多智能体¶

单个智能体可能难以应对需要专门处理多个领域或管理多种工具的情况。为了解决这个问题，您可以将智能体分解为更小、独立的智能体，并将它们组合成一个多智能体系统。

在多智能体系统中，智能体之间需要进行通信。它们通过移交来实现这一点——这是一种描述将控制权移交给哪个智能体以及发送给该智能体的数据负载的原始操作。

两种最受欢迎的多智能体架构是：

主管——单个智能体由一个中央主管智能体协调。主管控制所有通信流和任务委派，根据当前上下文和任务要求决定调用哪个智能体。
群组——智能体根据其专业性动态地相互移交控制权。系统会记住哪个智能体上次处于活动状态，确保在后续交互中，对话会与该智能体恢复。

主管¶

Supervisor

使用 langgraph-supervisor 库来创建主管多智能体系统

pip install langgraph-supervisor

^{API 参考： ChatOpenAI | create_react_agent | create_supervisor}

from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
from langgraph_supervisor import create_supervisor

def book_hotel(hotel_name: str):
    """Book a hotel"""
    return f"Successfully booked a stay at {hotel_name}."

def book_flight(from_airport: str, to_airport: str):
    """Book a flight"""
    return f"Successfully booked a flight from {from_airport} to {to_airport}."

flight_assistant = create_react_agent(
    model="openai:gpt-4o",
    tools=[book_flight],
    prompt="You are a flight booking assistant",
    name="flight_assistant"
)

hotel_assistant = create_react_agent(
    model="openai:gpt-4o",
    tools=[book_hotel],
    prompt="You are a hotel booking assistant",
    name="hotel_assistant"
)

supervisor = create_supervisor(
    agents=[flight_assistant, hotel_assistant],
    model=ChatOpenAI(model="gpt-4o"),
    prompt=(
        "You manage a hotel booking assistant and a"
        "flight booking assistant. Assign work to them."
    )
).compile()

for chunk in supervisor.stream(
    {
        "messages": [
            {
                "role": "user",
                "content": "book a flight from BOS to JFK and a stay at McKittrick Hotel"
            }
        ]
    }
):
    print(chunk)
    print("\n")

群组¶

Swarm

使用 langgraph-swarm 库来创建群组多智能体系统

pip install langgraph-swarm

^{API 参考： create_react_agent | create_swarm | create_handoff_tool}

from langgraph.prebuilt import create_react_agent
from langgraph_swarm import create_swarm, create_handoff_tool

transfer_to_hotel_assistant = create_handoff_tool(
    agent_name="hotel_assistant",
    description="Transfer user to the hotel-booking assistant.",
)
transfer_to_flight_assistant = create_handoff_tool(
    agent_name="flight_assistant",
    description="Transfer user to the flight-booking assistant.",
)

flight_assistant = create_react_agent(
    model="anthropic:claude-3-5-sonnet-latest",
    tools=[book_flight, transfer_to_hotel_assistant],
    prompt="You are a flight booking assistant",
    name="flight_assistant"
)
hotel_assistant = create_react_agent(
    model="anthropic:claude-3-5-sonnet-latest",
    tools=[book_hotel, transfer_to_flight_assistant],
    prompt="You are a hotel booking assistant",
    name="hotel_assistant"
)

swarm = create_swarm(
    agents=[flight_assistant, hotel_assistant],
    default_active_agent="flight_assistant"
).compile()

for chunk in swarm.stream(
    {
        "messages": [
            {
                "role": "user",
                "content": "book a flight from BOS to JFK and a stay at McKittrick Hotel"
            }
        ]
    }
):
    print(chunk)
    print("\n")

移交¶

多智能体交互中一个常见的模式是**移交（handoffs）**，即一个智能体将控制权*移交*给另一个智能体。移交允许您指定：

目的地：要导航到的目标智能体
负载：要传递给该智能体的信息

这在 langgraph-supervisor（主管移交给单个智能体）和 langgraph-swarm（单个智能体可以移交给其他智能体）中都有使用。

要使用 create_react_agent 实现移交，您需要：

创建一个可以转移控制权给不同智能体的特殊工具

def transfer_to_bob():
    """Transfer to bob."""
    return Command(
        # name of the agent (node) to go to
        goto="bob",
        # data to send to the agent
        update={"messages": [...]},
        # indicate to LangGraph that we need to navigate to
        # agent node in a parent graph
        graph=Command.PARENT,
    )

创建可以访问移交工具的单个智能体

flight_assistant = create_react_agent(
    ..., tools=[book_flight, transfer_to_hotel_assistant]
)
hotel_assistant = create_react_agent(
    ..., tools=[book_hotel, transfer_to_flight_assistant]
)

定义一个包含单个智能体作为节点的父图

from langgraph.graph import StateGraph, MessagesState
multi_agent_graph = (
    StateGraph(MessagesState)
    .add_node(flight_assistant)
    .add_node(hotel_assistant)
    ...
)

综合以上，以下是您如何实现一个简单的多智能体系统，其中包含两个智能体——一个航班预订助手和一个酒店预订助手：

^{API 参考： tool | InjectedToolCallId | create_react_agent | InjectedState | StateGraph | START | Command}

from typing import Annotated
from langchain_core.tools import tool, InjectedToolCallId
from langgraph.prebuilt import create_react_agent, InjectedState
from langgraph.graph import StateGraph, START, MessagesState
from langgraph.types import Command

def create_handoff_tool(*, agent_name: str, description: str | None = None):
    name = f"transfer_to_{agent_name}"
    description = description or f"Transfer to {agent_name}"

    @tool(name, description=description)
    def handoff_tool(
        state: Annotated[MessagesState, InjectedState], # (1)!
        tool_call_id: Annotated[str, InjectedToolCallId],
    ) -> Command:
        tool_message = {
            "role": "tool",
            "content": f"Successfully transferred to {agent_name}",
            "name": name,
            "tool_call_id": tool_call_id,
        }
        return Command(  # (2)!
            goto=agent_name,  # (3)!
            update={"messages": state["messages"] + [tool_message]},  # (4)!
            graph=Command.PARENT,  # (5)!
        )
    return handoff_tool

# Handoffs
transfer_to_hotel_assistant = create_handoff_tool(
    agent_name="hotel_assistant",
    description="Transfer user to the hotel-booking assistant.",
)
transfer_to_flight_assistant = create_handoff_tool(
    agent_name="flight_assistant",
    description="Transfer user to the flight-booking assistant.",
)

# Simple agent tools
def book_hotel(hotel_name: str):
    """Book a hotel"""
    return f"Successfully booked a stay at {hotel_name}."

def book_flight(from_airport: str, to_airport: str):
    """Book a flight"""
    return f"Successfully booked a flight from {from_airport} to {to_airport}."

# Define agents
flight_assistant = create_react_agent(
    model="anthropic:claude-3-5-sonnet-latest",
    tools=[book_flight, transfer_to_hotel_assistant],
    prompt="You are a flight booking assistant",
    name="flight_assistant"
)
hotel_assistant = create_react_agent(
    model="anthropic:claude-3-5-sonnet-latest",
    tools=[book_hotel, transfer_to_flight_assistant],
    prompt="You are a hotel booking assistant",
    name="hotel_assistant"
)

# Define multi-agent graph
multi_agent_graph = (
    StateGraph(MessagesState)
    .add_node(flight_assistant)
    .add_node(hotel_assistant)
    .add_edge(START, "flight_assistant")
    .compile()
)

# Run the multi-agent graph
for chunk in multi_agent_graph.stream(
    {
        "messages": [
            {
                "role": "user",
                "content": "book a flight from BOS to JFK and a stay at McKittrick Hotel"
            }
        ]
    }
):
    print(chunk)
    print("\n")

访问智能体的状态
Command 原始操作允许将状态更新和节点转换作为单个操作进行指定，这对于实现移交非常有用。
要移交到的智能体或节点的名称。
获取智能体的消息并将其作为移交的一部分**添加**到父级的**状态**中。下一个智能体将看到父级状态。
指示 LangGraph 我们需要导航到**父级**多智能体图中的智能体节点。

注意

此移交实现假设：

多智能体系统中的每个智能体都将整体消息历史（所有智能体的）作为其输入接收
每个智能体将其内部消息历史输出到多智能体系统的整体消息历史中

查看 LangGraph 主管和群组文档，了解如何自定义移交。