如何审查工具调用（函数式 API）¶

前提条件

本指南假设您熟悉以下内容

使用 interrupt 实现人机环路工作流程
如何使用函数式 API 创建 ReAct agent

本指南演示了如何使用 LangGraph 函数式 API 在 ReAct agent 中实现人机环路工作流程。

我们将以“如何使用函数式 API 创建 ReAct agent”指南中创建的 agent 为基础进行构建。

具体来说，我们将演示如何在执行之前审查工具调用，这些工具调用由聊天模型生成。这可以通过在应用程序的关键点使用 interrupt 函数来实现。

预览:

我们将实现一个简单的函数来审查从我们的聊天模型生成的工具调用，并在应用程序的入口点内部调用它

def review_tool_call(tool_call: ToolCall) -> Union[ToolCall, ToolMessage]:
    """Review a tool call, returning a validated version."""
    human_review = interrupt(
        {
            "question": "Is this correct?",
            "tool_call": tool_call,
        }
    )
    review_action = human_review["action"]
    review_data = human_review.get("data")
    if review_action == "continue":
        return tool_call
    elif review_action == "update":
        updated_tool_call = {**tool_call, **{"args": review_data}}
        return updated_tool_call
    elif review_action == "feedback":
        return ToolMessage(
            content=review_data, name=tool_call["name"], tool_call_id=tool_call["id"]
        )

设置¶

首先，让我们安装所需的软件包并设置我们的 API 密钥

%%capture --no-stderr
%pip install -U langgraph langchain-openai

import getpass
import os


def _set_env(var: str):
    if not os.environ.get(var):
        os.environ[var] = getpass.getpass(f"{var}: ")


_set_env("OPENAI_API_KEY")

设置 LangSmith 以获得更好的调试体验

注册 LangSmith 以快速发现问题并提高 LangGraph 项目的性能。LangSmith 允许您使用跟踪数据来调试、测试和监控使用 LangGraph 构建的 LLM 应用 — 在文档中阅读更多关于如何开始的信息。

定义模型和工具¶

首先，让我们定义将在示例中使用的工具和模型。与 ReAct agent 指南中一样，我们将使用一个占位符工具，用于获取某个地点的天气描述。

我们将在此示例中使用 OpenAI 聊天模型，但任何支持工具调用的模型都足够。

from langchain_openai import ChatOpenAI
from langchain_core.tools import tool

model = ChatOpenAI(model="gpt-4o-mini")


@tool
def get_weather(location: str):
    """Call to get the weather from a specific location."""
    # This is a placeholder for the actual implementation
    if any([city in location.lower() for city in ["sf", "san francisco"]]):
        return "It's sunny!"
    elif "boston" in location.lower():
        return "It's rainy!"
    else:
        return f"I am not sure what the weather is in {location}"


tools = [get_weather]

API 参考：ChatOpenAI | tool

定义任务¶

我们的任务与 ReAct agent 指南中的任务相同

调用模型：我们希望使用消息列表查询我们的聊天模型。
调用工具：如果我们的模型生成工具调用，我们希望执行它们。

from langchain_core.messages import ToolCall, ToolMessage
from langgraph.func import entrypoint, task


tools_by_name = {tool.name: tool for tool in tools}


@task
def call_model(messages):
    """Call model with a sequence of messages."""
    response = model.bind_tools(tools).invoke(messages)
    return response


@task
def call_tool(tool_call):
    tool = tools_by_name[tool_call["name"]]
    observation = tool.invoke(tool_call["args"])
    return ToolMessage(content=observation, tool_call_id=tool_call["id"])

API 参考：ToolCall | ToolMessage | entrypoint | task

定义入口点¶

为了在执行之前审查工具调用，我们添加了一个 review_tool_call 函数，该函数调用 interrupt。当调用此函数时，执行将暂停，直到我们发出恢复它的命令。

给定一个工具调用，我们的函数将 interrupt 以供人工审查。此时，我们可以选择

接受工具调用；
修改工具调用并继续；
生成自定义工具消息（例如，指示模型重新格式化其工具调用）。

我们将在下面的用法示例中演示这三种情况。

from typing import Union


def review_tool_call(tool_call: ToolCall) -> Union[ToolCall, ToolMessage]:
    """Review a tool call, returning a validated version."""
    human_review = interrupt(
        {
            "question": "Is this correct?",
            "tool_call": tool_call,
        }
    )
    review_action = human_review["action"]
    review_data = human_review.get("data")
    if review_action == "continue":
        return tool_call
    elif review_action == "update":
        updated_tool_call = {**tool_call, **{"args": review_data}}
        return updated_tool_call
    elif review_action == "feedback":
        return ToolMessage(
            content=review_data, name=tool_call["name"], tool_call_id=tool_call["id"]
        )

我们现在可以更新我们的入口点以审查生成的工具调用。如果工具调用被接受或修改，我们以与之前相同的方式执行。否则，我们只需附加由人提供的 ToolMessage。

提示

先前任务的结果（在本例中为初始模型调用）会被持久化，以便在 interrupt 后不会再次运行。

from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph.message import add_messages
from langgraph.types import Command, interrupt


checkpointer = MemorySaver()


@entrypoint(checkpointer=checkpointer)
def agent(messages, previous):
    if previous is not None:
        messages = add_messages(previous, messages)

    llm_response = call_model(messages).result()
    while True:
        if not llm_response.tool_calls:
            break

        # Review tool calls
        tool_results = []
        tool_calls = []
        for i, tool_call in enumerate(llm_response.tool_calls):
            review = review_tool_call(tool_call)
            if isinstance(review, ToolMessage):
                tool_results.append(review)
            else:  # is a validated tool call
                tool_calls.append(review)
                if review != tool_call:
                    llm_response.tool_calls[i] = review  # update message

        # Execute remaining tool calls
        tool_result_futures = [call_tool(tool_call) for tool_call in tool_calls]
        remaining_tool_results = [fut.result() for fut in tool_result_futures]

        # Append to message list
        messages = add_messages(
            messages,
            [llm_response, *tool_results, *remaining_tool_results],
        )

        # Call model again
        llm_response = call_model(messages).result()

    # Generate final response
    messages = add_messages(messages, llm_response)
    return entrypoint.final(value=llm_response, save=messages)

API 参考：MemorySaver | add_messages | Command | interrupt

用法¶

让我们演示一些场景。

def _print_step(step: dict) -> None:
    for task_name, result in step.items():
        if task_name == "agent":
            continue  # just stream from tasks
        print(f"\n{task_name}:")
        if task_name in ("__interrupt__", "review_tool_call"):
            print(result)
        else:
            result.pretty_print()

接受工具调用¶

要接受工具调用，我们只需在 Command 中提供的数据中指示工具调用应通过。

config = {"configurable": {"thread_id": "1"}}

user_message = {"role": "user", "content": "What's the weather in san francisco?"}
print(user_message)

for step in agent.stream([user_message], config):
    _print_step(step)

{'role': 'user', 'content': "What's the weather in san francisco?"}

call_model:
==================================[1m Ai Message [0m==================================
Tool Calls:
  get_weather (call_Bh5cSwMqCpCxTjx7AjdrQTPd)
 Call ID: call_Bh5cSwMqCpCxTjx7AjdrQTPd
  Args:
    location: San Francisco

__interrupt__:
(Interrupt(value={'question': 'Is this correct?', 'tool_call': {'name': 'get_weather', 'args': {'location': 'San Francisco'}, 'id': 'call_Bh5cSwMqCpCxTjx7AjdrQTPd', 'type': 'tool_call'}}, resumable=True, ns=['agent:22fcc9cd-3573-b39b-eea7-272a025903e2'], when='during'),)

human_input = Command(resume={"action": "continue"})

for step in agent.stream(human_input, config):
    _print_step(step)

call_tool:
=================================[1m Tool Message [0m=================================

It's sunny!

call_model:
==================================[1m Ai Message [0m==================================

The weather in San Francisco is sunny!

修改工具调用¶

要修改工具调用，我们可以提供更新的参数。

config = {"configurable": {"thread_id": "2"}}

user_message = {"role": "user", "content": "What's the weather in san francisco?"}
print(user_message)

for step in agent.stream([user_message], config):
    _print_step(step)

{'role': 'user', 'content': "What's the weather in san francisco?"}

call_model:
==================================[1m Ai Message [0m==================================
Tool Calls:
  get_weather (call_b9h8e18FqH0IQm3NMoeYKz6N)
 Call ID: call_b9h8e18FqH0IQm3NMoeYKz6N
  Args:
    location: san francisco

__interrupt__:
(Interrupt(value={'question': 'Is this correct?', 'tool_call': {'name': 'get_weather', 'args': {'location': 'san francisco'}, 'id': 'call_b9h8e18FqH0IQm3NMoeYKz6N', 'type': 'tool_call'}}, resumable=True, ns=['agent:9559a81d-5720-dc19-a457-457bac7bdd83'], when='during'),)

human_input = Command(resume={"action": "update", "data": {"location": "SF, CA"}})

for step in agent.stream(human_input, config):
    _print_step(step)

call_tool:
=================================[1m Tool Message [0m=================================

It's sunny!

call_model:
==================================[1m Ai Message [0m==================================

The weather in San Francisco is sunny!

此运行的 LangSmith 跟踪信息量特别大

在 interrupt 之前的跟踪中，我们为位置 “San Francisco” 生成了一个工具调用。
在恢复后的跟踪中，我们看到消息中的工具调用已更新为 “SF, CA”。

生成自定义 ToolMessage¶

要生成自定义 ToolMessage，我们提供消息的内容。在本例中，我们将要求模型重新格式化其工具调用。

config = {"configurable": {"thread_id": "3"}}

user_message = {"role": "user", "content": "What's the weather in san francisco?"}
print(user_message)

for step in agent.stream([user_message], config):
    _print_step(step)

{'role': 'user', 'content': "What's the weather in san francisco?"}

call_model:
==================================[1m Ai Message [0m==================================
Tool Calls:
  get_weather (call_VqGjKE7uu8HdWs9XuY1kMV18)
 Call ID: call_VqGjKE7uu8HdWs9XuY1kMV18
  Args:
    location: San Francisco

__interrupt__:
(Interrupt(value={'question': 'Is this correct?', 'tool_call': {'name': 'get_weather', 'args': {'location': 'San Francisco'}, 'id': 'call_VqGjKE7uu8HdWs9XuY1kMV18', 'type': 'tool_call'}}, resumable=True, ns=['agent:4b3b372b-9da3-70be-5c68-3d9317346070'], when='during'),)

human_input = Command(
    resume={
        "action": "feedback",
        "data": "Please format as <City>, <State>.",
    },
)

for step in agent.stream(human_input, config):
    _print_step(step)

call_model:
==================================[1m Ai Message [0m==================================
Tool Calls:
  get_weather (call_xoXkK8Cz0zIpvWs78qnXpvYp)
 Call ID: call_xoXkK8Cz0zIpvWs78qnXpvYp
  Args:
    location: San Francisco, CA

__interrupt__:
(Interrupt(value={'question': 'Is this correct?', 'tool_call': {'name': 'get_weather', 'args': {'location': 'San Francisco, CA'}, 'id': 'call_xoXkK8Cz0zIpvWs78qnXpvYp', 'type': 'tool_call'}}, resumable=True, ns=['agent:4b3b372b-9da3-70be-5c68-3d9317346070'], when='during'),)

一旦重新格式化，我们就可以接受它

human_input = Command(resume={"action": "continue"})

for step in agent.stream(human_input, config):
    _print_step(step)

call_tool:
=================================[1m Tool Message [0m=================================

It's sunny!

call_model:
==================================[1m Ai Message [0m==================================

The weather in San Francisco, CA is sunny!