update locally

config/config.yaml

@@ -5,7 +5,7 @@
 ## The official OPENAI_API_BASE is https://api.openai.com/v1
 ## If the official OPENAI_API_BASE is not available, we recommend using the [openai-forward](https://github.com/beidongjiedeguang/openai-forward).
 ## Or, you can configure OPENAI_PROXY to access official OPENAI_API_BASE.
-OPENAI_API_BASE: "https://api.openai.com/v1"
+#OPENAI_API_BASE: "https://api.openai.com/v1"
 #OPENAI_PROXY: "http://127.0.0.1:8118"
 #OPENAI_API_KEY: "YOUR_API_KEY"   # set the value to sk-xxx if you host the openai interface for open llm model
 OPENAI_API_MODEL: "gpt-4"
@@ -24,12 +24,13 @@ RPM: 10
 
 #### if AZURE, check https://github.com/openai/openai-cookbook/blob/main/examples/azure/chat.ipynb
 #### You can use ENGINE or DEPLOYMENT mode
-#OPENAI_API_TYPE: "azure"
-#OPENAI_API_BASE: "YOUR_AZURE_ENDPOINT"
-#OPENAI_API_KEY: "YOUR_AZURE_API_KEY"
-#OPENAI_API_VERSION: "YOUR_AZURE_API_VERSION"
-#DEPLOYMENT_NAME: "YOUR_DEPLOYMENT_NAME"
-#DEPLOYMENT_ID: "YOUR_DEPLOYMENT_ID"
+OPENAI_API_TYPE: "azure"
+OPENAI_API_BASE: "https://deepwisdom.openai.azure.com/"
+OPENAI_API_KEY: "02ae6058d09849c691176befeae2107c"
+#OPENAI_API_VERSION: "2023-05-15"
+OPENAI_API_VERSION: "2023-07-01-preview"
+DEPLOYMENT_ID: "GPT-4"
+OPENAI_API_ENGINE: "gpt-4"
 
 #### if zhipuai from `https://open.bigmodel.cn`. You can set here or export API_KEY="YOUR_API_KEY"
 # ZHIPUAI_API_KEY: "YOUR_API_KEY"

metagpt/roles/ml_engineer.py

@@ -10,7 +10,7 @@ from metagpt.actions import Action
 from metagpt.actions.execute_code import ExecutePyCode
 from metagpt.actions.write_analysis_code import WriteCodeByGenerate, WriteCodeWithTools
 from metagpt.actions.write_plan import WritePlan
-from metagpt.actions.write_task_guide import WriteTaskGuide
+# from metagpt.actions.write_task_guide import WriteTaskGuide
 from metagpt.logs import logger
 from metagpt.prompts.ml_engineer import GEN_DATA_DESC_PROMPT
 from metagpt.roles import Role
@@ -39,7 +39,7 @@ catboost
 def truncate(result: str, keep_len: int = 1000) -> str:
     desc = "Truncated to show only the last 1000 characters\n"
     if result.startswith(desc):
-        result = result[-len(desc) :]
+        result = result[-len(desc):]
 
     if len(result) > keep_len:
         result = result[-keep_len:]
@@ -110,9 +110,9 @@ class AskReview(Action):
         logger.info("most recent context:")
         latest_action = context[-1].cause_by.__name__ if context[-1].cause_by else ""
         prompt = f"\nPlease review output from {latest_action}:\n" \
-            "If you want to change a task in the plan, say 'change task task_id, ... (things to change)'\n" \
-            "If you confirm the output and wish to continue with the current process, type CONFIRM\n" \
-            "If you want to terminate the process, type exit:\n"
+                 "If you want to change a task in the plan, say 'change task task_id, ... (things to change)'\n" \
+                 "If you confirm the output and wish to continue with the current process, type CONFIRM\n" \
+                 "If you want to terminate the process, type exit:\n"
         rsp = input(prompt)
 
         if rsp.lower() in ("exit"):
@@ -148,7 +148,7 @@ class GenerateDataDesc(Action):
 
 class MLEngineer(Role):
     def __init__(
-        self, name="ABC", profile="MLEngineer", goal="", auto_run: bool = False, data_path: str = None
+            self, name="ABC", profile="MLEngineer", goal="", auto_run: bool = False, data_path: str = None
     ):
         super().__init__(name=name, profile=profile, goal=goal)
         self._set_react_mode(react_mode="plan_and_act")
@@ -300,11 +300,15 @@ if __name__ == "__main__":
     # requirement = "Run data analysis on sklearn Wisconsin Breast Cancer dataset, include a plot, train a model to predict targets (20% as validation), and show validation accuracy"
     # requirement = "Run EDA and visualization on this dataset, train a model to predict survival, report metrics on validation set (20%), dataset: workspace/titanic/train.csv"
 
+    from metagpt.const import DATA_PATH
+
     requirement = "Perform data analysis on the provided data. Train a model to predict the target variable Survived. Include data preprocessing, feature engineering, and modeling in your pipeline. The metric is accuracy."
-    data_path = "/data/lidanyang/tabular_data/titanic"
+    data_path = f"{DATA_PATH}/titanic"
+
 
     async def main(requirement: str = requirement, auto_run: bool = True, data_path: str = data_path):
         role = MLEngineer(goal=requirement, auto_run=auto_run, data_path=data_path)
         await role.run(requirement)
 
+
     fire.Fire(main)

metagpt/tools/functions/__init__.py

@@ -6,4 +6,4 @@
 # @Desc    :
 from metagpt.tools.functions.register.register import registry
 import metagpt.tools.functions.libs.feature_engineering
-import metagpt.tools.functions.libs.data_preprocess
+# import metagpt.tools.functions.libs.data_preprocess

metagpt/tools/web_browser_engine.py

@@ -7,7 +7,7 @@ from typing import Any, Callable, Coroutine, Literal, overload
 
 from metagpt.config import CONFIG
 from metagpt.tools import WebBrowserEngineType
-from metagpt.utils.parse_html import WebPage
+# from metagpt.utils.parse_html import WebPage
 
 
 class WebBrowserEngine:

metagpt/utils/__init__.py

@@ -6,7 +6,7 @@
 @File    : __init__.py
 """
 
-from metagpt.utils.read_document import read_docx
+# from metagpt.utils.read_document import read_docx
 from metagpt.utils.singleton import Singleton
 from metagpt.utils.token_counter import (
     TOKEN_COSTS,
@@ -16,7 +16,7 @@ from metagpt.utils.token_counter import (
 
 
 __all__ = [
-    "read_docx",
+    # "read_docx",
     "Singleton",
     "TOKEN_COSTS",
     "count_message_tokens",

requirements.txt

@@ -35,7 +35,6 @@ tqdm==4.64.0
 # webdriver_manager<3.9
 anthropic==0.3.6
 typing-inspect==0.8.0
-typing_extensions==4.5.0
 libcst==1.0.1
 qdrant-client==1.4.0
 pytest-mock==3.11.1
@@ -46,7 +45,6 @@ wrapt==1.15.0
 websocket-client==0.58.0
 zhipuai==1.0.7
 rich==13.6.0
-nbclient==0.9.0
 nbformat==5.9.2
 ipython==8.17.2
 ipykernel==6.27.0