mirror of
https://github.com/FoundationAgents/MetaGPT.git
synced 2026-05-27 14:25:20 +02:00
Merge branch 'main' into main
This commit is contained in:
Espérance Codjo AYIWAHOUN
GitHub
commit
65f9654df2
21 changed files with 452 additions and 88 deletions
10
.github/workflows/fulltest.yaml
vendored
10
.github/workflows/fulltest.yaml
vendored
|
|
@ -79,8 +79,8 @@ jobs:
|
|||
./tests/data/rsp_cache_new.json
|
||||
retention-days: 3
|
||||
if: ${{ always() }}
|
||||
- name: Upload coverage reports to Codecov
|
||||
uses: codecov/codecov-action@v3
|
||||
env:
|
||||
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
|
||||
if: ${{ always() }}
|
||||
# - name: Upload coverage reports to Codecov
|
||||
# uses: codecov/codecov-action@v3
|
||||
# env:
|
||||
# CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
|
||||
# if: ${{ always() }}
|
||||
|
|
|
|||
10
.github/workflows/unittest.yaml
vendored
10
.github/workflows/unittest.yaml
vendored
|
|
@ -91,8 +91,8 @@ jobs:
|
|||
./tests/data/rsp_cache_new.json
|
||||
retention-days: 3
|
||||
if: ${{ always() }}
|
||||
- name: Upload coverage reports to Codecov
|
||||
uses: codecov/codecov-action@v3
|
||||
env:
|
||||
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
|
||||
if: ${{ always() }}
|
||||
# - name: Upload coverage reports to Codecov
|
||||
# uses: codecov/codecov-action@v3
|
||||
# env:
|
||||
# CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
|
||||
# if: ${{ always() }}
|
||||
|
|
|
|||
10
README.md
10
README.md
|
|
@ -2,7 +2,7 @@
|
|||
# MetaGPT: The Multi-Agent Framework
|
||||
|
||||
<p align="center">
|
||||
<a href=""><img src="docs/resources/MetaGPT-new-log.png" alt="MetaGPT logo: Enable GPT to work in software company, collaborating to tackle more complex tasks." width="150px"></a>
|
||||
<a href=""><img src="docs/resources/MetaGPT-new-log.png" alt="MetaGPT logo: Enable GPT to work in a software company, collaborating to tackle more complex tasks." width="150px"></a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
|
|
@ -23,11 +23,11 @@ # MetaGPT: The Multi-Agent Framework
|
|||
<p align="center">
|
||||
<a href="https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/geekan/MetaGPT"><img src="https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode" alt="Open in Dev Containers"></a>
|
||||
<a href="https://codespaces.new/geekan/MetaGPT"><img src="https://img.shields.io/badge/Github_Codespace-Open-blue?logo=github" alt="Open in GitHub Codespaces"></a>
|
||||
<a href="https://huggingface.co/spaces/deepwisdom/MetaGPT" target="_blank"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20-Hugging%20Face-blue?color=blue&logoColor=white" /></a>
|
||||
<a href="https://huggingface.co/spaces/deepwisdom/MetaGPT-SoftwareCompany" target="_blank"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20-Hugging%20Face-blue?color=blue&logoColor=white" /></a>
|
||||
</p>
|
||||
|
||||
## News
|
||||
🚀 Mar. 29, 2024: [v0.8.0](https://github.com/geekan/MetaGPT/releases/tag/v0.8.0) released. Now you can use Data Interpreter ([arxiv](https://arxiv.org/abs/2402.18679), [example](https://docs.deepwisdom.ai/main/en/DataInterpreter/), [code](https://github.com/geekan/MetaGPT/tree/main/examples/di)) via pypi package import. Meanwhile, we integrated RAG module and supported multiple new LLMs.
|
||||
🚀 Mar. 29, 2024: [v0.8.0](https://github.com/geekan/MetaGPT/releases/tag/v0.8.0) released. Now you can use Data Interpreter ([arxiv](https://arxiv.org/abs/2402.18679), [example](https://docs.deepwisdom.ai/main/en/DataInterpreter/), [code](https://github.com/geekan/MetaGPT/tree/main/examples/di)) via pypi package import. Meanwhile, we integrated the RAG module and supported multiple new LLMs.
|
||||
|
||||
🚀 Feb. 08, 2024: [v0.7.0](https://github.com/geekan/MetaGPT/releases/tag/v0.7.0) released, supporting assigning different LLMs to different Roles. We also introduced [Data Interpreter](https://github.com/geekan/MetaGPT/blob/main/examples/di/README.md), a powerful agent capable of solving a wide range of real-world problems.
|
||||
|
||||
|
|
@ -121,7 +121,7 @@ ### Usage
|
|||
|
||||
|
||||
### QuickStart & Demo Video
|
||||
- Try it on [MetaGPT Huggingface Space](https://huggingface.co/spaces/deepwisdom/MetaGPT)
|
||||
- Try it on [MetaGPT Huggingface Space](https://huggingface.co/spaces/deepwisdom/MetaGPT-SoftwareCompany)
|
||||
- [Matthew Berman: How To Install MetaGPT - Build A Startup With One Prompt!!](https://youtu.be/uT75J_KG_aY)
|
||||
- [Official Demo Video](https://github.com/geekan/MetaGPT/assets/2707039/5e8c1062-8c35-440f-bb20-2b0320f8d27d)
|
||||
|
||||
|
|
@ -141,7 +141,7 @@ ## Tutorial
|
|||
- [Data Interpreter](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/interpreter/intro.html)
|
||||
- [Debate](https://docs.deepwisdom.ai/main/en/guide/use_cases/multi_agent/debate.html)
|
||||
- [Researcher](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/researcher.html)
|
||||
- [Recepit Assistant](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/receipt_assistant.html)
|
||||
- [Receipt Assistant](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/receipt_assistant.html)
|
||||
- ❓ [FAQs](https://docs.deepwisdom.ai/main/en/guide/faq.html)
|
||||
|
||||
## Support
|
||||
|
|
|
|||
|
|
@ -22,7 +22,7 @@ # MetaGPT: 多智能体框架
|
|||
<p align="center">
|
||||
<a href="https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/geekan/MetaGPT"><img src="https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode" alt="Open in Dev Containers"></a>
|
||||
<a href="https://codespaces.new/geekan/MetaGPT"><img src="https://img.shields.io/badge/Github_Codespace-Open-blue?logo=github" alt="Open in GitHub Codespaces"></a>
|
||||
<a href="https://huggingface.co/spaces/deepwisdom/MetaGPT" target="_blank"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20-Hugging%20Face-blue?color=blue&logoColor=white" /></a>
|
||||
<a href="https://huggingface.co/spaces/deepwisdom/MetaGPT-SoftwareCompany" target="_blank"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20-Hugging%20Face-blue?color=blue&logoColor=white" /></a>
|
||||
</p>
|
||||
|
||||
1. MetaGPT输入**一句话的老板需求**，输出**用户故事 / 竞品分析 / 需求 / 数据结构 / APIs / 文件等**
|
||||
|
|
@ -77,7 +77,7 @@ # 步骤2: 使用容器运行metagpt演示
|
|||
详细的安装请参考 [docker_install](https://docs.deepwisdom.ai/main/zh/guide/get_started/installation.html#%E4%BD%BF%E7%94%A8docker%E5%AE%89%E8%A3%85)
|
||||
|
||||
### 快速开始的演示视频
|
||||
- 在 [MetaGPT Huggingface Space](https://huggingface.co/spaces/deepwisdom/MetaGPT) 上进行体验
|
||||
- 在 [MetaGPT Huggingface Space](https://huggingface.co/spaces/deepwisdom/MetaGPT-SoftwareCompany) 上进行体验
|
||||
- [Matthew Berman: How To Install MetaGPT - Build A Startup With One Prompt!!](https://youtu.be/uT75J_KG_aY)
|
||||
- [官方演示视频](https://github.com/geekan/MetaGPT/assets/2707039/5e8c1062-8c35-440f-bb20-2b0320f8d27d)
|
||||
|
||||
|
|
|
|||
|
|
@ -22,7 +22,7 @@ # MetaGPT: マルチエージェントフレームワーク
|
|||
<p align="center">
|
||||
<a href="https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/geekan/MetaGPT"><img src="https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode" alt="Open in Dev Containers"></a>
|
||||
<a href="https://codespaces.new/geekan/MetaGPT"><img src="https://img.shields.io/badge/Github_Codespace-Open-blue?logo=github" alt="Open in GitHub Codespaces"></a>
|
||||
<a href="https://huggingface.co/spaces/deepwisdom/MetaGPT" target="_blank"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20-Hugging%20Face-blue?color=blue&logoColor=white" /></a>
|
||||
<a href="https://huggingface.co/spaces/deepwisdom/MetaGPT-SoftwareCompany" target="_blank"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20-Hugging%20Face-blue?color=blue&logoColor=white" /></a>
|
||||
</p>
|
||||
|
||||
1. MetaGPT は、**1 行の要件** を入力とし、**ユーザーストーリー / 競合分析 / 要件 / データ構造 / API / 文書など** を出力します。
|
||||
|
|
@ -292,7 +292,7 @@ ## クイックスタート
|
|||
- [MetaGPT クイックスタート](https://deepwisdom.feishu.cn/wiki/CyY9wdJc4iNqArku3Lncl4v8n2b)
|
||||
|
||||
Hugging Face Space で試す
|
||||
- https://huggingface.co/spaces/deepwisdom/MetaGPT
|
||||
- https://huggingface.co/spaces/deepwisdom/MetaGPT-SoftwareCompany
|
||||
|
||||
## 引用
|
||||
|
||||
|
|
|
|||
|
|
@ -5,6 +5,7 @@
|
|||
@Author : alexanderwu
|
||||
@File : llm_config.py
|
||||
"""
|
||||
|
||||
from enum import Enum
|
||||
from typing import Optional
|
||||
|
||||
|
|
@ -57,6 +58,7 @@ class LLMConfig(YamlModel):
|
|||
# For Cloud Service Provider like Baidu/ Alibaba
|
||||
access_key: Optional[str] = None
|
||||
secret_key: Optional[str] = None
|
||||
session_token: Optional[str] = None
|
||||
endpoint: Optional[str] = None # for self-deployed model on the cloud
|
||||
|
||||
# For Spark(Xunfei), maybe remove later
|
||||
|
|
@ -76,6 +78,7 @@ class LLMConfig(YamlModel):
|
|||
best_of: Optional[int] = None
|
||||
n: Optional[int] = None
|
||||
stream: bool = True
|
||||
seed: Optional[int] = None
|
||||
# https://cookbook.openai.com/examples/using_logprobs
|
||||
logprobs: Optional[bool] = None
|
||||
top_logprobs: Optional[int] = None
|
||||
|
|
|
|||
99
metagpt/document_store/milvus_store.py
Normal file
99
metagpt/document_store/milvus_store.py
Normal file
|
|
@ -0,0 +1,99 @@
|
|||
from dataclasses import dataclass
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
from metagpt.document_store.base_store import BaseStore
|
||||
|
||||
|
||||
@dataclass
|
||||
class MilvusConnection:
|
||||
"""
|
||||
Args:
|
||||
uri: milvus url
|
||||
token: milvus token
|
||||
"""
|
||||
|
||||
uri: str = None
|
||||
token: str = None
|
||||
|
||||
|
||||
class MilvusStore(BaseStore):
|
||||
def __init__(self, connect: MilvusConnection):
|
||||
try:
|
||||
from pymilvus import MilvusClient
|
||||
except ImportError:
|
||||
raise Exception("Please install pymilvus first.")
|
||||
if not connect.uri:
|
||||
raise Exception("please check MilvusConnection, uri must be set.")
|
||||
self.client = MilvusClient(uri=connect.uri, token=connect.token)
|
||||
|
||||
def create_collection(self, collection_name: str, dim: int, enable_dynamic_schema: bool = True):
|
||||
from pymilvus import DataType
|
||||
|
||||
if self.client.has_collection(collection_name=collection_name):
|
||||
self.client.drop_collection(collection_name=collection_name)
|
||||
|
||||
schema = self.client.create_schema(
|
||||
auto_id=False,
|
||||
enable_dynamic_field=False,
|
||||
)
|
||||
schema.add_field(field_name="id", datatype=DataType.VARCHAR, is_primary=True, max_length=36)
|
||||
schema.add_field(field_name="vector", datatype=DataType.FLOAT_VECTOR, dim=dim)
|
||||
|
||||
index_params = self.client.prepare_index_params()
|
||||
index_params.add_index(field_name="vector", index_type="AUTOINDEX", metric_type="COSINE")
|
||||
|
||||
self.client.create_collection(
|
||||
collection_name=collection_name,
|
||||
schema=schema,
|
||||
index_params=index_params,
|
||||
enable_dynamic_schema=enable_dynamic_schema,
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def build_filter(key, value) -> str:
|
||||
if isinstance(value, str):
|
||||
filter_expression = f'{key} == "{value}"'
|
||||
else:
|
||||
if isinstance(value, list):
|
||||
filter_expression = f"{key} in {value}"
|
||||
else:
|
||||
filter_expression = f"{key} == {value}"
|
||||
|
||||
return filter_expression
|
||||
|
||||
def search(
|
||||
self,
|
||||
collection_name: str,
|
||||
query: List[float],
|
||||
filter: Dict = None,
|
||||
limit: int = 10,
|
||||
output_fields: Optional[List[str]] = None,
|
||||
) -> List[dict]:
|
||||
filter_expression = " and ".join([self.build_filter(key, value) for key, value in filter.items()])
|
||||
print(filter_expression)
|
||||
|
||||
res = self.client.search(
|
||||
collection_name=collection_name,
|
||||
data=[query],
|
||||
filter=filter_expression,
|
||||
limit=limit,
|
||||
output_fields=output_fields,
|
||||
)[0]
|
||||
|
||||
return res
|
||||
|
||||
def add(self, collection_name: str, _ids: List[str], vector: List[List[float]], metadata: List[Dict[str, Any]]):
|
||||
data = dict()
|
||||
|
||||
for i, id in enumerate(_ids):
|
||||
data["id"] = id
|
||||
data["vector"] = vector[i]
|
||||
data["metadata"] = metadata[i]
|
||||
|
||||
self.client.upsert(collection_name=collection_name, data=data)
|
||||
|
||||
def delete(self, collection_name: str, _ids: List[str]):
|
||||
self.client.delete(collection_name=collection_name, ids=_ids)
|
||||
|
||||
def write(self, *args, **kwargs):
|
||||
pass
|
||||
|
|
@ -57,15 +57,34 @@ class AnthropicProvider(BaseBedrockProvider):
|
|||
|
||||
|
||||
class CohereProvider(BaseBedrockProvider):
|
||||
# See https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-cohere-command.html
|
||||
# For more information, see
|
||||
# (Command) https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-cohere-command.html
|
||||
# (Command R/R+) https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-cohere-command-r-plus.html
|
||||
|
||||
def __init__(self, model_name: str) -> None:
|
||||
self.model_name = model_name
|
||||
|
||||
def _get_completion_from_dict(self, rsp_dict: dict) -> str:
|
||||
return rsp_dict["generations"][0]["text"]
|
||||
|
||||
def messages_to_prompt(self, messages: list[dict]) -> str:
|
||||
if "command-r" in self.model_name:
|
||||
role_map = {"user": "USER", "assistant": "CHATBOT", "system": "USER"}
|
||||
messages = list(
|
||||
map(lambda message: {"role": role_map[message["role"]], "message": message["content"]}, messages)
|
||||
)
|
||||
return messages
|
||||
else:
|
||||
"""[{"role": "user", "content": msg}] to user: <msg> etc."""
|
||||
return "\n".join([f"{msg['role']}: {msg['content']}" for msg in messages])
|
||||
|
||||
def get_request_body(self, messages: list[dict], generate_kwargs, *args, **kwargs):
|
||||
body = json.dumps(
|
||||
{"prompt": self.messages_to_prompt(messages), "stream": kwargs.get("stream", False), **generate_kwargs}
|
||||
)
|
||||
prompt = self.messages_to_prompt(messages)
|
||||
if "command-r" in self.model_name:
|
||||
chat_history, message = prompt[:-1], prompt[-1]["message"]
|
||||
body = json.dumps({"message": message, "chat_history": chat_history, **generate_kwargs})
|
||||
else:
|
||||
body = json.dumps({"prompt": prompt, "stream": kwargs.get("stream", False), **generate_kwargs})
|
||||
return body
|
||||
|
||||
def get_choice_text_from_stream(self, event) -> str:
|
||||
|
|
@ -95,10 +114,37 @@ class MetaProvider(BaseBedrockProvider):
|
|||
class Ai21Provider(BaseBedrockProvider):
|
||||
# See https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-jurassic2.html
|
||||
|
||||
max_tokens_field_name = "maxTokens"
|
||||
def __init__(self, model_type: Literal["j2", "jamba"]) -> None:
|
||||
self.model_type = model_type
|
||||
if self.model_type == "j2":
|
||||
self.max_tokens_field_name = "maxTokens"
|
||||
else:
|
||||
self.max_tokens_field_name = "max_tokens"
|
||||
|
||||
def get_request_body(self, messages: list[dict], generate_kwargs, *args, **kwargs) -> str:
|
||||
if self.model_type == "j2":
|
||||
body = super().get_request_body(messages, generate_kwargs, *args, **kwargs)
|
||||
else:
|
||||
body = json.dumps(
|
||||
{
|
||||
"messages": messages,
|
||||
**generate_kwargs,
|
||||
}
|
||||
)
|
||||
return body
|
||||
|
||||
def get_choice_text_from_stream(self, event) -> str:
|
||||
rsp_dict = json.loads(event["chunk"]["bytes"])
|
||||
completions = rsp_dict.get("choices", [{}])[0].get("delta", {}).get("content", "")
|
||||
return completions
|
||||
|
||||
def _get_completion_from_dict(self, rsp_dict: dict) -> str:
|
||||
return rsp_dict["completions"][0]["data"]["text"]
|
||||
if self.model_type == "j2":
|
||||
# See https://docs.ai21.com/reference/j2-complete-ref
|
||||
return rsp_dict["completions"][0]["data"]["text"]
|
||||
else:
|
||||
# See https://docs.ai21.com/reference/jamba-instruct-api
|
||||
return rsp_dict["choices"][0]["message"]["content"]
|
||||
|
||||
|
||||
class AmazonProvider(BaseBedrockProvider):
|
||||
|
|
@ -136,4 +182,10 @@ def get_provider(model_id: str):
|
|||
if provider == "meta":
|
||||
# distinguish llama2 and llama3
|
||||
return PROVIDERS[provider](model_name[:6])
|
||||
elif provider == "ai21":
|
||||
# distinguish between j2 and jamba
|
||||
return PROVIDERS[provider](model_name.split("-")[0])
|
||||
elif provider == "cohere":
|
||||
# distinguish between R/R+ and older models
|
||||
return PROVIDERS[provider](model_name)
|
||||
return PROVIDERS[provider]()
|
||||
|
|
|
|||
|
|
@ -1,52 +1,97 @@
|
|||
from metagpt.logs import logger
|
||||
|
||||
# max_tokens for each model
|
||||
NOT_SUUPORT_STREAM_MODELS = {
|
||||
"ai21.j2-grande-instruct": 8000,
|
||||
"ai21.j2-jumbo-instruct": 8000,
|
||||
"ai21.j2-mid": 8000,
|
||||
"ai21.j2-mid-v1": 8000,
|
||||
"ai21.j2-ultra": 8000,
|
||||
"ai21.j2-ultra-v1": 8000,
|
||||
NOT_SUPPORT_STREAM_MODELS = {
|
||||
# Jurassic-2 Mid-v1 and Ultra-v1
|
||||
# + Legacy date: 2024-04-30 (us-west-2/Oregon)
|
||||
# + EOL date: 2024-08-31 (us-west-2/Oregon)
|
||||
"ai21.j2-mid-v1": 8191,
|
||||
"ai21.j2-ultra-v1": 8191,
|
||||
}
|
||||
|
||||
SUPPORT_STREAM_MODELS = {
|
||||
"amazon.titan-tg1-large": 8000,
|
||||
"amazon.titan-text-express-v1": 8000,
|
||||
"amazon.titan-text-express-v1:0:8k": 8000,
|
||||
"amazon.titan-text-lite-v1:0:4k": 4000,
|
||||
"amazon.titan-text-lite-v1": 4000,
|
||||
"anthropic.claude-instant-v1": 100000,
|
||||
"anthropic.claude-instant-v1:2:100k": 100000,
|
||||
"anthropic.claude-v1": 100000,
|
||||
"anthropic.claude-v2": 100000,
|
||||
"anthropic.claude-v2:1": 200000,
|
||||
"anthropic.claude-v2:0:18k": 18000,
|
||||
"anthropic.claude-v2:1:200k": 200000,
|
||||
"anthropic.claude-3-sonnet-20240229-v1:0": 200000,
|
||||
"anthropic.claude-3-sonnet-20240229-v1:0:28k": 28000,
|
||||
"anthropic.claude-3-sonnet-20240229-v1:0:200k": 200000,
|
||||
"anthropic.claude-3-haiku-20240307-v1:0": 200000,
|
||||
"anthropic.claude-3-5-sonnet-20240620-v1:0": 200000,
|
||||
"anthropic.claude-3-haiku-20240307-v1:0:48k": 48000,
|
||||
"anthropic.claude-3-haiku-20240307-v1:0:200k": 200000,
|
||||
# currently (2024-4-29) only available at US West (Oregon) AWS Region.
|
||||
"anthropic.claude-3-opus-20240229-v1:0": 200000,
|
||||
"cohere.command-text-v14": 4000,
|
||||
"cohere.command-text-v14:7:4k": 4000,
|
||||
"cohere.command-light-text-v14": 4000,
|
||||
"cohere.command-light-text-v14:7:4k": 4000,
|
||||
"meta.llama2-13b-chat-v1:0:4k": 4000,
|
||||
"meta.llama2-13b-chat-v1": 2000,
|
||||
"meta.llama2-70b-v1": 4000,
|
||||
"meta.llama2-70b-v1:0:4k": 4000,
|
||||
"meta.llama2-70b-chat-v1": 2000,
|
||||
"meta.llama2-70b-chat-v1:0:4k": 2000,
|
||||
"meta.llama3-8b-instruct-v1:0": 2000,
|
||||
"meta.llama3-70b-instruct-v1:0": 2000,
|
||||
"mistral.mistral-7b-instruct-v0:2": 32000,
|
||||
"mistral.mixtral-8x7b-instruct-v0:1": 32000,
|
||||
"mistral.mistral-large-2402-v1:0": 32000,
|
||||
# Jamba-Instruct
|
||||
# https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-jamba.html
|
||||
"ai21.jamba-instruct-v1:0": 4096,
|
||||
# Titan Text G1 - Lite
|
||||
# https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-titan-text.html
|
||||
"amazon.titan-text-lite-v1:0:4k": 4096,
|
||||
"amazon.titan-text-lite-v1": 4096,
|
||||
# Titan Text G1 - Express
|
||||
"amazon.titan-text-express-v1": 8192,
|
||||
"amazon.titan-text-express-v1:0:8k": 8192,
|
||||
# Titan Text Premier
|
||||
"amazon.titan-text-premier-v1:0": 3072,
|
||||
"amazon.titan-text-premier-v1:0:32k": 3072,
|
||||
# Claude Instant v1
|
||||
# https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-text-completion.html
|
||||
# https://docs.anthropic.com/en/docs/about-claude/models#model-comparison
|
||||
"anthropic.claude-instant-v1": 4096,
|
||||
"anthropic.claude-instant-v1:2:100k": 4096,
|
||||
# Claude v2
|
||||
"anthropic.claude-v2": 4096,
|
||||
"anthropic.claude-v2:0:18k": 4096,
|
||||
"anthropic.claude-v2:0:100k": 4096,
|
||||
# Claude v2.1
|
||||
"anthropic.claude-v2:1": 4096,
|
||||
"anthropic.claude-v2:1:18k": 4096,
|
||||
"anthropic.claude-v2:1:200k": 4096,
|
||||
# Claude 3 Sonnet
|
||||
"anthropic.claude-3-sonnet-20240229-v1:0": 4096,
|
||||
"anthropic.claude-3-sonnet-20240229-v1:0:28k": 4096,
|
||||
"anthropic.claude-3-sonnet-20240229-v1:0:200k": 4096,
|
||||
# Claude 3 Haiku
|
||||
"anthropic.claude-3-haiku-20240307-v1:0": 4096,
|
||||
"anthropic.claude-3-haiku-20240307-v1:0:48k": 4096,
|
||||
"anthropic.claude-3-haiku-20240307-v1:0:200k": 4096,
|
||||
# Claude 3 Opus
|
||||
"anthropic.claude-3-opus-20240229-v1:0": 4096,
|
||||
# Claude 3.5 Sonnet
|
||||
"anthropic.claude-3-5-sonnet-20240620-v1:0": 8192,
|
||||
# Command Text
|
||||
# https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-cohere-command.html
|
||||
"cohere.command-text-v14": 4096,
|
||||
"cohere.command-text-v14:7:4k": 4096,
|
||||
# Command Light Text
|
||||
"cohere.command-light-text-v14": 4096,
|
||||
"cohere.command-light-text-v14:7:4k": 4096,
|
||||
# Command R
|
||||
# https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-cohere-command-r-plus.html
|
||||
"cohere.command-r-v1:0": 4096,
|
||||
# Command R+
|
||||
"cohere.command-r-plus-v1:0": 4096,
|
||||
# Llama 2 (--> Llama 3/3.1/3.2) !!!
|
||||
# https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html
|
||||
# + Legacy: 2024-05-12
|
||||
# + EOL: 2024-10-30
|
||||
# "meta.llama2-13b-chat-v1": 2048,
|
||||
# "meta.llama2-13b-chat-v1:0:4k": 2048,
|
||||
# "meta.llama2-70b-v1": 2048,
|
||||
# "meta.llama2-70b-v1:0:4k": 2048,
|
||||
# "meta.llama2-70b-chat-v1": 2048,
|
||||
# "meta.llama2-70b-chat-v1:0:4k": 2048,
|
||||
# Llama 3 Instruct
|
||||
# "meta.llama3-8b-instruct-v1:0": 2048,
|
||||
"meta.llama3-70b-instruct-v1:0": 2048,
|
||||
# Llama 3.1 Instruct
|
||||
# "meta.llama3-1-8b-instruct-v1:0": 2048,
|
||||
"meta.llama3-1-70b-instruct-v1:0": 2048,
|
||||
"meta.llama3-1-405b-instruct-v1:0": 2048,
|
||||
# Llama 3.2 Instruct
|
||||
# "meta.llama3-2-3b-instruct-v1:0": 2048,
|
||||
# "meta.llama3-2-11b-instruct-v1:0": 2048,
|
||||
"meta.llama3-2-90b-instruct-v1:0": 2048,
|
||||
# Mistral 7B Instruct
|
||||
# https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-mistral-text-completion.html
|
||||
# "mistral.mistral-7b-instruct-v0:2": 8192,
|
||||
# Mixtral 8x7B Instruct
|
||||
"mistral.mixtral-8x7b-instruct-v0:1": 4096,
|
||||
# Mistral Small
|
||||
"mistral.mistral-small-2402-v1:0": 8192,
|
||||
# Mistral Large (24.02)
|
||||
"mistral.mistral-large-2402-v1:0": 8192,
|
||||
# Mistral Large 2 (24.07)
|
||||
"mistral.mistral-large-2407-v1:0": 8192,
|
||||
}
|
||||
|
||||
# TODO:use a more general function for constructing chat templates.
|
||||
|
|
@ -106,7 +151,7 @@ def messages_to_prompt_claude2(messages: list[dict]) -> str:
|
|||
|
||||
def get_max_tokens(model_id: str) -> int:
|
||||
try:
|
||||
max_tokens = (NOT_SUUPORT_STREAM_MODELS | SUPPORT_STREAM_MODELS)[model_id]
|
||||
max_tokens = (NOT_SUPPORT_STREAM_MODELS | SUPPORT_STREAM_MODELS)[model_id]
|
||||
except KeyError:
|
||||
logger.warning(f"Couldn't find model:{model_id} , max tokens has been set to 2048")
|
||||
max_tokens = 2048
|
||||
|
|
|
|||
|
|
@ -1,5 +1,6 @@
|
|||
import asyncio
|
||||
import json
|
||||
import os
|
||||
from functools import partial
|
||||
from typing import List, Literal
|
||||
|
||||
|
|
@ -11,7 +12,7 @@ from metagpt.const import USE_CONFIG_TIMEOUT
|
|||
from metagpt.logs import log_llm_stream, logger
|
||||
from metagpt.provider.base_llm import BaseLLM
|
||||
from metagpt.provider.bedrock.bedrock_provider import get_provider
|
||||
from metagpt.provider.bedrock.utils import NOT_SUUPORT_STREAM_MODELS, get_max_tokens
|
||||
from metagpt.provider.bedrock.utils import NOT_SUPPORT_STREAM_MODELS, get_max_tokens
|
||||
from metagpt.provider.llm_provider_registry import register_provider
|
||||
from metagpt.utils.cost_manager import CostManager
|
||||
from metagpt.utils.token_counter import BEDROCK_TOKEN_COSTS
|
||||
|
|
@ -24,18 +25,19 @@ class BedrockLLM(BaseLLM):
|
|||
self.__client = self.__init_client("bedrock-runtime")
|
||||
self.__provider = get_provider(self.config.model)
|
||||
self.cost_manager = CostManager(token_costs=BEDROCK_TOKEN_COSTS)
|
||||
if self.config.model in NOT_SUUPORT_STREAM_MODELS:
|
||||
if self.config.model in NOT_SUPPORT_STREAM_MODELS:
|
||||
logger.warning(f"model {self.config.model} doesn't support streaming output!")
|
||||
|
||||
def __init_client(self, service_name: Literal["bedrock-runtime", "bedrock"]):
|
||||
"""initialize boto3 client"""
|
||||
# access key and secret key from https://us-east-1.console.aws.amazon.com/iam
|
||||
self.__credentital_kwargs = {
|
||||
"aws_secret_access_key": self.config.secret_key,
|
||||
"aws_access_key_id": self.config.access_key,
|
||||
"region_name": self.config.region_name,
|
||||
self.__credential_kwargs = {
|
||||
"aws_secret_access_key": os.environ.get("AWS_SECRET_ACCESS_KEY", self.config.secret_key),
|
||||
"aws_access_key_id": os.environ.get("AWS_ACCESS_KEY_ID", self.config.access_key),
|
||||
"aws_session_token": os.environ.get("AWS_SESSION_TOKEN", self.config.session_token),
|
||||
"region_name": os.environ.get("AWS_DEFAULT_REGION", self.config.region_name),
|
||||
}
|
||||
session = boto3.Session(**self.__credentital_kwargs)
|
||||
session = boto3.Session(**self.__credential_kwargs)
|
||||
client = session.client(service_name)
|
||||
return client
|
||||
|
||||
|
|
@ -111,7 +113,7 @@ class BedrockLLM(BaseLLM):
|
|||
return await self.acompletion(messages)
|
||||
|
||||
async def _achat_completion_stream(self, messages: list[dict], timeout=USE_CONFIG_TIMEOUT) -> str:
|
||||
if self.config.model in NOT_SUUPORT_STREAM_MODELS:
|
||||
if self.config.model in NOT_SUPPORT_STREAM_MODELS:
|
||||
rsp = await self.acompletion(messages)
|
||||
full_text = self.get_choice_text(rsp)
|
||||
log_llm_stream(full_text)
|
||||
|
|
|
|||
|
|
@ -103,7 +103,7 @@ class OpenAILLM(BaseLLM):
|
|||
if has_finished:
|
||||
# for oneapi, there has a usage chunk after finish_reason not none chunk
|
||||
if chunk_has_usage:
|
||||
usage = CompletionUsage(**chunk.usage)
|
||||
usage = CompletionUsage(**chunk.usage) if isinstance(chunk.usage, dict) else chunk.usage
|
||||
if finish_reason:
|
||||
if chunk_has_usage:
|
||||
# Some services have usage as an attribute of the chunk, such as Fireworks
|
||||
|
|
|
|||
|
|
@ -8,6 +8,7 @@ from llama_index.core.vector_stores.types import BasePydanticVectorStore
|
|||
from llama_index.vector_stores.chroma import ChromaVectorStore
|
||||
from llama_index.vector_stores.elasticsearch import ElasticsearchStore
|
||||
from llama_index.vector_stores.faiss import FaissVectorStore
|
||||
from llama_index.vector_stores.milvus import MilvusVectorStore
|
||||
|
||||
from metagpt.rag.factories.base import ConfigBasedFactory
|
||||
from metagpt.rag.schema import (
|
||||
|
|
@ -17,6 +18,7 @@ from metagpt.rag.schema import (
|
|||
ElasticsearchIndexConfig,
|
||||
ElasticsearchKeywordIndexConfig,
|
||||
FAISSIndexConfig,
|
||||
MilvusIndexConfig,
|
||||
)
|
||||
|
||||
|
||||
|
|
@ -28,6 +30,7 @@ class RAGIndexFactory(ConfigBasedFactory):
|
|||
BM25IndexConfig: self._create_bm25,
|
||||
ElasticsearchIndexConfig: self._create_es,
|
||||
ElasticsearchKeywordIndexConfig: self._create_es,
|
||||
MilvusIndexConfig: self._create_milvus,
|
||||
}
|
||||
super().__init__(creators)
|
||||
|
||||
|
|
@ -46,6 +49,11 @@ class RAGIndexFactory(ConfigBasedFactory):
|
|||
|
||||
return self._index_from_storage(storage_context=storage_context, config=config, **kwargs)
|
||||
|
||||
def _create_milvus(self, config: MilvusIndexConfig, **kwargs) -> VectorStoreIndex:
|
||||
vector_store = MilvusVectorStore(collection_name=config.collection_name, uri=config.uri, token=config.token)
|
||||
|
||||
return self._index_from_vector_store(vector_store=vector_store, config=config, **kwargs)
|
||||
|
||||
def _create_chroma(self, config: ChromaIndexConfig, **kwargs) -> VectorStoreIndex:
|
||||
db = chromadb.PersistentClient(str(config.persist_path))
|
||||
chroma_collection = db.get_or_create_collection(config.collection_name, metadata=config.metadata)
|
||||
|
|
|
|||
|
|
@ -12,6 +12,7 @@ from llama_index.core.vector_stores.types import BasePydanticVectorStore
|
|||
from llama_index.vector_stores.chroma import ChromaVectorStore
|
||||
from llama_index.vector_stores.elasticsearch import ElasticsearchStore
|
||||
from llama_index.vector_stores.faiss import FaissVectorStore
|
||||
from llama_index.vector_stores.milvus import MilvusVectorStore
|
||||
|
||||
from metagpt.rag.factories.base import ConfigBasedFactory
|
||||
from metagpt.rag.retrievers.base import RAGRetriever
|
||||
|
|
@ -20,6 +21,7 @@ from metagpt.rag.retrievers.chroma_retriever import ChromaRetriever
|
|||
from metagpt.rag.retrievers.es_retriever import ElasticsearchRetriever
|
||||
from metagpt.rag.retrievers.faiss_retriever import FAISSRetriever
|
||||
from metagpt.rag.retrievers.hybrid_retriever import SimpleHybridRetriever
|
||||
from metagpt.rag.retrievers.milvus_retriever import MilvusRetriever
|
||||
from metagpt.rag.schema import (
|
||||
BaseRetrieverConfig,
|
||||
BM25RetrieverConfig,
|
||||
|
|
@ -27,6 +29,7 @@ from metagpt.rag.schema import (
|
|||
ElasticsearchKeywordRetrieverConfig,
|
||||
ElasticsearchRetrieverConfig,
|
||||
FAISSRetrieverConfig,
|
||||
MilvusRetrieverConfig,
|
||||
)
|
||||
|
||||
|
||||
|
|
@ -56,6 +59,7 @@ class RetrieverFactory(ConfigBasedFactory):
|
|||
ChromaRetrieverConfig: self._create_chroma_retriever,
|
||||
ElasticsearchRetrieverConfig: self._create_es_retriever,
|
||||
ElasticsearchKeywordRetrieverConfig: self._create_es_retriever,
|
||||
MilvusRetrieverConfig: self._create_milvus_retriever,
|
||||
}
|
||||
super().__init__(creators)
|
||||
|
||||
|
|
@ -76,6 +80,11 @@ class RetrieverFactory(ConfigBasedFactory):
|
|||
|
||||
return index.as_retriever()
|
||||
|
||||
def _create_milvus_retriever(self, config: MilvusRetrieverConfig, **kwargs) -> MilvusRetriever:
|
||||
config.index = self._build_milvus_index(config, **kwargs)
|
||||
|
||||
return MilvusRetriever(**config.model_dump())
|
||||
|
||||
def _create_faiss_retriever(self, config: FAISSRetrieverConfig, **kwargs) -> FAISSRetriever:
|
||||
config.index = self._build_faiss_index(config, **kwargs)
|
||||
|
||||
|
|
@ -128,6 +137,14 @@ class RetrieverFactory(ConfigBasedFactory):
|
|||
|
||||
return self._build_index_from_vector_store(config, vector_store, **kwargs)
|
||||
|
||||
@get_or_build_index
|
||||
def _build_milvus_index(self, config: MilvusRetrieverConfig, **kwargs) -> VectorStoreIndex:
|
||||
vector_store = MilvusVectorStore(
|
||||
uri=config.uri, collection_name=config.collection_name, token=config.token, dim=config.dimensions
|
||||
)
|
||||
|
||||
return self._build_index_from_vector_store(config, vector_store, **kwargs)
|
||||
|
||||
@get_or_build_index
|
||||
def _build_es_index(self, config: ElasticsearchRetrieverConfig, **kwargs) -> VectorStoreIndex:
|
||||
vector_store = ElasticsearchStore(**config.store_config.model_dump())
|
||||
|
|
|
|||
17
metagpt/rag/retrievers/milvus_retriever.py
Normal file
17
metagpt/rag/retrievers/milvus_retriever.py
Normal file
|
|
@ -0,0 +1,17 @@
|
|||
"""Milvus retriever."""
|
||||
|
||||
from llama_index.core.retrievers import VectorIndexRetriever
|
||||
from llama_index.core.schema import BaseNode
|
||||
|
||||
|
||||
class MilvusRetriever(VectorIndexRetriever):
|
||||
"""Milvus retriever."""
|
||||
|
||||
def add_nodes(self, nodes: list[BaseNode], **kwargs) -> None:
|
||||
"""Support add nodes."""
|
||||
self._index.insert_nodes(nodes, **kwargs)
|
||||
|
||||
def persist(self, persist_dir: str, **kwargs) -> None:
|
||||
"""Support persist.
|
||||
|
||||
Milvus automatically saves, so there is no need to implement."""
|
||||
|
|
@ -62,6 +62,36 @@ class BM25RetrieverConfig(IndexRetrieverConfig):
|
|||
_no_embedding: bool = PrivateAttr(default=True)
|
||||
|
||||
|
||||
class MilvusRetrieverConfig(IndexRetrieverConfig):
|
||||
"""Config for Milvus-based retrievers."""
|
||||
|
||||
uri: str = Field(default="./milvus_local.db", description="The directory to save data.")
|
||||
collection_name: str = Field(default="metagpt", description="The name of the collection.")
|
||||
token: str = Field(default=None, description="The token for Milvus")
|
||||
metadata: Optional[CollectionMetadata] = Field(
|
||||
default=None, description="Optional metadata to associate with the collection"
|
||||
)
|
||||
dimensions: int = Field(default=0, description="Dimensionality of the vectors for Milvus index construction.")
|
||||
|
||||
_embedding_type_to_dimensions: ClassVar[dict[EmbeddingType, int]] = {
|
||||
EmbeddingType.GEMINI: 768,
|
||||
EmbeddingType.OLLAMA: 4096,
|
||||
}
|
||||
|
||||
@model_validator(mode="after")
|
||||
def check_dimensions(self):
|
||||
if self.dimensions == 0:
|
||||
self.dimensions = config.embedding.dimensions or self._embedding_type_to_dimensions.get(
|
||||
config.embedding.api_type, 1536
|
||||
)
|
||||
if not config.embedding.dimensions and config.embedding.api_type not in self._embedding_type_to_dimensions:
|
||||
logger.warning(
|
||||
f"You didn't set dimensions in config when using {config.embedding.api_type}, default to 1536"
|
||||
)
|
||||
|
||||
return self
|
||||
|
||||
|
||||
class ChromaRetrieverConfig(IndexRetrieverConfig):
|
||||
"""Config for Chroma-based retrievers."""
|
||||
|
||||
|
|
@ -170,6 +200,17 @@ class ChromaIndexConfig(VectorIndexConfig):
|
|||
)
|
||||
|
||||
|
||||
class MilvusIndexConfig(VectorIndexConfig):
|
||||
"""Config for milvus-based index."""
|
||||
|
||||
collection_name: str = Field(default="metagpt", description="The name of the collection.")
|
||||
uri: str = Field(default="./milvus_local.db", description="The uri of the index.")
|
||||
token: Optional[str] = Field(default=None, description="The token of the index.")
|
||||
metadata: Optional[CollectionMetadata] = Field(
|
||||
default=None, description="Optional metadata to associate with the collection"
|
||||
)
|
||||
|
||||
|
||||
class BM25IndexConfig(BaseIndexConfig):
|
||||
"""Config for bm25-based index."""
|
||||
|
||||
|
|
|
|||
|
|
@ -12,14 +12,14 @@ typer==0.9.0
|
|||
lancedb==0.4.0
|
||||
loguru==0.6.0
|
||||
meilisearch==0.21.0
|
||||
numpy>=1.24.3
|
||||
openai>=1.6.1
|
||||
openpyxl
|
||||
numpy~=1.26.4
|
||||
openai~=1.39.0
|
||||
openpyxl~=3.1.5
|
||||
beautifulsoup4==4.12.3
|
||||
pandas==2.1.1
|
||||
pydantic>=2.5.3
|
||||
#pygame==2.1.3
|
||||
#pymilvus==2.2.8
|
||||
# pymilvus==2.4.6
|
||||
# pytest==7.2.2 # test extras require
|
||||
python_docx==0.8.11
|
||||
PyYAML==6.0.1
|
||||
|
|
@ -35,6 +35,9 @@ anthropic==0.18.1
|
|||
typing-inspect==0.8.0
|
||||
libcst==1.0.1
|
||||
qdrant-client==1.7.0
|
||||
grpcio~=1.67.0
|
||||
grpcio-tools~=1.62.3
|
||||
grpcio-status~=1.62.3
|
||||
# pytest-mock==3.11.1 # test extras require
|
||||
# open-interpreter==0.1.7; python_version>"3.9" # Conflict with openai 1.x
|
||||
ta==0.10.2
|
||||
|
|
@ -72,10 +75,10 @@ qianfan~=0.4.4
|
|||
dashscope~=1.19.3
|
||||
rank-bm25==0.2.2 # for tool recommendation
|
||||
jieba==0.42.1 # for tool recommendation
|
||||
volcengine-python-sdk[ark]~=1.0.94
|
||||
volcengine-python-sdk[ark]~=1.0.94 # Solution for installation error in Windows: https://github.com/volcengine/volcengine-python-sdk/issues/5
|
||||
# llama-index-vector-stores-elasticsearch~=0.2.5 # Used by `metagpt/memory/longterm_memory.py`
|
||||
# llama-index-vector-stores-chroma~=0.1.10 # Used by `metagpt/memory/longterm_memory.py`
|
||||
gymnasium==0.29.1
|
||||
boto3~=1.34.69
|
||||
spark_ai_python~=0.3.30
|
||||
agentops
|
||||
agentops
|
||||
3
setup.py
3
setup.py
|
|
@ -43,6 +43,7 @@ extras_require = {
|
|||
"llama-index-postprocessor-cohere-rerank==0.1.4",
|
||||
"llama-index-postprocessor-colbert-rerank==0.1.1",
|
||||
"llama-index-postprocessor-flag-embedding-reranker==0.1.2",
|
||||
# "llama-index-vector-stores-milvus==0.1.23",
|
||||
"docx2txt==0.8",
|
||||
],
|
||||
}
|
||||
|
|
@ -60,8 +61,6 @@ extras_require["test"] = [
|
|||
"azure-cognitiveservices-speech~=1.31.0",
|
||||
"aioboto3~=12.4.0",
|
||||
"gradio==3.0.0",
|
||||
"grpcio-status==1.48.2",
|
||||
"grpcio-tools==1.48.2",
|
||||
"google-api-core==2.17.1",
|
||||
"protobuf==3.19.6",
|
||||
"pylint==3.0.3",
|
||||
|
|
|
|||
48
tests/metagpt/document_store/test_milvus_store.py
Normal file
48
tests/metagpt/document_store/test_milvus_store.py
Normal file
|
|
@ -0,0 +1,48 @@
|
|||
import random
|
||||
|
||||
import pytest
|
||||
|
||||
from metagpt.document_store.milvus_store import MilvusConnection, MilvusStore
|
||||
|
||||
seed_value = 42
|
||||
random.seed(seed_value)
|
||||
|
||||
vectors = [[random.random() for _ in range(8)] for _ in range(10)]
|
||||
ids = [f"doc_{i}" for i in range(10)]
|
||||
metadata = [{"color": "red", "rand_number": i % 10} for i in range(10)]
|
||||
|
||||
|
||||
def assert_almost_equal(actual, expected):
|
||||
delta = 1e-10
|
||||
if isinstance(expected, list):
|
||||
assert len(actual) == len(expected)
|
||||
for ac, exp in zip(actual, expected):
|
||||
assert abs(ac - exp) <= delta, f"{ac} is not within {delta} of {exp}"
|
||||
else:
|
||||
assert abs(actual - expected) <= delta, f"{actual} is not within {delta} of {expected}"
|
||||
|
||||
|
||||
@pytest.mark.skip() # Skip because the pymilvus dependency is not installed by default
|
||||
def test_milvus_store():
|
||||
milvus_connection = MilvusConnection(uri="./milvus_local.db")
|
||||
milvus_store = MilvusStore(milvus_connection)
|
||||
|
||||
collection_name = "TestCollection"
|
||||
milvus_store.create_collection(collection_name, dim=8)
|
||||
|
||||
milvus_store.add(collection_name, ids, vectors, metadata)
|
||||
|
||||
search_results = milvus_store.search(collection_name, query=[1.0] * 8)
|
||||
assert len(search_results) > 0
|
||||
first_result = search_results[0]
|
||||
assert first_result["id"] == "doc_0"
|
||||
|
||||
search_results_with_filter = milvus_store.search(collection_name, query=[1.0] * 8, filter={"rand_number": 1})
|
||||
assert len(search_results_with_filter) > 0
|
||||
assert search_results_with_filter[0]["id"] == "doc_1"
|
||||
|
||||
milvus_store.delete(collection_name, _ids=["doc_0"])
|
||||
deleted_results = milvus_store.search(collection_name, query=[1.0] * 8, limit=1)
|
||||
assert deleted_results[0]["id"] != "doc_0"
|
||||
|
||||
milvus_store.client.drop_collection(collection_name)
|
||||
|
|
@ -3,7 +3,7 @@ import json
|
|||
import pytest
|
||||
|
||||
from metagpt.provider.bedrock.utils import (
|
||||
NOT_SUUPORT_STREAM_MODELS,
|
||||
NOT_SUPPORT_STREAM_MODELS,
|
||||
SUPPORT_STREAM_MODELS,
|
||||
)
|
||||
from metagpt.provider.bedrock_api import BedrockLLM
|
||||
|
|
@ -14,7 +14,7 @@ from tests.metagpt.provider.req_resp_const import (
|
|||
)
|
||||
|
||||
# all available model from bedrock
|
||||
models = SUPPORT_STREAM_MODELS | NOT_SUUPORT_STREAM_MODELS
|
||||
models = SUPPORT_STREAM_MODELS | NOT_SUPPORT_STREAM_MODELS
|
||||
messages = [{"role": "user", "content": "Hi!"}]
|
||||
usage = {
|
||||
"prompt_tokens": 1000000,
|
||||
|
|
|
|||
|
|
@ -8,6 +8,7 @@ from metagpt.rag.schema import (
|
|||
ElasticsearchIndexConfig,
|
||||
ElasticsearchStoreConfig,
|
||||
FAISSIndexConfig,
|
||||
MilvusIndexConfig,
|
||||
)
|
||||
|
||||
|
||||
|
|
@ -20,6 +21,10 @@ class TestRAGIndexFactory:
|
|||
def faiss_config(self):
|
||||
return FAISSIndexConfig(persist_path="")
|
||||
|
||||
@pytest.fixture
|
||||
def milvus_config(self):
|
||||
return MilvusIndexConfig(uri="", collection_name="")
|
||||
|
||||
@pytest.fixture
|
||||
def chroma_config(self):
|
||||
return ChromaIndexConfig(persist_path="", collection_name="")
|
||||
|
|
@ -65,6 +70,16 @@ class TestRAGIndexFactory:
|
|||
):
|
||||
self.index_factory.get_index(bm25_config, embed_model=mock_embedding)
|
||||
|
||||
def test_create_milvus_index(self, mocker, milvus_config, mock_from_vector_store, mock_embedding):
|
||||
# Mock
|
||||
mock_milvus_store = mocker.patch("metagpt.rag.factories.index.MilvusVectorStore")
|
||||
|
||||
# Exec
|
||||
self.index_factory.get_index(milvus_config, embed_model=mock_embedding)
|
||||
|
||||
# Assert
|
||||
mock_milvus_store.assert_called_once()
|
||||
|
||||
def test_create_chroma_index(self, mocker, chroma_config, mock_from_vector_store, mock_embedding):
|
||||
# Mock
|
||||
mock_chroma_db = mocker.patch("metagpt.rag.factories.index.chromadb.PersistentClient")
|
||||
|
|
|
|||
|
|
@ -5,6 +5,7 @@ from llama_index.core.embeddings import MockEmbedding
|
|||
from llama_index.core.schema import TextNode
|
||||
from llama_index.vector_stores.chroma import ChromaVectorStore
|
||||
from llama_index.vector_stores.elasticsearch import ElasticsearchStore
|
||||
from llama_index.vector_stores.milvus import MilvusVectorStore
|
||||
|
||||
from metagpt.rag.factories.retriever import RetrieverFactory
|
||||
from metagpt.rag.retrievers.bm25_retriever import DynamicBM25Retriever
|
||||
|
|
@ -12,12 +13,14 @@ from metagpt.rag.retrievers.chroma_retriever import ChromaRetriever
|
|||
from metagpt.rag.retrievers.es_retriever import ElasticsearchRetriever
|
||||
from metagpt.rag.retrievers.faiss_retriever import FAISSRetriever
|
||||
from metagpt.rag.retrievers.hybrid_retriever import SimpleHybridRetriever
|
||||
from metagpt.rag.retrievers.milvus_retriever import MilvusRetriever
|
||||
from metagpt.rag.schema import (
|
||||
BM25RetrieverConfig,
|
||||
ChromaRetrieverConfig,
|
||||
ElasticsearchRetrieverConfig,
|
||||
ElasticsearchStoreConfig,
|
||||
FAISSRetrieverConfig,
|
||||
MilvusRetrieverConfig,
|
||||
)
|
||||
|
||||
|
||||
|
|
@ -41,6 +44,10 @@ class TestRetrieverFactory:
|
|||
def mock_chroma_vector_store(self, mocker):
|
||||
return mocker.MagicMock(spec=ChromaVectorStore)
|
||||
|
||||
@pytest.fixture
|
||||
def mock_milvus_vector_store(self, mocker):
|
||||
return mocker.MagicMock(spec=MilvusVectorStore)
|
||||
|
||||
@pytest.fixture
|
||||
def mock_es_vector_store(self, mocker):
|
||||
return mocker.MagicMock(spec=ElasticsearchStore)
|
||||
|
|
@ -91,6 +98,14 @@ class TestRetrieverFactory:
|
|||
|
||||
assert isinstance(retriever, ChromaRetriever)
|
||||
|
||||
def test_get_retriever_with_milvus_config(self, mocker, mock_milvus_vector_store, mock_embedding):
|
||||
mock_config = MilvusRetrieverConfig(uri="/path/to/milvus.db", collection_name="test_collection")
|
||||
mocker.patch("metagpt.rag.factories.retriever.MilvusVectorStore", return_value=mock_milvus_vector_store)
|
||||
|
||||
retriever = self.retriever_factory.get_retriever(configs=[mock_config], nodes=[], embed_model=mock_embedding)
|
||||
|
||||
assert isinstance(retriever, MilvusRetriever)
|
||||
|
||||
def test_get_retriever_with_es_config(self, mocker, mock_es_vector_store, mock_embedding):
|
||||
mock_config = ElasticsearchRetrieverConfig(store_config=ElasticsearchStoreConfig())
|
||||
mocker.patch("metagpt.rag.factories.retriever.ElasticsearchStore", return_value=mock_es_vector_store)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue