项目地址： GitHub - datawhalechina/hugging-multi-agent: A tutorial to quickly help you understand the concept of agent and muti-agent and get started with coding development

AutoDL租用实例

conda环境配置

逐行输入以下三条命令：

bash

conda create -n metagpt python=3.9

conda activate metagpt

metagpt安装

(0.6.6版本): 时间比较久

pip install metagpt==0.6.6

智谱AI API获取与配置

API获取，请登录智谱AI官网（智谱AI开放平台）申请使用权限。

新建metagpt文件夹，进入metagpt文件夹内并新建config文件夹，在config文件夹内创建config.yaml并填写以下内容（ZHIPU_API_KEY替换为自己的key）：

mkdir metagpt
cd metagpt
mkdir config
cd config
vim config.yaml

角色对话demo

在metagpt目录下，创建demo.py，复制以下代码：

import asyncio

from metagpt.actions import Action
from metagpt.environment import Environment
from metagpt.roles import Role
from metagpt.team import Team

from metagpt.const import DEFAULT_WORKSPACE_ROOT, METAGPT_ROOT, OPTIONS
default_yaml_file = METAGPT_ROOT / "config/config.yaml"
print(METAGPT_ROOT / "config/config.yaml")

action1 = Action(name="AlexSay", instruction="Express your opinion with emotion and don't repeat it")
action2 = Action(name="BobSay", instruction="Express your opinion with emotion and don't repeat it")
alex = Role(name="Alex", profile="Democratic candidate", goal="Win the election", actions=[action1], watch=[action2])
bob = Role(name="Bob", profile="Republican candidate", goal="Win the election", actions=[action2], watch=[action1])
env = Environment(desc="US election live broadcast")
team = Team(investment=10.0, env=env, roles=[alex, bob])

asyncio.run(team.run(idea="Topic: climate change. Under 80 words per message.", send_to="Alex", n_round=5))

运行demo

python demo.py

可以看到，demo中包含了AI，Alex和Bob三位角色进行的对话。