seo搜索引擎优化是通过优化答案,seo的特点是什么,网站域名怎么进行实名认证,为什么不推荐免费建站这篇文章瞄的是AutoGen官方教学文档 Advanced 章节中的 Selector Group Chat 篇章#xff0c;介绍了SelectorGroupChat对象如何从一个Team中选择其中一个Agent与LLM进行对话#xff0c;并且在得到结果后进行二次规划#xff0c;同时你也可以自定义选择函数。本质上还是对Tea…这篇文章瞄的是AutoGen官方教学文档 Advanced 章节中的 Selector Group Chat 篇章介绍了SelectorGroupChat对象如何从一个Team中选择其中一个Agent与LLM进行对话并且在得到结果后进行二次规划同时你也可以自定义选择函数。本质上还是对Team的流程控制。
官网链接https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/selector-group-chat.html# Selector Group Chat
官方展示了一个名为 SelectorGroupChat 的对象是一个Team对象也就是由多个Agent组成的对象和我们之前使用的 RoundRobinGroupChat 是同一类型。它的作用在于内部的每一个Agent都会轮流向其他Agent进行广播消息然后由LLM根据整个Team的上下文环境选择与这个Team中的哪一个Agent进行对话。
SelectorGroupChat 对象的关键特性有以下几点
依靠LLM选择合适的Agent可以配置参与对象于描述防止同一个Agent持续性对话可选可自定义的prompt可自定义选择函数selection function即你也可以不让LLM进行选择而是根据你的选择函数给LLM一个Agent进行对话
相当于之前使用的RoundRobinGroupChat是内部Agent自发向LLM进行对话而SelectorGroupChat是将整个Team的上下文发给LLM然后让LLM或者你自定义的选择函数使用其中一个Agent与LLM对话。 How Does it Work?
SelectorGroupChat之所以能够实现上面提到的选择功能是依靠在 run() 或者 run_stream() 函数中按照下面的步骤执行
Team分析当前对话的上下文包括历史记录、每一个Agent的name和description以此为依据选择下一个与LLM对话的Agent默认情况下不会选择上一次与LLM对话的Agent尽量避免只有一个Agent持续与LLM进行对话除非这个Team中只有一个Agent但也可以通过参数 allow_repeated_speakerTrue 的方式允许Agent持续与LLM对话你也可以通过自定义的选择函数来筛选下一次要和LLM对话的Agent被选中的Agent会将自己的prompt和LLM的response都广播给整个Team中的所有其他Agent只有当终止条件被触发时间才会终止Team否则整个Team会持续运行下去当对话结束时会返回一个 TaskResult 类型其中包含了所有的聊天记录
和RoundRobinGroupChat用法一样一旦任务结束后Team仍然会保留完整的上下文以便你进行二次激活并且可以使用 reset() 函数清空上下文。 Example: Web Search/Analysis
官网在这里给出了一个使用 SelectorGroupChat 进行Web内容搜索和数据分析的任务整个Team的结构如下设计了三个内部Agent Planning Agent将一个复杂任务拆解成简单任务并决策由哪个Agent执行相当于上面提到的选择函数只不过这个Agent用了LLM进行选择Web Search Agent网络内容搜索Agent使用 search_web_tool 工具进行搜索Data Analyst Agent数据分析Agent使用percentage_change_tool工具进行计算
上面提到的两个 search_web_tool 和 percentage_change_tool 定义如下
# Note: This example uses mock tools instead of real APIs for demonstration purposes
def search_web_tool(query: str) - str:if 2006-2007 in query:return Here are the total points scored by Miami Heat players in the 2006-2007 season:Udonis Haslem: 844 pointsDwayne Wade: 1397 pointsJames Posey: 550 points...elif 2007-2008 in query:return The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.elif 2008-2009 in query:return The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.return No data found.def percentage_change_tool(start: float, end: float) - float:return ((end - start) / start) * 100然后就是用 AssistantAgent 来定义上面三个Agent这里官方提示在定义时最重要的是些明白Agent的 name 和 description因为这两个信息会变成LLM选择下一个与其对话的依据。
定义一个基于 gpt-4o 的模型后面三个Agent都要用这个模型接口
model_client OpenAIChatCompletionClient(modelgpt-4o)Planning Agent 任务拆解Agent在这里就是选择对话的Agent
planning_agent AssistantAgent(PlanningAgent,descriptionAn agent for planning tasks, this agent should be the first to engage when given a new task.,model_clientmodel_client,system_messageYou are a planning agent.Your job is to break down complex tasks into smaller, manageable subtasks.Your team members are:WebSearchAgent: Searches for informationDataAnalystAgent: Performs calculationsYou only plan and delegate tasks - you do not execute them yourself.When assigning tasks, use this format:1. agent : taskAfter all tasks are complete, summarize the findings and end with TERMINATE.,
)Web Search Agent 内容搜索Agent调用search_web_tool工具进行搜索
web_search_agent AssistantAgent(WebSearchAgent,descriptionAn agent for searching information on the web.,tools[search_web_tool],model_clientmodel_client,system_messageYou are a web search agent.Your only tool is search_tool - use it to find information.You make only one search call at a time.Once you have the results, you never do calculations based on them.,
)Data Analyst Agen 数据分析Agent调用工具percentage_change_tool对内容进行分析
data_analyst_agent AssistantAgent(DataAnalystAgent,descriptionAn agent for performing calculations.,model_clientmodel_client,tools[percentage_change_tool],system_messageYou are a data analyst.Given the tasks you have been assigned, you should analyze the data and provide results using the tools provided.If you have not seen the data, ask for it.,
)【Note】如果你的工具函数返回的不是自然语言格式的字符串可以在定义Agent的时候使用 reflect_on_tool_useTrue 参数让Agent帮你将字符串整理成自然语言本质还是调用LLM。因为Team内部广播或者沟通的基本单元仍然是一个封装好自然语言的Message。 Workflow
根据官网描述上面定义的Team运行流程如下
SelectorGroupChat 首先接受到一个Task任务然后根据Agent的属性name与descriptions信息 自主选择 最适合的一个Agent来启动整个任务通常情况是 Planning AgentPlanning Agent将这个Task拆分成子任务然后按照 Agent:task 的格式分发给对应的Agent根据整个Team中的上线文环境、各个Agent的descriptionsSelectorGroupChat 动态选择下一个与LLM进行对话的AgentWeb Search Agent执行一次搜索动作并将LLM返回的结果保存在共享的记录中如果Data Analyst Agent被选中那么就使用tools来处理数据整个Team的终止条件是如果子任务中检测到TERMINATE 或者其他终止条件
【注意】在自定义Agent的时候尽量将descriptions写成 精炼、完备、排他因为SelectorGroupChat 会根据Team内的所有Agent的描述进行决策下一个与LLM对话的是哪个Agent Termination Conditions
官方在这里定义了两个终止条件TextMentionTermination和MaxMessageTermination这两个终止条件我们在前面已经用了很多次了分别是文本关键字终止和最大组内沟通信息条数终止
text_mention_termination TextMentionTermination(TERMINATE)
max_messages_termination MaxMessageTermination(max_messages25)
termination text_mention_termination | max_messages_terminationSelector Prompt
SelectorGroupChat 基于组内的上下文环境来选择下一个与LLM对话的Agent因此这里我们自己写一个prompt来告诉SelectorGroupChat 选择Agent的依据是什么
selector_prompt Select an agent to perform task.{roles}Current conversation context:
{history}Read the above conversation, then select an agent from {participants} to perform the next task.
Make sure the planner agent has assigned tasks before other agents start working.
Only select one agent.官网在如何设置这个prompt时给了以下几个Tips
这个提示词不要写的太长防止选择器过载如何判断自己提示词是不是过长了这个是根据LLM模型规模决定的如果你使用的模型是GPT-4o的话就可以写稍微长一点但模型规模较小时就不能太长官方提供的上面demo就是对于小模型设计的如果你对每一个Agent都写了多个条件那么其实最适合的是使用自定义选择函数由SelectorGroupChat自主选择的初衷是减少你的工作量 Running the Team
然后将上面我们提到的Agent、终止条件、自定义选择prompt结合起来形成一个Team
team SelectorGroupChat([planning_agent, web_search_agent, data_analyst_agent],model_clientmodel_client,termination_conditiontermination,selector_promptselector_prompt,allow_repeated_speakerTrue, # Allow an agent to speak multiple turns in a row.
)然后再定义一个传给Team的任务
task Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?那么完整代码如下
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_agentchat.conditions import TextMentionTermination, MaxMessageTermination
from autogen_agentchat.teams import SelectorGroupChat
from autogen_agentchat.ui import Consoleimport asyncio, osos.environ[OPENAI_API_KEY] 你的OpenAI API Key#-----------------------------------------------------------------------------#
# Part1. 定义两个搜索工具
def search_web_tool(query: str) - str:if 2006-2007 in query:return Here are the total points scored by Miami Heat players in the 2006-2007 season:Udonis Haslem: 844 pointsDwayne Wade: 1397 pointsJames Posey: 550 points...elif 2007-2008 in query:return The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.elif 2008-2009 in query:return The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.return No data found.def percentage_change_tool(start: float, end: float) - float:return ((end - start) / start) * 100#-----------------------------------------------------------------------------#
# Part2. 定义三个Agent和model
model_client OpenAIChatCompletionClient(modelgpt-4o)planning_agent AssistantAgent(PlanningAgent,descriptionAn agent for planning tasks, this agent should be the first to engage when given a new task.,model_clientmodel_client,system_messageYou are a planning agent.Your job is to break down complex tasks into smaller, manageable subtasks.Your team members are:WebSearchAgent: Searches for informationDataAnalystAgent: Performs calculationsYou only plan and delegate tasks - you do not execute them yourself.When assigning tasks, use this format:1. agent : taskAfter all tasks are complete, summarize the findings and end with TERMINATE.,
)web_search_agent AssistantAgent(WebSearchAgent,descriptionAn agent for searching information on the web.,tools[search_web_tool],model_clientmodel_client,system_messageYou are a web search agent.Your only tool is search_tool - use it to find information.You make only one search call at a time.Once you have the results, you never do calculations based on them.,
)data_analyst_agent AssistantAgent(DataAnalystAgent,descriptionAn agent for performing calculations.,model_clientmodel_client,tools[percentage_change_tool],system_messageYou are a data analyst.Given the tasks you have been assigned, you should analyze the data and provide results using the tools provided.If you have not seen the data, ask for it.,
)#-----------------------------------------------------------------------------#
# Part3. 定义Team的终止条件
text_mention_termination TextMentionTermination(TERMINATE)
max_messages_termination MaxMessageTermination(max_messages25)
termination text_mention_termination | max_messages_terminationselector_prompt Select an agent to perform task.{roles}Current conversation context:
{history}Read the above conversation, then select an agent from {participants} to perform the next task.
Make sure the planner agent has assigned tasks before other agents start working.
Only select one agent.
#-----------------------------------------------------------------------------#
# Part4. 定义任务Task
task Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?#-----------------------------------------------------------------------------#
# Part5. 将Agent、model、终止条件、prompt组合成一个team
team SelectorGroupChat([planning_agent, web_search_agent, data_analyst_agent],model_clientmodel_client,termination_conditiontermination,selector_promptselector_prompt,allow_repeated_speakerTrue, # Allow an agent to speak multiple turns in a row.
)#-----------------------------------------------------------------------------#
# Part6. 运行team
asyncio.run(Console(team.run_stream(tasktask))
)运行结果如下从输出内容来看除了实际执行的部分其他都是Team内部上下文同步的过程感兴趣的可以自己运行看看他们的同步逻辑
$ python demo.pyCustom Selector Function
上面提到了你也可以自定义选择函数但如果你自定义的选择函数返回的是 None 对象那么 SelectorGroupChat 仍然会使用基于LLM模型的Agent选择。
这里官方demo中自定义选择函数非常简单当组内最新的消息不是由PlanningAgent生成时就直接调用PlanningAgent否则让LLM来选择实际上就是每执行一步都让PlanningAgent重新规划一下
def selector_func(messages: Sequence[AgentEvent | ChatMessage]) - str | None:if messages[-1].source ! planning_agent.name:return planning_agent.namereturn None然后需要在定义Team的时候就将选择函数设置进去
team SelectorGroupChat([planning_agent, web_search_agent, data_analyst_agent],model_clientmodel_client,termination_conditiontermination,selector_promptselector_prompt,allow_repeated_speakerTrue,selector_funcselector_func,
)完成代码如下
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_agentchat.conditions import TextMentionTermination, MaxMessageTermination
from autogen_agentchat.teams import SelectorGroupChat
from autogen_agentchat.ui import Console
from autogen_agentchat.messages import ChatMessage, AgentEvent
from typing import Sequenceimport asyncio, osos.environ[OPENAI_API_KEY] 你的OpenAI API Keydef search_web_tool(query: str) - str:if 2006-2007 in query:return Here are the total points scored by Miami Heat players in the 2006-2007 season:Udonis Haslem: 844 pointsDwayne Wade: 1397 pointsJames Posey: 550 points...elif 2007-2008 in query:return The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.elif 2008-2009 in query:return The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.return No data found.def percentage_change_tool(start: float, end: float) - float:return ((end - start) / start) * 100model_client OpenAIChatCompletionClient(modelgpt-4o)planning_agent AssistantAgent(PlanningAgent,descriptionAn agent for planning tasks, this agent should be the first to engage when given a new task.,model_clientmodel_client,system_messageYou are a planning agent.Your job is to break down complex tasks into smaller, manageable subtasks.Your team members are:WebSearchAgent: Searches for informationDataAnalystAgent: Performs calculationsYou only plan and delegate tasks - you do not execute them yourself.When assigning tasks, use this format:1. agent : taskAfter all tasks are complete, summarize the findings and end with TERMINATE.,
)web_search_agent AssistantAgent(WebSearchAgent,descriptionAn agent for searching information on the web.,tools[search_web_tool],model_clientmodel_client,system_messageYou are a web search agent.Your only tool is search_tool - use it to find information.You make only one search call at a time.Once you have the results, you never do calculations based on them.,
)data_analyst_agent AssistantAgent(DataAnalystAgent,descriptionAn agent for performing calculations.,model_clientmodel_client,tools[percentage_change_tool],system_messageYou are a data analyst.Given the tasks you have been assigned, you should analyze the data and provide results using the tools provided.If you have not seen the data, ask for it.,
)text_mention_termination TextMentionTermination(TERMINATE)
max_messages_termination MaxMessageTermination(max_messages25)
termination text_mention_termination | max_messages_terminationselector_prompt Select an agent to perform task.{roles}Current conversation context:
{history}Read the above conversation, then select an agent from {participants} to perform the next task.
Make sure the planner agent has assigned tasks before other agents start working.
Only select one agent.
task Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?# 上面部分完全一致
#-----------------------------------------------------------------------------#
# Part1. 定义选择函数
def selector_func(messages: Sequence[AgentEvent | ChatMessage]) - str | None:if messages[-1].source ! planning_agent.name:return planning_agent.namereturn None# Part2. 设置team使用自己的选择函数
team SelectorGroupChat([planning_agent, web_search_agent, data_analyst_agent],model_clientmodel_client,termination_conditiontermination,selector_promptselector_prompt,allow_repeated_speakerTrue,selector_funcselector_func,
)# Part3. 运行team
asyncio.run(Console(team.run_stream(tasktask))
)运行结果如下
$ python demo.pyUser Feedback
在之前的文章 AutoGen学习笔记系列五Tutorial -Human-in-the-Loop 中提到了 “人在回路” 策略让人在Team走向的 关键节点 上让人来决策。在这里我们同样可以使用 UserProxyAgent 将人在回路策略引入 SelectorGroupChat 中
首先定义 UserProxyAgent 和选择函数在选择函数中使用 Agent 以实现人在回路这里的逻辑如下
首先第一次使用 PlanningAgent 激活整个Team的TaskPlanningAgent通过LLM得到下一个想要执行的Agent名由人来确认是否使用这个Agent允许就输入APPROVE否则会打回给LLM重新选择一个再来确认
# 定义 UserProxyAgent
user_proxy_agent UserProxyAgent(UserProxyAgent, descriptionA proxy for the user to approve or disapprove tasks.)# 定义使用 UserProxyAgent 的选择函数
def selector_func_with_user_proxy(messages: Sequence[AgentEvent | ChatMessage]) - str | None:if messages[-1].source ! planning_agent.name and messages[-1].source ! user_proxy_agent.name:# 必须让PlanningAgent作为第一个被调用的否则任务无法启动return planning_agent.nameif messages[-1].source planning_agent.name:if messages[-2].source user_proxy_agent.name and APPROVE in messages[-1].content.upper(): # type: ignore# 如果检测到了人输入的 APPROVE 则确认下一个Agent是被被使用return Nonereturn user_proxy_agent.nameif messages[-1].source user_proxy_agent.name:# 如果人输入的不是 APPROVE 则让 PlanningAgent重新选择if APPROVE not in messages[-1].content.upper(): # type: ignorereturn planning_agent.namereturn None完整代码如下
from autogen_agentchat.agents import AssistantAgent, UserProxyAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_agentchat.conditions import TextMentionTermination, MaxMessageTermination
from autogen_agentchat.teams import SelectorGroupChat
from autogen_agentchat.ui import Console
from autogen_agentchat.messages import ChatMessage, AgentEvent
from typing import Sequenceimport asyncio, osos.environ[OPENAI_API_KEY] 你的OpenAI API Keydef search_web_tool(query: str) - str:if 2006-2007 in query:return Here are the total points scored by Miami Heat players in the 2006-2007 season:Udonis Haslem: 844 pointsDwayne Wade: 1397 pointsJames Posey: 550 points...elif 2007-2008 in query:return The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.elif 2008-2009 in query:return The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.return No data found.def percentage_change_tool(start: float, end: float) - float:return ((end - start) / start) * 100model_client OpenAIChatCompletionClient(modelgpt-4o)planning_agent AssistantAgent(PlanningAgent,descriptionAn agent for planning tasks, this agent should be the first to engage when given a new task.,model_clientmodel_client,system_messageYou are a planning agent.Your job is to break down complex tasks into smaller, manageable subtasks.Your team members are:WebSearchAgent: Searches for informationDataAnalystAgent: Performs calculationsYou only plan and delegate tasks - you do not execute them yourself.When assigning tasks, use this format:1. agent : taskAfter all tasks are complete, summarize the findings and end with TERMINATE.,
)web_search_agent AssistantAgent(WebSearchAgent,descriptionAn agent for searching information on the web.,tools[search_web_tool],model_clientmodel_client,system_messageYou are a web search agent.Your only tool is search_tool - use it to find information.You make only one search call at a time.Once you have the results, you never do calculations based on them.,
)data_analyst_agent AssistantAgent(DataAnalystAgent,descriptionAn agent for performing calculations.,model_clientmodel_client,tools[percentage_change_tool],system_messageYou are a data analyst.Given the tasks you have been assigned, you should analyze the data and provide results using the tools provided.If you have not seen the data, ask for it.,
)text_mention_termination TextMentionTermination(TERMINATE)
max_messages_termination MaxMessageTermination(max_messages25)
termination text_mention_termination | max_messages_terminationselector_prompt Select an agent to perform task.{roles}Current conversation context:
{history}Read the above conversation, then select an agent from {participants} to perform the next task.
Make sure the planner agent has assigned tasks before other agents start working.
Only select one agent.
task Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?# 上面部分完全一致
#-----------------------------------------------------------------------------#
# Part1. 定义 UserProxyAgent
user_proxy_agent UserProxyAgent(UserProxyAgent, descriptionA proxy for the user to approve or disapprove tasks.)# Part2. 定义使用 UserProxyAgent 的选择函数
def selector_func_with_user_proxy(messages: Sequence[AgentEvent | ChatMessage]) - str | None:if messages[-1].source ! planning_agent.name and messages[-1].source ! user_proxy_agent.name:return planning_agent.nameif messages[-1].source planning_agent.name:if messages[-2].source user_proxy_agent.name and APPROVE in messages[-1].content.upper(): # type: ignorereturn Nonereturn user_proxy_agent.nameif messages[-1].source user_proxy_agent.name:if APPROVE not in messages[-1].content.upper(): # type: ignorereturn planning_agent.namereturn None# Part2. 设置team使用自己的选择函数
team SelectorGroupChat([planning_agent, web_search_agent, data_analyst_agent, user_proxy_agent],model_clientmodel_client,termination_conditiontermination,selector_promptselector_prompt,selector_funcselector_func_with_user_proxy,allow_repeated_speakerTrue,
)# Part3. 运行team
asyncio.run(Console(team.run_stream(tasktask))
)运行结果如下可以发现每到选择Agent的时候都会等待人进行决策
$ python demo.pyUsing Reasoning Models
上面所有的demo都是基于 gpt-4o 或 Gemini 这种满血大模型根据上面小节 Selector Prompt 提到的几个 tips 内容对于像 o3-mini 这种小模型而言还是要尽可能写短描述选择的prompt而是让模型自行决策这样可以减小模型本身的压力。官方在下面的示例中使用 o3-mini 作为模型
from autogen_agentchat.agents import AssistantAgent, UserProxyAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_agentchat.conditions import TextMentionTermination, MaxMessageTermination
from autogen_agentchat.teams import SelectorGroupChat
from autogen_agentchat.ui import Console
from autogen_agentchat.messages import ChatMessage, AgentEvent
from typing import Sequenceimport asyncio, osos.environ[OPENAI_API_KEY] 你的OpenAI API Keydef search_web_tool(query: str) - str:if 2006-2007 in query:return Here are the total points scored by Miami Heat players in the 2006-2007 season:Udonis Haslem: 844 pointsDwayne Wade: 1397 pointsJames Posey: 550 points...elif 2007-2008 in query:return The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.elif 2008-2009 in query:return The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.return No data found.def percentage_change_tool(start: float, end: float) - float:return ((end - start) / start) * 100text_mention_termination TextMentionTermination(TERMINATE)
max_messages_termination MaxMessageTermination(max_messages25)
termination text_mention_termination | max_messages_terminationtask Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?# 上面部分完全一致
#-----------------------------------------------------------------------------#
model_client OpenAIChatCompletionClient(modelo3-mini)web_search_agent AssistantAgent(WebSearchAgent,descriptionAn agent for searching information on the web.,tools[search_web_tool],model_clientmodel_client,system_messageUse web search tool to find information.,
)data_analyst_agent AssistantAgent(DataAnalystAgent,descriptionAn agent for performing calculations.,model_clientmodel_client,tools[percentage_change_tool],system_messageUse tool to perform calculation. If you have not seen the data, ask for it.,
)user_proxy_agent UserProxyAgent(UserProxyAgent,descriptionA user to approve or disapprove tasks.,
)selector_prompt Select an agent to perform task.
{roles}Current conversation context:
{history}Read the above conversation, then select an agent from {participants} to perform the next task.
When the task is complete, let the user approve or disapprove the task.
team SelectorGroupChat([web_search_agent, data_analyst_agent, user_proxy_agent],model_clientmodel_client,termination_conditiontermination, # Use the same termination condition as before.selector_promptselector_prompt,allow_repeated_speakerTrue,
)# Part3. 运行team
asyncio.run(Console(team.run_stream(tasktask))
)运行结果如下如果你运行的话会发现这个过程慢了不少而且很容易出现一个Agent不停被循环调用的情况大小模型之间的差异还是很明显的
$ python demo.py
