ToolNode 是一个 LangChain Runnable，它以图形状态（带有消息列表）作为输入，并使用工具调用的结果输出状态更新。它被设计为与 LangGraph 预构建的 ReAct 代理一起开箱即用，但也可以与任何 StateGraph 一起工作，只要它的状态有一个带有reducer的message key（参见 MessagesState）。from langchain_core.messages import AIMessagefrom langchain_core.tools import toolfrom langgraph.prebuilt import ToolNode@tooldef get_weather(location: str): """Call to get the current weather.""" if location.lower() in ["sf", "san francisco"]: return "It's 60 degrees and foggy." else: return "It's 90 degrees and sunny."@tooldef get_coolest_cities(): """Get a list of coolest cities""" return "nyc, sf"tools = [get_weather, get_coolest_cities]tool_node = ToolNode(tools)
ToolNode 使用消息列表对graph状态进行操作。它要求列表中的最后一条消息是带有 tool_calls 参数的 AIMessage。message_with_single_tool_call = AIMessage( content="", tool_calls=[ { "name": "get_weather", "args": {"location": "sf"}, "id": "tool_call_id", "type": "tool_call", } ],)print(tool_node.invoke({"messages": [message_with_single_tool_call]}))
{'messages': [ToolMessage(content="It's 60 degrees and foggy.", name='get_weather', tool_call_id='tool_call_id')]}
注意，通常我们不需要手动创建 AIMessage，它将由任何支持工具调用的 LangChain 聊天模型自动生成。如果将多个工具调用传递给 AIMessage 的 tool_calls 参数，还可以使用 ToolNode 进行并行工具调用：message_with_multiple_tool_calls = AIMessage( content="", tool_calls=[ { "name": "get_coolest_cities", "args": {}, "id": "tool_call_id_1", "type": "tool_call", }, { "name": "get_weather", "args": {"location": "sf"}, "id": "tool_call_id_2", "type": "tool_call", }, ],)print(tool_node.invoke({"messages": [message_with_multiple_tool_calls]}))
{'messages': [ToolMessage(content='nyc, sf', name='get_coolest_cities', tool_call_id='tool_call_id_1'), ToolMessage(content="It's 60 degrees and foggy.", name='get_weather', tool_call_id='tool_call_id_2')]}
我们通常会使用到一个叫做 bind_tools的方法：from langchain_ollama import ChatOllamaimport base_confmodel_with_tools = (ChatOllama(base_url=base_conf.base_url, model=base_conf.model_name) .bind_tools(tools))print(model_with_tools.invoke("what's the weather in sf?").tool_calls)
[{'name': 'get_weather', 'args': {'location': 'sf'}, 'id': 'ba41aa58-1d28-4228-bd9f-44fce328cf8c', 'type': 'tool_call'}]
如你所见，聊天模型生成的 AI 消息已经填充了 tool_calls，因此我们可以直接将其传递给 ToolNodetool_node.invoke({"messages": [model_with_tools.invoke("what's the weather in sf?")]})
{'messages': [ToolMessage(content="It's 60 degrees and foggy.", name='get_weather', tool_call_id='a433fe97-736f-4518-b8c4-c930767ea99f')]}
接下来，让我们看看如何在 LangGraph 图表中使用 ToolNode。让我们设置 ReAct agent的graph实现。该代理将一些查询作为输入，然后反复调用工具，直到它有足够的信息来解决查询。我们基本沿用上面定义好的一些代码from typing import Literalfrom langgraph.graph import StateGraph, MessagesState, START, END
def should_continue(state: MessagesState): messages = state["messages"] last_message = messages[-1] if last_message.tool_calls: return "tools" return END
def call_model(state: MessagesState): messages = state["messages"] response = model_with_tools.invoke(messages) return {"messages": [response]}
workflow = StateGraph(MessagesState)# Define the two nodes we will cycle betweenworkflow.add_node("agent", call_model)workflow.add_node("tools", tool_node)workflow.add_edge(START, "agent")workflow.add_conditional_edges("agent", should_continue, ["tools", END])workflow.add_edge("tools", "agent")app = workflow.compile()
for chunk in app.stream( {"messages": [("human", "what's the weather in sf?")]}, stream_mode="values"): chunk["messages"][-1].pretty_print()
================================ Human Message =================================
what's the weather in sf?================================== Ai Message ==================================Tool Calls: get_weather (0969a8d8-490e-4c2d-bbaa-fda07bdd917d) Call ID: 0969a8d8-490e-4c2d-bbaa-fda07bdd917d Args: location: sf================================= Tool Message =================================Name: get_weather
It's 60 degrees and foggy.================================== Ai Message ==================================
The current weather in SF is 60 degrees with some fog.
for chunk in app.stream( {"messages": [("human", "what's the weather in the coolest cities?")]}, stream_mode="values",): chunk["messages"][-1].pretty_print()
================================ Human Message =================================
what's the weather in the coolest cities?================================== Ai Message ==================================Tool Calls: get_coolest_cities (6e1f1592-d214-40c8-929d-e6476d2881bc) Call ID: 6e1f1592-d214-40c8-929d-e6476d2881bc Args:================================= Tool Message =================================Name: get_coolest_cities
nyc, sf================================== Ai Message ==================================Tool Calls: get_weather (1c308e8a-026a-4ed0-9e12-3d2512b477ac) Call ID: 1c308e8a-026a-4ed0-9e12-3d2512b477ac Args: location: New York City get_weather (a725f375-5150-4ab9-af97-eb8d3b039073) Call ID: a725f375-5150-4ab9-af97-eb8d3b039073 Args: location: San Francisco================================= Tool Message =================================Name: get_weather
It's 60 degrees and foggy.================================== Ai Message ==================================
The weather in the coolest cities, New York City and San Francisco, is as follows:
- In New York City, it's currently 90 degrees with clear skies and sunny conditions.- In San Francisco, it's a more comfortable 60 degrees with some fog.
Stay cool out there!
ToolNode 还可以处理工具执行期间的错误。可以通过设置 handle_tool_errors=True（默认启用）来启用/禁用此功能。
