Selector Group Chat#
SelectorGroupChat implements a team where participants take turns broadcasting messages to all other members. A generative model (e.g., an LLM) selects the next speaker based on the shared context, enabling dynamic, context-aware collaboration.
Key features include:
Model-based speaker selection
Configurable participant roles and descriptions
Prevention of consecutive turns by the same speaker (optional)
Customizable selection prompting
Customizable selection function to override the default model-based selection
Note
SelectorGroupChat is a high-level API. For more control and customization, refer to the Group Chat Pattern in the Core API documentation to implement your own group chat logic.
How Does it Work?#
SelectorGroupChat is a group chat similar to RoundRobinGroupChat,
but with a model-based next speaker selection mechanism.
When the team receives a task through run() or run_stream(),
the following steps are executed:
The team analyzes the current conversation context, including the conversation history and participants’
nameanddescriptionattributes, to determine the next speaker using a model. By default, the team will not select the same speak consecutively unless it is the only agent available. This can be changed by settingallow_repeated_speaker=True. You can also override the model by providing a custom selection function.The team prompts the selected speaker agent to provide a response, which is then broadcasted to all other participants.
The termination condition is checked to determine if the conversation should end, if not, the process repeats from step 1.
When the conversation ends, the team returns the
TaskResultcontaining the conversation history from this task.
Once the team finishes the task, the conversation context is kept within the team and all participants, so the next task can continue from the previous conversation context.
You can reset the conversation context by calling reset().
In this section, we will demonstrate how to use SelectorGroupChat with a simple example for a web search and data analysis task.
Example: Web Search/Analysis#
from typing import Sequence
from autogen_agentchat.agents import AssistantAgent, UserProxyAgent
from autogen_agentchat.conditions import MaxMessageTermination, TextMentionTermination
from autogen_agentchat.messages import AgentEvent, ChatMessage
from autogen_agentchat.teams import SelectorGroupChat
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient
Agents#
This system uses three specialized agents:
Planning Agent: The strategic coordinator that breaks down complex tasks into manageable subtasks.
Web Search Agent: An information retrieval specialist that interfaces with the
search_web_tool.Data Analyst Agent: An agent specialist in performing calculations equipped with
percentage_change_tool.
The tools search_web_tool and percentage_change_tool are external tools that the agents can use to perform their tasks.
# 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 points
Dwayne Wade: 1397 points
James 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
Let’s create the specialized agents using the AssistantAgent class.
It is important to note that the agents’ name and description attributes are used by the model to determine the next speaker,
so it is recommended to provide meaningful names and descriptions.
model_client = OpenAIChatCompletionClient(model="gpt-4o")
planning_agent = AssistantAgent(
"PlanningAgent",
description="An agent for planning tasks, this agent should be the first to engage when given a new task.",
model_client=model_client,
system_message="""
You are a planning agent.
Your job is to break down complex tasks into smaller, manageable subtasks.
Your team members are:
WebSearchAgent: Searches for information
DataAnalystAgent: Performs calculations
You only plan and delegate tasks - you do not execute them yourself.
When assigning tasks, use this format:
1. <agent> : <task>
After all tasks are complete, summarize the findings and end with "TERMINATE".
""",
)
web_search_agent = AssistantAgent(
"WebSearchAgent",
description="An agent for searching information on the web.",
tools=[search_web_tool],
model_client=model_client,
system_message="""
You 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",
description="An agent for performing calculations.",
model_client=model_client,
tools=[percentage_change_tool],
system_message="""
You 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
By default, AssistantAgent returns the
tool output as the response. If your tool does not return a well-formed
string in natural language format, you may want to add a reflection step
within the agent by setting reflect_on_tool_use=True when creating the agent.
This will allow the agent to reflect on the tool output and provide a natural
language response.
Workflow#
The task is received by the
SelectorGroupChatwhich, based on agent descriptions, selects the most appropriate agent to handle the initial task (typically the Planning Agent).The Planning Agent analyzes the task and breaks it down into subtasks, assigning each to the most appropriate agent using the format:
<agent> : <task>Based on the conversation context and agent descriptions, the
SelectorGroupChatmanager dynamically selects the next agent to handle their assigned subtask.The Web Search Agent performs searches one at a time, storing results in the shared conversation history.
The Data Analyst processes the gathered information using available calculation tools when selected.
The workflow continues with agents being dynamically selected until either:
The Planning Agent determines all subtasks are complete and sends “TERMINATE”
An alternative termination condition is met (e.g., a maximum number of messages)
When defining your agents, make sure to include a helpful description since this is used to decide which agent to select next.
Termination Conditions#
Let’s use two termination conditions:
TextMentionTermination to end the conversation when the Planning Agent sends “TERMINATE”,
and MaxMessageTermination to limit the conversation to 25 messages to avoid infinite loop.
text_mention_termination = TextMentionTermination("TERMINATE")
max_messages_termination = MaxMessageTermination(max_messages=25)
termination = text_mention_termination | max_messages_termination
Selector Prompt#
SelectorGroupChat uses a model to select
the next speaker based on the conversation context.
We will use a custom selector prompt to properly align with the workflow.
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.
"""
Running the Team#
Let’s create the team with the agents, termination conditions, and custom selector prompt.
team = SelectorGroupChat(
[planning_agent, web_search_agent, data_analyst_agent],
model_client=model_client,
termination_condition=termination,
selector_prompt=selector_prompt,
allow_repeated_speaker=True, # Allow an agent to speak multiple turns in a row.
)
Now we run the team with a task to find information about an NBA player.
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?"
# Use asyncio.run(...) if you are running this in a script.
await Console(team.run_stream(task=task))
---------- user ----------
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?
---------- PlanningAgent ----------
To answer this question, we'll need to break it down into the following tasks:
1. WebSearchAgent: Investigate who was the Miami Heat player with the highest points scored in the 2006-2007 NBA season.
2. WebSearchAgent: Gather statistics for the player's total rebounds during the 2007-2008 NBA season.
3. WebSearchAgent: Collect statistics for the same player's total rebounds during the 2008-2009 NBA season.
4. DataAnalystAgent: Calculate the percentage change in total rebounds for the player between the 2007-2008 and 2008-2009 seasons.
Let's begin by gathering the necessary data.
1. WebSearchAgent: Investigate who was the Miami Heat player with the highest points scored in the 2006-2007 NBA season.
---------- WebSearchAgent ----------
[FunctionCall(id='call_knPrF0edlVal8opo7AMMU8Z0', arguments='{"query":"Miami Heat highest points scorer 2006-2007 NBA season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n Udonis Haslem: 844 points\n Dwayne Wade: 1397 points\n James Posey: 550 points\n ...\n ', call_id='call_knPrF0edlVal8opo7AMMU8Z0')]
---------- WebSearchAgent ----------
Here are the total points scored by Miami Heat players in the 2006-2007 season:
Udonis Haslem: 844 points
Dwayne Wade: 1397 points
James Posey: 550 points
...
---------- WebSearchAgent ----------
[FunctionCall(id='call_KOP1aR8O2kLGIeAkaUa8dE8u', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 season"}', name='search_web_tool'), FunctionCall(id='call_Hk9j3wvryEhlKpe0YOUgXO46', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', call_id='call_KOP1aR8O2kLGIeAkaUa8dE8u'), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_Hk9j3wvryEhlKpe0YOUgXO46')]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.
The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.
/Users/ekzhu/autogen/python/packages/autogen-agentchat/src/autogen_agentchat/agents/_assistant_agent.py:415: UserWarning: Both tool_calls and content are present in the message. This is unexpected. content will be ignored, tool_calls will be used.
model_result = await self._model_client.create(
---------- DataAnalystAgent ----------
[FunctionCall(id='call_By2X8HJjd7K0B3qKSOti1vJ8', arguments='{"start":214,"end":398}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='85.98130841121495', call_id='call_By2X8HJjd7K0B3qKSOti1vJ8')]
---------- DataAnalystAgent ----------
85.98130841121495
---------- PlanningAgent ----------
To summarize:
- The Miami Heat player with the highest points in the 2006-2007 season was Dwyane Wade, with a total of 1,397 points.
- The percentage change in Dwyane Wade's total rebounds from the 2007-2008 season to the 2008-2009 season is approximately 85.98%.
TERMINATE
TaskResult(messages=[TextMessage(source='user', models_usage=None, content='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?', type='TextMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=161, completion_tokens=169), content="To answer this question, we'll need to break it down into the following tasks:\n\n1. WebSearchAgent: Investigate who was the Miami Heat player with the highest points scored in the 2006-2007 NBA season.\n2. WebSearchAgent: Gather statistics for the player's total rebounds during the 2007-2008 NBA season.\n3. WebSearchAgent: Collect statistics for the same player's total rebounds during the 2008-2009 NBA season.\n4. DataAnalystAgent: Calculate the percentage change in total rebounds for the player between the 2007-2008 and 2008-2009 seasons.\n\nLet's begin by gathering the necessary data. \n\n1. WebSearchAgent: Investigate who was the Miami Heat player with the highest points scored in the 2006-2007 NBA season.", type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=317, completion_tokens=28), content=[FunctionCall(id='call_knPrF0edlVal8opo7AMMU8Z0', arguments='{"query":"Miami Heat highest points scorer 2006-2007 NBA season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n Udonis Haslem: 844 points\n Dwayne Wade: 1397 points\n James Posey: 550 points\n ...\n ', call_id='call_knPrF0edlVal8opo7AMMU8Z0')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n Udonis Haslem: 844 points\n Dwayne Wade: 1397 points\n James Posey: 550 points\n ...\n ', type='ToolCallSummaryMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=410, completion_tokens=142), content=[FunctionCall(id='call_KOP1aR8O2kLGIeAkaUa8dE8u', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 season"}', name='search_web_tool'), FunctionCall(id='call_Hk9j3wvryEhlKpe0YOUgXO46', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', call_id='call_KOP1aR8O2kLGIeAkaUa8dE8u'), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_Hk9j3wvryEhlKpe0YOUgXO46')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.\nThe number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', type='ToolCallSummaryMessage'), ToolCallRequestEvent(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=437, completion_tokens=21), content=[FunctionCall(id='call_By2X8HJjd7K0B3qKSOti1vJ8', arguments='{"start":214,"end":398}', name='percentage_change_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='DataAnalystAgent', models_usage=None, content=[FunctionExecutionResult(content='85.98130841121495', call_id='call_By2X8HJjd7K0B3qKSOti1vJ8')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, content='85.98130841121495', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=469, completion_tokens=79), content="To summarize: \n\n- The Miami Heat player with the highest points in the 2006-2007 season was Dwyane Wade, with a total of 1,397 points.\n- The percentage change in Dwyane Wade's total rebounds from the 2007-2008 season to the 2008-2009 season is approximately 85.98%.\n\nTERMINATE", type='TextMessage')], stop_reason="Text 'TERMINATE' mentioned")
As we can see, after the Web Search Agent conducts the necessary searches and the Data Analyst Agent completes the necessary calculations, we find that Dwayne Wade was the Miami Heat player with the highest points in the 2006-2007 season, and the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons is 85.98%!
Custom Selector Function#
Often times we want better control over the selection process.
To this end, we can set the selector_func argument with a custom selector function to override the default model-based selection.
For instance, we want the Planning Agent to speak immediately after any specialized agent to check the progress.
Note
Returning None from the custom selector function will use the default model-based selection.
def selector_func(messages: Sequence[AgentEvent | ChatMessage]) -> str | None:
if messages[-1].source != planning_agent.name:
return planning_agent.name
return None
# Reset the previous team and run the chat again with the selector function.
await team.reset()
team = SelectorGroupChat(
[planning_agent, web_search_agent, data_analyst_agent],
model_client=model_client,
termination_condition=termination,
selector_prompt=selector_prompt,
allow_repeated_speaker=True,
selector_func=selector_func,
)
await Console(team.run_stream(task=task))
---------- user ----------
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?
---------- PlanningAgent ----------
To answer this question, we need to follow these steps:
1. Identify the Miami Heat player with the highest points in the 2006-2007 season.
2. Retrieve the total rebounds of that player for the 2007-2008 and 2008-2009 seasons.
3. Calculate the percentage change in his total rebounds between the two seasons.
Let's delegate these tasks:
1. WebSearchAgent: Find the Miami Heat player with the highest points in the 2006-2007 NBA season.
2. WebSearchAgent: Retrieve the total rebounds for the identified player during the 2007-2008 NBA season.
3. WebSearchAgent: Retrieve the total rebounds for the identified player during the 2008-2009 NBA season.
4. DataAnalystAgent: Calculate the percentage change in total rebounds between the 2007-2008 and 2008-2009 seasons for the player found.
---------- WebSearchAgent ----------
[FunctionCall(id='call_Pz82ndNLSV4cH0Sg6g7ArP4L', arguments='{"query":"Miami Heat player highest points 2006-2007 season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n Udonis Haslem: 844 points\n Dwayne Wade: 1397 points\n James Posey: 550 points\n ...\n ', call_id='call_Pz82ndNLSV4cH0Sg6g7ArP4L')]
---------- WebSearchAgent ----------
Here are the total points scored by Miami Heat players in the 2006-2007 season:
Udonis Haslem: 844 points
Dwayne Wade: 1397 points
James Posey: 550 points
...
---------- PlanningAgent ----------
Great! Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season. Now, let's continue with the next tasks:
2. WebSearchAgent: Retrieve the total rebounds for Dwyane Wade during the 2007-2008 NBA season.
3. WebSearchAgent: Retrieve the total rebounds for Dwyane Wade during the 2008-2009 NBA season.
---------- WebSearchAgent ----------
[FunctionCall(id='call_3qv9so2DXFZIHtzqDIfXoFID', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 season"}', name='search_web_tool'), FunctionCall(id='call_Vh7zzzWUeiUAvaYjP0If0k1k', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', call_id='call_3qv9so2DXFZIHtzqDIfXoFID'), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_Vh7zzzWUeiUAvaYjP0If0k1k')]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.
The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.
---------- PlanningAgent ----------
Now let's calculate the percentage change in total rebounds between the 2007-2008 and 2008-2009 seasons for Dwyane Wade.
4. DataAnalystAgent: Calculate the percentage change in total rebounds for Dwyane Wade between the 2007-2008 and 2008-2009 seasons.
---------- DataAnalystAgent ----------
[FunctionCall(id='call_FXnPSr6JVGfAWs3StIizbt2V', arguments='{"start":214,"end":398}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='85.98130841121495', call_id='call_FXnPSr6JVGfAWs3StIizbt2V')]
---------- DataAnalystAgent ----------
85.98130841121495
---------- PlanningAgent ----------
Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season, scoring a total of 1397 points. The percentage change in his total rebounds from the 2007-2008 season (214 rebounds) to the 2008-2009 season (398 rebounds) is approximately 86.0%.
TERMINATE
TaskResult(messages=[TextMessage(source='user', models_usage=None, content='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?', type='TextMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=161, completion_tokens=192), content="To answer this question, we need to follow these steps: \n\n1. Identify the Miami Heat player with the highest points in the 2006-2007 season.\n2. Retrieve the total rebounds of that player for the 2007-2008 and 2008-2009 seasons.\n3. Calculate the percentage change in his total rebounds between the two seasons.\n\nLet's delegate these tasks:\n\n1. WebSearchAgent: Find the Miami Heat player with the highest points in the 2006-2007 NBA season.\n2. WebSearchAgent: Retrieve the total rebounds for the identified player during the 2007-2008 NBA season.\n3. WebSearchAgent: Retrieve the total rebounds for the identified player during the 2008-2009 NBA season.\n4. DataAnalystAgent: Calculate the percentage change in total rebounds between the 2007-2008 and 2008-2009 seasons for the player found.", type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=340, completion_tokens=27), content=[FunctionCall(id='call_Pz82ndNLSV4cH0Sg6g7ArP4L', arguments='{"query":"Miami Heat player highest points 2006-2007 season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n Udonis Haslem: 844 points\n Dwayne Wade: 1397 points\n James Posey: 550 points\n ...\n ', call_id='call_Pz82ndNLSV4cH0Sg6g7ArP4L')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n Udonis Haslem: 844 points\n Dwayne Wade: 1397 points\n James Posey: 550 points\n ...\n ', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=420, completion_tokens=87), content="Great! Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season. Now, let's continue with the next tasks:\n\n2. WebSearchAgent: Retrieve the total rebounds for Dwyane Wade during the 2007-2008 NBA season.\n3. WebSearchAgent: Retrieve the total rebounds for Dwyane Wade during the 2008-2009 NBA season.", type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=525, completion_tokens=71), content=[FunctionCall(id='call_3qv9so2DXFZIHtzqDIfXoFID', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 season"}', name='search_web_tool'), FunctionCall(id='call_Vh7zzzWUeiUAvaYjP0If0k1k', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', call_id='call_3qv9so2DXFZIHtzqDIfXoFID'), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_Vh7zzzWUeiUAvaYjP0If0k1k')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.\nThe number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=569, completion_tokens=68), content="Now let's calculate the percentage change in total rebounds between the 2007-2008 and 2008-2009 seasons for Dwyane Wade.\n\n4. DataAnalystAgent: Calculate the percentage change in total rebounds for Dwyane Wade between the 2007-2008 and 2008-2009 seasons.", type='TextMessage'), ToolCallRequestEvent(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=627, completion_tokens=21), content=[FunctionCall(id='call_FXnPSr6JVGfAWs3StIizbt2V', arguments='{"start":214,"end":398}', name='percentage_change_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='DataAnalystAgent', models_usage=None, content=[FunctionExecutionResult(content='85.98130841121495', call_id='call_FXnPSr6JVGfAWs3StIizbt2V')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, content='85.98130841121495', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=659, completion_tokens=76), content='Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season, scoring a total of 1397 points. The percentage change in his total rebounds from the 2007-2008 season (214 rebounds) to the 2008-2009 season (398 rebounds) is approximately 86.0%.\n\nTERMINATE', type='TextMessage')], stop_reason="Text 'TERMINATE' mentioned")
You can see from the conversation log that the Planning Agent always speaks immediately after the specialized agents.
User Feedback#
We can add UserProxyAgent to the team to
provide user feedback during a run.
See Human-in-the-Loop for more details
about UserProxyAgent.
To use the UserProxyAgent in the
web search example, we simply add it to the team and update the selector function
to always check for user feedback after the planning agent speaks.
If the user responds with "APPROVE", the conversation continues, otherwise,
the planning agent tries again, until the user approves.
user_proxy_agent = UserProxyAgent("UserProxyAgent", description="A proxy for the user to approve or disapprove tasks.")
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:
# Planning agent should be the first to engage when given a new task, or check progress.
return planning_agent.name
if messages[-1].source == planning_agent.name:
if messages[-2].source == user_proxy_agent.name and "APPROVE" in messages[-1].content.upper(): # type: ignore
# User has approved the plan, proceed to the next agent.
return None
# Use the user proxy agent to get the user's approval to proceed.
return user_proxy_agent.name
if messages[-1].source == user_proxy_agent.name:
# If the user does not approve, return to the planning agent.
if "APPROVE" not in messages[-1].content.upper(): # type: ignore
return planning_agent.name
return None
# Reset the previous agents and run the chat again with the user proxy agent and selector function.
await team.reset()
team = SelectorGroupChat(
[planning_agent, web_search_agent, data_analyst_agent, user_proxy_agent],
model_client=model_client,
termination_condition=termination,
selector_prompt=selector_prompt,
selector_func=selector_func_with_user_proxy,
allow_repeated_speaker=True,
)
await Console(team.run_stream(task=task))
---------- user ----------
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?
---------- PlanningAgent ----------
To address the user's query, we will need to perform the following tasks:
1. Identify the Miami Heat player with the highest points in the 2006-2007 season.
2. Find the total rebounds for that player in the 2007-2008 season.
3. Find the total rebounds for that player in the 2008-2009 season.
4. Calculate the percentage change in the total rebounds between the 2007-2008 and 2008-2009 seasons.
Let's assign these tasks:
1. **WebSearchAgent**: Identify the Miami Heat player with the highest points in the 2006-2007 season.
(Task 2 and 3 depend on the result of Task 1. We'll proceed with Tasks 2 and 3 once Task 1 is complete.)
---------- UserProxyAgent ----------
approve
---------- WebSearchAgent ----------
[FunctionCall(id='call_0prr3fUnG5CtisUG7QeygW0w', arguments='{"query":"Miami Heat highest points scorer 2006-2007 NBA season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n Udonis Haslem: 844 points\n Dwayne Wade: 1397 points\n James Posey: 550 points\n ...\n ', call_id='call_0prr3fUnG5CtisUG7QeygW0w')]
---------- WebSearchAgent ----------
Here are the total points scored by Miami Heat players in the 2006-2007 season:
Udonis Haslem: 844 points
Dwayne Wade: 1397 points
James Posey: 550 points
...
---------- PlanningAgent ----------
Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season, scoring 1397 points.
Next, we need to find Dwyane Wade's total rebounds for the 2007-2008 and 2008-2009 seasons:
2. **WebSearchAgent**: Find Dwyane Wade's total rebounds for the 2007-2008 season.
3. **WebSearchAgent**: Find Dwyane Wade's total rebounds for the 2008-2009 season.
---------- UserProxyAgent ----------
approve
---------- WebSearchAgent ----------
[FunctionCall(id='call_fBZe80NaBfruOVGwRWbhXyRm', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 NBA season"}', name='search_web_tool'), FunctionCall(id='call_cURYibna4fGxySiL7IYt0c3s', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 NBA season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', call_id='call_fBZe80NaBfruOVGwRWbhXyRm'), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_cURYibna4fGxySiL7IYt0c3s')]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.
The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.
---------- PlanningAgent ----------
Now that we have Dwyane Wade's total rebounds for both seasons, we can calculate the percentage change:
4. **DataAnalystAgent**: Calculate the percentage change in Dwyane Wade's total rebounds from the 2007-2008 season (214 rebounds) to the 2008-2009 season (398 rebounds).
---------- UserProxyAgent ----------
approve
---------- DataAnalystAgent ----------
[FunctionCall(id='call_z3uog7t2x0z1Suzl5hACF9hY', arguments='{"start":214,"end":398}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='85.98130841121495', call_id='call_z3uog7t2x0z1Suzl5hACF9hY')]
---------- DataAnalystAgent ----------
85.98130841121495
---------- PlanningAgent ----------
Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season, scoring 1397 points. His total rebounds increased from 214 in the 2007-2008 season to 398 in the 2008-2009 season, which is a percentage change of approximately 85.98%.
TERMINATE
TaskResult(messages=[TextMessage(source='user', models_usage=None, content='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?', type='TextMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=161, completion_tokens=166), content="To address the user's query, we will need to perform the following tasks:\n\n1. Identify the Miami Heat player with the highest points in the 2006-2007 season.\n2. Find the total rebounds for that player in the 2007-2008 season.\n3. Find the total rebounds for that player in the 2008-2009 season.\n4. Calculate the percentage change in the total rebounds between the 2007-2008 and 2008-2009 seasons.\n\nLet's assign these tasks:\n\n1. **WebSearchAgent**: Identify the Miami Heat player with the highest points in the 2006-2007 season.\n \n(Task 2 and 3 depend on the result of Task 1. We'll proceed with Tasks 2 and 3 once Task 1 is complete.)", type='TextMessage'), UserInputRequestedEvent(source='UserProxyAgent', models_usage=None, request_id='2a433f88-f886-4b39-a078-ea1acdcb2f9d', content='', type='UserInputRequestedEvent'), TextMessage(source='UserProxyAgent', models_usage=None, content='approve', type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=323, completion_tokens=28), content=[FunctionCall(id='call_0prr3fUnG5CtisUG7QeygW0w', arguments='{"query":"Miami Heat highest points scorer 2006-2007 NBA season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n Udonis Haslem: 844 points\n Dwayne Wade: 1397 points\n James Posey: 550 points\n ...\n ', call_id='call_0prr3fUnG5CtisUG7QeygW0w')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n Udonis Haslem: 844 points\n Dwayne Wade: 1397 points\n James Posey: 550 points\n ...\n ', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=403, completion_tokens=112), content="Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season, scoring 1397 points.\n\nNext, we need to find Dwyane Wade's total rebounds for the 2007-2008 and 2008-2009 seasons:\n\n2. **WebSearchAgent**: Find Dwyane Wade's total rebounds for the 2007-2008 season.\n3. **WebSearchAgent**: Find Dwyane Wade's total rebounds for the 2008-2009 season.", type='TextMessage'), UserInputRequestedEvent(source='UserProxyAgent', models_usage=None, request_id='23dd4570-2391-41e9-aeea-86598499792c', content='', type='UserInputRequestedEvent'), TextMessage(source='UserProxyAgent', models_usage=None, content='approve', type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=543, completion_tokens=73), content=[FunctionCall(id='call_fBZe80NaBfruOVGwRWbhXyRm', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 NBA season"}', name='search_web_tool'), FunctionCall(id='call_cURYibna4fGxySiL7IYt0c3s', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 NBA season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', call_id='call_fBZe80NaBfruOVGwRWbhXyRm'), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_cURYibna4fGxySiL7IYt0c3s')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.\nThe number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=586, completion_tokens=70), content="Now that we have Dwyane Wade's total rebounds for both seasons, we can calculate the percentage change:\n\n4. **DataAnalystAgent**: Calculate the percentage change in Dwyane Wade's total rebounds from the 2007-2008 season (214 rebounds) to the 2008-2009 season (398 rebounds).", type='TextMessage'), UserInputRequestedEvent(source='UserProxyAgent', models_usage=None, request_id='e849d193-4ab3-4558-8560-7dbc062a0aee', content='', type='UserInputRequestedEvent'), TextMessage(source='UserProxyAgent', models_usage=None, content='approve', type='TextMessage'), ToolCallRequestEvent(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=655, completion_tokens=21), content=[FunctionCall(id='call_z3uog7t2x0z1Suzl5hACF9hY', arguments='{"start":214,"end":398}', name='percentage_change_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='DataAnalystAgent', models_usage=None, content=[FunctionExecutionResult(content='85.98130841121495', call_id='call_z3uog7t2x0z1Suzl5hACF9hY')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, content='85.98130841121495', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=687, completion_tokens=74), content='Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season, scoring 1397 points. His total rebounds increased from 214 in the 2007-2008 season to 398 in the 2008-2009 season, which is a percentage change of approximately 85.98%.\n\nTERMINATE', type='TextMessage')], stop_reason="Text 'TERMINATE' mentioned")
Now, the user’s feedback is incorporated into the conversation flow, and the user can approve or reject the planning agent’s decisions.