run(url) assert isinstance(result, WebPage) diff --git a/tests/metagpt/tools/test_web_browser_engine_selenium.py b/tests/metagpt/tools/test_web_browser_engine_selenium.py index 8dcd006f3..e38905b85 100644 --- a/tests/metagpt/tools/test_web_browser_engine_selenium.py +++ b/tests/metagpt/tools/test_web_browser_engine_selenium.py @@ -25,8 +25,8 @@ async def test_scrape_web_page(browser_type, use_proxy, url, urls, proxy, capfd) global_proxy = config.proxy try: if use_proxy: - server, proxy = await proxy - config.proxy = proxy + server, proxy_url = await proxy() + config.proxy = proxy_url browser = web_browser_engine_selenium.SeleniumWrapper(browser_type=browser_type) result = await browser.run(url) assert isinstance(result, WebPage)