AutoGen-构建问答智能体

news2025/3/15 15:19:56

概述

如https://github.com/microsoft/autogen所述，autogen是一多智能体的框架，属于微软旗下的产品。

依靠AutoGen我们可以快速构建出一个多智能体应用，以满足我们各种业务场景。

环境说明

python，3.10
AutoGen，0.4.2
chainlit，2.0.2
大模型，deepseek

安装依赖

pip install autogen-agentchat openai autogen-ext

使用UI交互界面为Chainlit 安装chainlit命令

pip install chainlit

3.示例一，聊天机器人

应用场景：创建一个聊天机器人，让他给你回复

代码

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @File    : ai_hub.py
# @Software: PyCharm
import chainlit as cl
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_ext.models.openai import OpenAIChatCompletionClient

@cl.on_chat_start
async def main():
    await cl.Message(content="sir 我是贾维斯，有什么可以帮您？").send()

async def run_team(query: str):
    model_client = OpenAIChatCompletionClient(model="deepseek-chat", base_url="https://api.deepseek.com",api_key="YOU DEEPSEEK API KEY", model_info={
            "vision": False,
            "function_calling": False,
            "json_output": True,
            "family": "unknown",
        }, )
    assistant_agent = AssistantAgent("assistant", model_client=model_client,
                                     system_message="你是一个机器人，请根据你所会的知识与用户进行友好交流！")
    team = RoundRobinGroupChat(participants=[assistant_agent], max_turns=1)
    response_stream = team.run_stream(task=query)
    async for msg in response_stream:
        if hasattr(msg, "source") and msg.source != "user" and hasattr(msg, "content"):
            msg = cl.Message(content=msg.content, author="Agent Team")
            await msg.send()

@cl.on_message
async def main(message: cl.Message):
    await run_team(message.content)

启动机器人

chainlit run .\ai_hub.py -w

结果及界面