LangGraph 多智能体群集是一种 Python 库，用于创建基于 LangGraph 的多智能体系统。这种系统允许智能体根据其专业化动态地将控制权交给彼此，并记住最后活跃的智能体，以便在后续交互中继续对话。

基础概念

多智能体协作：不同智能体可以合作并将上下文传递给彼此。可定制的交接工具：内置工具用于智能体之间的通信。

安装和快速开始

安装库：

pip install langgraph-swarm langchain-openai

设置 OpenAI API：

export OPENAI_API_KEY=

创建智能体：

from langchain_openai import ChatOpenAIfrom langgraph.checkpoint.memory import InMemorySaverfrom langgraph.prebuilt import create_react_agentfrom langgraph_swarm import create_handoff_tool, create_swarmmodel = ChatOpenAI(model="gpt-4o")def add(a: int, b: int) -> int:    return a + balice = create_react_agent(    model,    [add, create_handoff_tool(agent_name="Bob")],    prompt="You are Alice, an addition expert.",    name="Alice",)bob = create_react_agent(    model,    [create_handoff_tool(agent_name="Alice", description="Transfer to Alice, she can help with math")],    prompt="You are Bob, you speak like a pirate.",    name="Bob",)checkpointer = InMemorySaver()workflow = create_swarm([alice, bob], default_active_agent="Alice")app = workflow.compile(checkpointer=checkpointer)config = {"configurable": {"thread_id": "1"}}turn_1 = app.invoke({"messages": [{"role": "user", "content": "i'd like to speak to Bob"}]}, config)print(turn_1)turn_2 = app.invoke({"messages": [{"role": "user", "content": "what's 5 + 7?"}]}, config)print(turn_2)

内存管理

短期内存：使用 InMemorySaver 来维持对话状态。长期内存：使用 InMemoryStore 来存储历史数据。

自定义

自定义交接工具：

from langchain_core.tools import tool, BaseToolfrom langchain_core.messages import ToolMessagefrom langgraph.types import Commanddef create_custom_handoff_tool(*, agent_name: str, tool_name: str, tool_description: str) -> BaseTool:    @tool(name=tool_name, description=tool_description)    def handoff_to_agent(task_description: str, state: dict, tool_call_id: str):        tool_message = ToolMessage(            content=f"Successfully transferred to {agent_name}",            name=tool_name,            tool_call_id=tool_call_id,        )        return Command(            goto=agent_name,            graph=Command.PARENT,            update={                "messages": [state["messages"][-1], tool_message],                "active_agent": agent_name,                "task_description": task_description,            },        )    return handoff_to_agent

自定义智能体实现：

from langchain_core.messages import AnyMessagefrom langgraph.graph import StateGraphclass AliceState:    alice_messages: list[AnyMessage]alice = (    StateGraph(AliceState)    .add_node("model", ...)    .add_node("tools", ...)    .add_edge(...)    .compile())def call_alice(state):    response = alice.invoke({"alice_messages": state["messages"]})    return {"messages": response["alice_messages"]}workflow = (    StateGraph()    .add_node("Alice", call_alice, destinations=("Bob",))    .add_node("Bob", call_bob, destinations=("Alice",)))workflow = add_active_agent_router(workflow, route_to=["Alice", "Bob"], default_active_agent="Alice")app = workflow.compile()

总结

LangGraph 多智能体群集提供了一个灵活的框架，用于创建多智能体系统。通过自定义交接工具和智能体实现，可以满足不同应用场景的需求。同时，内存管理对于维持对话状态至关重要。