Selector Group Chat#

SelectorGroupChat implementiert ein Team, in dem die Teilnehmer abwechselnd Nachrichten an alle anderen Mitglieder senden. Ein generatives Modell (z. B. ein LLM) wählt den nächsten Sprecher basierend auf dem geteilten Kontext aus und ermöglicht so eine dynamische, kontextbezogene Zusammenarbeit.

Hauptmerkmale sind

  • Modellbasierte Sprecherwahl

  • Konfigurierbare Teilnehmerrollen und Beschreibungen

  • Verhinderung aufeinanderfolgender Züge desselben Sprechers (optional)

  • Anpassbare Auswahlaufforderung

  • Anpassbare Auswahlfunktion zum Überschreiben der standardmäßigen modellbasierten Auswahl

  • Anpassbare Kandidatenfunktion zur Eingrenzung des für die Auswahl durch das Modell verfügbaren Agentensatzes

Hinweis

SelectorGroupChat ist eine High-Level-API. Für mehr Kontrolle und Anpassungsmöglichkeiten siehe das Group Chat Pattern in der Core API-Dokumentation, um Ihre eigene Gruppenchat-Logik zu implementieren.

Wie funktioniert das?#

SelectorGroupChat ist ein Gruppenchat ähnlich wie RoundRobinGroupChat, jedoch mit einem modellbasierten Mechanismus zur Auswahl des nächsten Sprechers. Wenn das Team eine Aufgabe über run() oder run_stream() erhält, werden die folgenden Schritte ausgeführt:

  1. Das Team analysiert den aktuellen Gesprächskontext, einschließlich der Gesprächshistorie und der Attribute name und description der Teilnehmer, um den nächsten Sprecher mithilfe eines Modells zu ermitteln. Standardmäßig wählt das Team nicht denselben Sprecher nacheinander aus, es sei denn, er ist der einzige verfügbare Agent. Dies kann durch Setzen von allow_repeated_speaker=True geändert werden. Sie können das Modell auch überschreiben, indem Sie eine benutzerdefinierte Auswahlfunktion bereitstellen.

  2. Das Team fordert den ausgewählten Sprecher-Agenten auf, eine Antwort zu geben, die dann an alle anderen Teilnehmer **gesendet** wird.

  3. Die Abbruchbedingung wird überprüft, um zu bestimmen, ob das Gespräch beendet werden soll. Wenn nicht, wiederholt sich der Vorgang ab Schritt 1.

  4. Wenn das Gespräch beendet ist, gibt das Team das TaskResult zurück, das die Gesprächshistorie dieser Aufgabe enthält.

Sobald das Team die Aufgabe abgeschlossen hat, wird der Gesprächskontext innerhalb des Teams und aller Teilnehmer beibehalten, sodass die nächste Aufgabe vom vorherigen Gesprächskontext fortgesetzt werden kann. Sie können den Gesprächskontext zurücksetzen, indem Sie reset() aufrufen.

In diesem Abschnitt zeigen wir, wie Sie SelectorGroupChat mit einem einfachen Beispiel für eine Web-Such- und Datenanalysungsaufgabe verwenden.

Beispiel: Websuche/Analyse#

from typing import List, Sequence

from autogen_agentchat.agents import AssistantAgent, UserProxyAgent
from autogen_agentchat.conditions import MaxMessageTermination, TextMentionTermination
from autogen_agentchat.messages import BaseAgentEvent, BaseChatMessage
from autogen_agentchat.teams import SelectorGroupChat
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient

Agenten#

Selector Group Chat

Dieses System verwendet drei spezialisierte Agenten

  • Planungsagent: Der strategische Koordinator, der komplexe Aufgaben in überschaubare Unteraufgaben zerlegt.

  • Web-Suchagent: Ein Informationsbeschaffungsspezialist, der mit dem search_web_tool interagiert.

  • Datenanalyst-Agent: Ein auf Berechnungen spezialisierter Agent, der mit dem percentage_change_tool ausgestattet ist.

Die Tools search_web_tool und percentage_change_tool sind externe Tools, die die Agenten zur Ausführung ihrer Aufgaben verwenden können.

# 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

Erstellen wir die spezialisierten Agenten mit der Klasse AssistantAgent. Es ist wichtig zu beachten, dass die Attribute name und description der Agenten vom Modell verwendet werden, um den nächsten Sprecher zu bestimmen. Daher wird empfohlen, aussagekräftige Namen und Beschreibungen anzugeben.

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.
    """,
)

Hinweis

Standardmäßig gibt AssistantAgent die Tool-Ausgabe als Antwort zurück. Wenn Ihr Tool keine gut formatierte Zeichenkette im natürlichen Sprachformat zurückgibt, möchten Sie möglicherweise einen Reflexionsschritt innerhalb des Agenten hinzufügen, indem Sie reflect_on_tool_use=True beim Erstellen des Agenten setzen. Dies ermöglicht es dem Agenten, über die Tool-Ausgabe zu reflektieren und eine Antwort in natürlicher Sprache zu geben.

Arbeitsablauf#

  1. Die Aufgabe wird vom SelectorGroupChat empfangen, der basierend auf den Agentenbeschreibungen den am besten geeigneten Agenten für die Bearbeitung der anfänglichen Aufgabe auswählt (typischerweise den Planungsagenten).

  2. Der **Planungsagent** analysiert die Aufgabe und zerlegt sie in Unteraufgaben, die er dem am besten geeigneten Agenten im Format zuweist: <agent> : <task>

  3. Basierend auf dem Gesprächskontext und den Agentenbeschreibungen wählt der Manager von SelectorGroupChat dynamisch den nächsten Agenten aus, um seine zugewiesenen Unteraufgaben zu bearbeiten.

  4. Der **Web-Suchagent** führt nacheinander Suchen durch und speichert die Ergebnisse in der gemeinsamen Gesprächshistorie.

  5. Der **Datenanalyst** verarbeitet die gesammelten Informationen mit verfügbaren Berechnungstools, wenn er ausgewählt wird.

  6. Der Workflow wird fortgesetzt, wobei Agenten dynamisch ausgewählt werden, bis entweder

    • Der Planungsagent bestimmt, dass alle Unteraufgaben abgeschlossen sind, und sendet "TERMINATE".

    • Eine alternative Abbruchbedingung wird erfüllt (z. B. eine maximale Anzahl von Nachrichten).

Stellen Sie bei der Definition Ihrer Agenten sicher, dass Sie eine hilfreiche description einfügen, da diese verwendet wird, um zu entscheiden, welcher Agent als nächstes ausgewählt werden soll.

Abbruchbedingungen#

Wir verwenden zwei Abbruchbedingungen: TextMentionTermination, um das Gespräch zu beenden, wenn der Planungsagent "TERMINATE" sendet, und MaxMessageTermination, um das Gespräch auf 25 Nachrichten zu beschränken, um eine Endlosschleife zu vermeiden.

text_mention_termination = TextMentionTermination("TERMINATE")
max_messages_termination = MaxMessageTermination(max_messages=25)
termination = text_mention_termination | max_messages_termination

Selector Prompt#

SelectorGroupChat verwendet ein Modell, um den nächsten Sprecher basierend auf dem Gesprächskontext auszuwählen. Wir verwenden eine benutzerdefinierte Auswahlaufforderung, um sie ordnungsgemäß an den Workflow anzupassen.

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.
"""

Die im Selector Prompt verfügbaren Zeichenvariablen sind:

  • {participants}: Die Namen der Kandidaten für die Auswahl. Das Format ist ["<name1>", "<name2>", ...].

  • {roles}: Eine durch Zeilenumbrüche getrennte Liste von Namen und Beschreibungen der Kandidaten-Agenten. Das Format für jede Zeile ist: "<name> : <description>".

  • {history}: Die Gesprächshistorie, formatiert als durch doppelte Zeilenumbrüche getrennte Namen und Nachrichteninhalt. Das Format für jede Nachricht ist: "<name> : <message content>".

Tipp

Versuchen Sie, das Modell nicht mit zu vielen Anweisungen in der Auswahlaufforderung zu überladen.

Was ist zu viel? Das hängt von den Fähigkeiten des Modells ab, das Sie verwenden. Für GPT-4o und Äquivalente können Sie eine Auswahlaufforderung mit einer Bedingung für jeden Sprecher verwenden. Für kleinere Modelle wie Phi-4 sollten Sie die Auswahlaufforderung so einfach wie möglich halten, wie in diesem Beispiel.

Im Allgemeinen ist es ein Zeichen dafür, dass Sie eine benutzerdefinierte Auswahlfunktion in Betracht ziehen oder die Aufgabe in kleinere, sequentielle Aufgaben aufteilen sollten, die von separaten Agenten oder Teams bearbeitet werden, wenn Sie mehrere Bedingungen für jeden Agenten schreiben.

Ausführen des Teams#

Erstellen wir das Team mit den Agenten, Abbruchbedingungen und der benutzerdefinierten Auswahlaufforderung.

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.
)

Nun führen wir das Team mit einer Aufgabe aus, um Informationen über einen NBA-Spieler zu finden.

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 complete this task, we need to perform the following subtasks:

1. Find out which Miami Heat player had the highest points in the 2006-2007 season.
2. Gather data on this player's total rebounds for the 2007-2008 season.
3. Gather data on this player's total rebounds for the 2008-2009 season.
4. Calculate the percentage change in the player's total rebounds between the 2007-2008 and 2008-2009 seasons.

I'll assign these tasks accordingly:

1. WebSearchAgent: Search for the Miami Heat player with the highest points in the 2006-2007 NBA season.
2. WebSearchAgent: Find the total rebounds for this player in the 2007-2008 NBA season.
3. WebSearchAgent: Find the total rebounds for this player in the 2008-2009 NBA season.
4. DataAnalystAgent: Calculate the percentage change in total rebounds from the 2007-2008 season to the 2008-2009 season for this player.
---------- WebSearchAgent ----------
[FunctionCall(id='call_89tUNHaAM0kKQYPJLleGUKK7', 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        ', name='search_web_tool', call_id='call_89tUNHaAM0kKQYPJLleGUKK7', is_error=False)]
---------- 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 ----------
The Miami Heat player with the highest points in the 2006-2007 season was Dwyane Wade, with 1,397 points.

Next, I will search for Dwyane Wade's total rebounds for the 2007-2008 season.
---------- WebSearchAgent ----------
[FunctionCall(id='call_RC55TkSjG3JXRuVOTPrcE1RL', arguments='{"query":"Dwyane Wade total rebounds 2007-2008 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.', name='search_web_tool', call_id='call_RC55TkSjG3JXRuVOTPrcE1RL', is_error=False)]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.
---------- WebSearchAgent ----------
[FunctionCall(id='call_pBXoABrErDow0rZjw3tjOZol', 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 2008-2009 is 398.', name='search_web_tool', call_id='call_pBXoABrErDow0rZjw3tjOZol', is_error=False)]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.
---------- DataAnalystAgent ----------
[FunctionCall(id='call_qMxxXtcJsiK8KFSSCx3zm0is', arguments='{"start":214,"end":398}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='85.98130841121495', name='percentage_change_tool', call_id='call_qMxxXtcJsiK8KFSSCx3zm0is', is_error=False)]
---------- DataAnalystAgent ----------
85.98130841121495
---------- PlanningAgent ----------
The player with the highest points for the Miami Heat in the 2006-2007 NBA season was Dwyane Wade, who scored 1,397 points. The percentage change in Dwyane Wade's total rebounds from 214 in the 2007-2008 season to 398 in the 2008-2009 season is approximately 85.98%.

TERMINATE

TaskResult(messages=[TextMessage(source='user', models_usage=None, metadata={}, 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=220), metadata={}, content="To complete this task, we need to perform the following subtasks:\n\n1. Find out which Miami Heat player had the highest points in the 2006-2007 season.\n2. Gather data on this player's total rebounds for the 2007-2008 season.\n3. Gather data on this player's total rebounds for the 2008-2009 season.\n4. Calculate the percentage change in the player's total rebounds between the 2007-2008 and 2008-2009 seasons.\n\nI'll assign these tasks accordingly:\n\n1. WebSearchAgent: Search for the Miami Heat player with the highest points in the 2006-2007 NBA season.\n2. WebSearchAgent: Find the total rebounds for this player in the 2007-2008 NBA season.\n3. WebSearchAgent: Find the total rebounds for this player in the 2008-2009 NBA season.\n4. DataAnalystAgent: Calculate the percentage change in total rebounds from the 2007-2008 season to the 2008-2009 season for this player.", type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=368, completion_tokens=27), metadata={}, content=[FunctionCall(id='call_89tUNHaAM0kKQYPJLleGUKK7', arguments='{"query":"Miami Heat player highest points 2006-2007 season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, metadata={}, 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        ', name='search_web_tool', call_id='call_89tUNHaAM0kKQYPJLleGUKK7', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, metadata={}, 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'), ThoughtEvent(source='WebSearchAgent', models_usage=None, metadata={}, content="The Miami Heat player with the highest points in the 2006-2007 season was Dwyane Wade, with 1,397 points.\n\nNext, I will search for Dwyane Wade's total rebounds for the 2007-2008 season.", type='ThoughtEvent'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=460, completion_tokens=83), metadata={}, content=[FunctionCall(id='call_RC55TkSjG3JXRuVOTPrcE1RL', arguments='{"query":"Dwyane Wade total rebounds 2007-2008 season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', name='search_web_tool', call_id='call_RC55TkSjG3JXRuVOTPrcE1RL', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, metadata={}, content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', type='ToolCallSummaryMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=585, completion_tokens=28), metadata={}, content=[FunctionCall(id='call_pBXoABrErDow0rZjw3tjOZol', arguments='{"query":"Dwyane Wade total rebounds 2008-2009 season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', name='search_web_tool', call_id='call_pBXoABrErDow0rZjw3tjOZol', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, metadata={}, content='The 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=496, completion_tokens=21), metadata={}, content=[FunctionCall(id='call_qMxxXtcJsiK8KFSSCx3zm0is', arguments='{"start":214,"end":398}', name='percentage_change_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='DataAnalystAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='85.98130841121495', name='percentage_change_tool', call_id='call_qMxxXtcJsiK8KFSSCx3zm0is', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, metadata={}, content='85.98130841121495', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=528, completion_tokens=80), metadata={}, content="The player with the highest points for the Miami Heat in the 2006-2007 NBA season was Dwyane Wade, who scored 1,397 points. The percentage change in Dwyane Wade's total rebounds from 214 in the 2007-2008 season to 398 in the 2008-2009 season is approximately 85.98%.\n\nTERMINATE", type='TextMessage')], stop_reason="Text 'TERMINATE' mentioned")

Wie wir sehen, finden wir, nachdem der Web-Suchagent die notwendigen Suchen durchgeführt und der Datenanalyst die notwendigen Berechnungen abgeschlossen hat, dass Dwayne Wade der Miami Heat-Spieler mit den meisten Punkten in der Saison 2006-2007 war und die prozentuale Veränderung seiner Gesamtrebounds zwischen den Saisons 2007-2008 und 2008-2009 85,98 % beträgt!

Benutzerdefinierte Selector-Funktion#

Oftmals wünschen wir uns eine bessere Kontrolle über den Auswahlprozess. Zu diesem Zweck können wir das Argument selector_func mit einer benutzerdefinierten Selector-Funktion setzen, um die standardmäßige modellbasierte Auswahl zu überschreiben. Dies ermöglicht uns, komplexere Auswahl-Logik und zustandsbasierte Übergänge zu implementieren.

Zum Beispiel möchten wir, dass der Planungsagent sofort nach jedem spezialisierten Agenten spricht, um den Fortschritt zu überprüfen.

Hinweis

Die Rückgabe von None aus der benutzerdefinierten Selector-Funktion verwendet die standardmäßige modellbasierte Auswahl.

Hinweis

Benutzerdefinierte Selector-Funktionen werden nicht serialisiert, wenn .dump_component() für das SelectorGroupChat-Team aufgerufen wird. Wenn Sie Teamkonfigurationen mit benutzerdefinierten Selector-Funktionen serialisieren müssen, erwägen Sie die Implementierung benutzerdefinierter Workflows und Serialisierungs-Logik.

def selector_func(messages: Sequence[BaseAgentEvent | BaseChatMessage]) -> 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")

Aus dem Gesprächsprotokoll ist ersichtlich, dass der Planungsagent immer unmittelbar nach den spezialisierten Agenten spricht.

Tipp

Jeder teilnehmende Agent führt pro Runde nur einen Schritt aus (Ausführen von Tools, Generieren einer Antwort usw.). Wenn Sie möchten, dass ein AssistantAgent wiederholt, bis er keine ToolCallSummaryMessage mehr zurückgibt, nachdem er alle benötigten Tools ausgeführt hat, können Sie dies tun, indem Sie die letzte Nachricht überprüfen und den Agenten zurückgeben, wenn es sich um eine ToolCallSummaryMessage handelt.

Benutzerdefinierte Kandidatenfunktion#

Eine weitere mögliche Anforderung könnte sein, den nächsten Sprecher automatisch aus einer gefilterten Liste von Agenten auszuwählen. Dafür können wir den Parameter candidate_func mit einer benutzerdefinierten Kandidatenfunktion setzen, um die Liste potenzieller Agenten für die Sprecherwahl für jede Runde des Gruppenchats einzugrenzen.

Dies ermöglicht es uns, die Sprecherwahl auf eine bestimmte Gruppe von Agenten nach einem bestimmten Agenten zu beschränken.

Hinweis

Die candidate_func ist nur gültig, wenn selector_func nicht gesetzt ist. Die Rückgabe von None oder einer leeren Liste [] aus der benutzerdefinierten Kandidatenfunktion führt zu einem ValueError.

def candidate_func(messages: Sequence[BaseAgentEvent | BaseChatMessage]) -> List[str]:
    # keep planning_agent first one to plan out the tasks
    if messages[-1].source == "user":
        return [planning_agent.name]

    # if previous agent is planning_agent and if it explicitely asks for web_search_agent
    # or data_analyst_agent or both (in-case of re-planning or re-assignment of tasks)
    # then return those specific agents
    last_message = messages[-1]
    if last_message.source == planning_agent.name:
        participants = []
        if web_search_agent.name in last_message.to_text():
            participants.append(web_search_agent.name)
        if data_analyst_agent.name in last_message.to_text():
            participants.append(data_analyst_agent.name)
        if participants:
            return participants  # SelectorGroupChat will select from the remaining two agents.

    # we can assume that the task is finished once the web_search_agent
    # and data_analyst_agent have took their turns, thus we send
    # in planning_agent to terminate the chat
    previous_set_of_agents = set(message.source for message in messages)
    if web_search_agent.name in previous_set_of_agents and data_analyst_agent.name in previous_set_of_agents:
        return [planning_agent.name]

    # if no-conditions are met then return all the agents
    return [planning_agent.name, web_search_agent.name, data_analyst_agent.name]


# 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,
    candidate_func=candidate_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'll break it down into two main subtasks:

1. Identify the Miami Heat player with the highest points in the 2006-2007 season.
2. Calculate the percentage change in that player's total rebounds between the 2007-2008 and 2008-2009 seasons.

Let's assign these tasks:

1. WebSearchAgent: Search for the Miami Heat player with the highest points in the 2006-2007 NBA season.
2. WebSearchAgent: Find the total rebound statistics for that identified player for both the 2007-2008 and 2008-2009 NBA seasons.
3. DataAnalystAgent: Calculate the percentage change in the player's total rebounds between the 2007-2008 and 2008-2009 seasons once the data is retrieved.
---------- WebSearchAgent ----------
[FunctionCall(id='call_WtR5KTfEIxs3jIO25gjAw7dF', 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        ', name='search_web_tool', call_id='call_WtR5KTfEIxs3jIO25gjAw7dF', is_error=False)]
---------- 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
        ...
        
---------- DataAnalystAgent ----------
[FunctionCall(id='call_9HA3DEacUl4WuG2G2PtRkXAO', arguments='{"start": 432, "end": 527}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='21.99074074074074', name='percentage_change_tool', call_id='call_9HA3DEacUl4WuG2G2PtRkXAO', is_error=False)]
---------- DataAnalystAgent ----------
21.99074074074074
---------- PlanningAgent ----------
It seems we've missed some context there, so let's assign the subtasks again for clarity:

Based on the search results, Dwyane Wade had the highest points for the Miami Heat in the 2006-2007 season with 1397 points.

Now, let's find the necessary rebound statistics:

2. WebSearchAgent: Find Dwyane Wade's total rebound statistics for both the 2007-2008 and 2008-2009 NBA seasons.
3. DataAnalystAgent: Once the data is retrieved, calculate the percentage change in Dwyane Wade's total rebounds between the 2007-2008 and 2008-2009 seasons.
---------- WebSearchAgent ----------
[FunctionCall(id='call_3i1wTDSjkGg6Ev8YKYWkZK55', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 NBA season"}', name='search_web_tool'), FunctionCall(id='call_NRAs6jHxXRi8zsvpW5WlHAaU', 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.', name='search_web_tool', call_id='call_3i1wTDSjkGg6Ev8YKYWkZK55', is_error=False), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', name='search_web_tool', call_id='call_NRAs6jHxXRi8zsvpW5WlHAaU', is_error=False)]
---------- 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 ----------
The total rebounds for Dwyane Wade in the 2007-2008 season were 214, and in the 2008-2009 season, they were 398.

Now, let's calculate the percentage change.

3. DataAnalystAgent: Calculate the percentage change in Dwyane Wade's total rebounds from the 2007-2008 season to the 2008-2009 season.
---------- DataAnalystAgent ----------
[FunctionCall(id='call_XECA7ezz7VIKbf8IbZYSCSpI', arguments='{"start":214,"end":398}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='85.98130841121495', name='percentage_change_tool', call_id='call_XECA7ezz7VIKbf8IbZYSCSpI', is_error=False)]
---------- DataAnalystAgent ----------
85.98130841121495
---------- PlanningAgent ----------
The Miami Heat player with the highest points in the 2006-2007 season was Dwyane Wade, with 1397 points. The percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons was approximately 85.98%.

TERMINATE

TaskResult(messages=[TextMessage(source='user', models_usage=None, metadata={}, 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), metadata={}, content="To answer this question, we'll break it down into two main subtasks:\n\n1. Identify the Miami Heat player with the highest points in the 2006-2007 season.\n2. Calculate the percentage change in that player's total rebounds between the 2007-2008 and 2008-2009 seasons.\n\nLet's assign these tasks:\n\n1. WebSearchAgent: Search for the Miami Heat player with the highest points in the 2006-2007 NBA season.\n2. WebSearchAgent: Find the total rebound statistics for that identified player for both the 2007-2008 and 2008-2009 NBA seasons.\n3. DataAnalystAgent: Calculate the percentage change in the player's total rebounds between the 2007-2008 and 2008-2009 seasons once the data is retrieved.", type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=324, completion_tokens=28), metadata={}, content=[FunctionCall(id='call_WtR5KTfEIxs3jIO25gjAw7dF', arguments='{"query":"Miami Heat highest points scorer 2006-2007 NBA season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, metadata={}, 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        ', name='search_web_tool', call_id='call_WtR5KTfEIxs3jIO25gjAw7dF', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, metadata={}, 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='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=390, completion_tokens=37), metadata={}, content=[FunctionCall(id='call_9HA3DEacUl4WuG2G2PtRkXAO', arguments='{"start": 432, "end": 527}', name='percentage_change_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='DataAnalystAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='21.99074074074074', name='percentage_change_tool', call_id='call_9HA3DEacUl4WuG2G2PtRkXAO', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, metadata={}, content='21.99074074074074', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=413, completion_tokens=137), metadata={}, content="It seems we've missed some context there, so let's assign the subtasks again for clarity:\n\nBased on the search results, Dwyane Wade had the highest points for the Miami Heat in the 2006-2007 season with 1397 points.\n\nNow, let's find the necessary rebound statistics:\n\n2. WebSearchAgent: Find Dwyane Wade's total rebound statistics for both the 2007-2008 and 2008-2009 NBA seasons.\n3. DataAnalystAgent: Once the data is retrieved, calculate the percentage change in Dwyane Wade's total rebounds between the 2007-2008 and 2008-2009 seasons.", type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=576, completion_tokens=73), metadata={}, content=[FunctionCall(id='call_3i1wTDSjkGg6Ev8YKYWkZK55', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 NBA season"}', name='search_web_tool'), FunctionCall(id='call_NRAs6jHxXRi8zsvpW5WlHAaU', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 NBA season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', name='search_web_tool', call_id='call_3i1wTDSjkGg6Ev8YKYWkZK55', is_error=False), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', name='search_web_tool', call_id='call_NRAs6jHxXRi8zsvpW5WlHAaU', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, metadata={}, 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=612, completion_tokens=84), metadata={}, content="The total rebounds for Dwyane Wade in the 2007-2008 season were 214, and in the 2008-2009 season, they were 398.\n\nNow, let's calculate the percentage change.\n\n3. DataAnalystAgent: Calculate the percentage change in Dwyane Wade's total rebounds from the 2007-2008 season to the 2008-2009 season.", type='TextMessage'), ToolCallRequestEvent(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=720, completion_tokens=21), metadata={}, content=[FunctionCall(id='call_XECA7ezz7VIKbf8IbZYSCSpI', arguments='{"start":214,"end":398}', name='percentage_change_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='DataAnalystAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='85.98130841121495', name='percentage_change_tool', call_id='call_XECA7ezz7VIKbf8IbZYSCSpI', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, metadata={}, content='85.98130841121495', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=718, completion_tokens=63), metadata={}, content='The Miami Heat player with the highest points in the 2006-2007 season was Dwyane Wade, with 1397 points. The percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons was approximately 85.98%.\n\nTERMINATE', type='TextMessage')], stop_reason="Text 'TERMINATE' mentioned")

Aus dem Gesprächsprotokoll ist ersichtlich, dass der Planungsagent zur Konversation zurückkehrt, nachdem der Web-Suchagent und der Datenanalyst-Agent ihre Züge gemacht haben, und feststellt, dass die Aufgabe nicht wie erwartet abgeschlossen wurde, sodass er den WebSearchAgent erneut aufruft, um Bindungswerte zu erhalten, und dann den DataAnalysetAgent aufruft, um die prozentuale Veränderung zu erhalten.

Benutzerfeedback#

Wir können UserProxyAgent zum Team hinzufügen, um während der Ausführung Benutzerfeedback zu geben. Weitere Details zu UserProxyAgent finden Sie unter Human-in-the-Loop.

Um den UserProxyAgent im Web-Suchbeispiel zu verwenden, fügen wir ihn einfach zum Team hinzu und aktualisieren die Selector-Funktion, um immer nach Benutzerfeedback zu suchen, nachdem der Planungsagent gesprochen hat. Wenn der Benutzer mit "APPROVE" antwortet, wird die Konversation fortgesetzt, andernfalls versucht der Planungsagent es erneut, bis der Benutzer zustimmt.

user_proxy_agent = UserProxyAgent("UserProxyAgent", description="A proxy for the user to approve or disapprove tasks.")


def selector_func_with_user_proxy(messages: Sequence[BaseAgentEvent | BaseChatMessage]) -> 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")

Jetzt ist das Feedback des Benutzers in den Gesprächsfluss integriert, und der Benutzer kann die Entscheidungen des Planungsagenten genehmigen oder ablehnen.

Verwendung von Reasoning-Modellen#

Bisher haben wir in den Beispielen ein gpt-4o-Modell verwendet. Modelle wie gpt-4o und gemini-1.5-flash sind sehr gut darin, Anweisungen zu befolgen, sodass Sie relativ detaillierte Anweisungen in der Auswahlaufforderung für das Team und den Systemnachrichten für jeden Agenten haben können, um deren Verhalten zu steuern.

Wenn Sie jedoch ein Reasoning-Modell wie o3-mini verwenden, müssen Sie die Auswahlaufforderung und die Systemnachrichten so einfach und prägnant wie möglich halten. Das liegt daran, dass die Reasoning-Modelle bereits gut darin sind, ihre eigenen Anweisungen zu formulieren, angesichts des ihnen bereitgestellten Kontexts.

Dies bedeutet auch, dass wir keinen Planungsagenten mehr benötigen, um die Aufgabe zu zerlegen, da der SelectorGroupChat, der ein Reasoning-Modell verwendet, dies selbst tun kann.

Im folgenden Beispiel verwenden wir o3-mini als Modell für die Agenten und das Team, und wir verwenden keinen Planungsagenten. Außerdem halten wir die Auswahlaufforderung und die Systemnachrichten so einfach wie möglich.

model_client = OpenAIChatCompletionClient(model="o3-mini")

web_search_agent = AssistantAgent(
    "WebSearchAgent",
    description="An agent for searching information on the web.",
    tools=[search_web_tool],
    model_client=model_client,
    system_message="""Use web search tool to find information.""",
)

data_analyst_agent = AssistantAgent(
    "DataAnalystAgent",
    description="An agent for performing calculations.",
    model_client=model_client,
    tools=[percentage_change_tool],
    system_message="""Use tool to perform calculation. If you have not seen the data, ask for it.""",
)

user_proxy_agent = UserProxyAgent(
    "UserProxyAgent",
    description="A 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_client=model_client,
    termination_condition=termination,  # Use the same termination condition as before.
    selector_prompt=selector_prompt,
    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?
---------- WebSearchAgent ----------
[FunctionCall(id='call_hl7EP6Lp5jj5wEdxeNHTwUVG', arguments='{"query": "Who was the Miami Heat player with the highest points in the 2006-2007 season Miami Heat statistics Dwyane Wade rebounds percentage change 2007-2008 2008-2009 seasons"}', 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_hl7EP6Lp5jj5wEdxeNHTwUVG', is_error=False)]
---------- 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
        ...
        
---------- DataAnalystAgent ----------
I found that in the 2006–2007 season the player with the highest points was Dwyane Wade (with 1,397 points). Could you please provide Dwyane Wade’s total rebounds for the 2007–2008 and the 2008–2009 seasons so I can calculate the percentage change?
---------- WebSearchAgent ----------
[FunctionCall(id='call_lppGTILXDvO9waPwKO66ehK6', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 and 2008-2009 seasons for Miami Heat"}', 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_lppGTILXDvO9waPwKO66ehK6', is_error=False)]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.
---------- DataAnalystAgent ----------
Could you please provide Dwyane Wade’s total rebounds in the 2008-2009 season?
---------- WebSearchAgent ----------
[FunctionCall(id='call_r8DBcbJtQfdtugLtyTrqOvoK', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 season Miami Heat"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_r8DBcbJtQfdtugLtyTrqOvoK', is_error=False)]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.
---------- DataAnalystAgent ----------
[FunctionCall(id='call_4jejv1wM7V1osbBCxJze8aQM', arguments='{"start": 214, "end": 398}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='85.98130841121495', call_id='call_4jejv1wM7V1osbBCxJze8aQM', is_error=False)]
---------- DataAnalystAgent ----------
85.98130841121495
---------- DataAnalystAgent ----------
Dwyane Wade was the Miami Heat player with the highest total points (1,397) during the 2006-2007 season. His total rebounds increased by approximately 86% from 214 in the 2007-2008 season to 398 in the 2008-2009 season.
---------- UserProxyAgent ----------
Approve. 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'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=103, completion_tokens=384), content=[FunctionCall(id='call_hl7EP6Lp5jj5wEdxeNHTwUVG', arguments='{"query": "Who was the Miami Heat player with the highest points in the 2006-2007 season Miami Heat statistics Dwyane Wade rebounds percentage change 2007-2008 2008-2009 seasons"}', 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_hl7EP6Lp5jj5wEdxeNHTwUVG', is_error=False)], 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='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=183, completion_tokens=1038), content='I found that in the 2006–2007 season the player with the highest points was Dwyane Wade (with 1,397 points). Could you please provide Dwyane Wade’s total rebounds for the 2007–2008 and the 2008–2009 seasons so I can calculate the percentage change?', type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=299, completion_tokens=109), content=[FunctionCall(id='call_lppGTILXDvO9waPwKO66ehK6', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 and 2008-2009 seasons for Miami Heat"}', 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_lppGTILXDvO9waPwKO66ehK6', is_error=False)], 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.', type='ToolCallSummaryMessage'), TextMessage(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=291, completion_tokens=224), content='Could you please provide Dwyane Wade’s total rebounds in the 2008-2009 season?', type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=401, completion_tokens=37), content=[FunctionCall(id='call_r8DBcbJtQfdtugLtyTrqOvoK', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 season Miami Heat"}', 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 2008-2009 is 398.', call_id='call_r8DBcbJtQfdtugLtyTrqOvoK', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='The 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=353, completion_tokens=158), content=[FunctionCall(id='call_4jejv1wM7V1osbBCxJze8aQM', 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_4jejv1wM7V1osbBCxJze8aQM', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, content='85.98130841121495', type='ToolCallSummaryMessage'), TextMessage(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=394, completion_tokens=138), content='Dwyane Wade was the Miami Heat player with the highest total points (1,397) during the 2006-2007 season. His total rebounds increased by approximately 86% from 214 in the 2007-2008 season to 398 in the 2008-2009 season.', type='TextMessage'), UserInputRequestedEvent(source='UserProxyAgent', models_usage=None, request_id='b3b05408-73fc-47d4-b832-16c9f447cd6e', content='', type='UserInputRequestedEvent'), TextMessage(source='UserProxyAgent', models_usage=None, content='Approve. TERMINATE', type='TextMessage')], stop_reason="Text 'TERMINATE' mentioned")

Tipp

Weitere Anleitungen zur Abfrage von Reasoning-Modellen finden Sie im Azure AI Services Blog unter Prompt Engineering für OpenAI’s O1 und O3-mini Reasoning Models.