如何将配置传递给工具¶

前置条件

本指南假设您熟悉以下内容：

在运行时，您可能需要将值传递给工具，例如用户ID，该值应由应用程序逻辑设置，而不是由LLM控制，以确保安全。LLM应仅管理其预期的参数。

LangChain工具使用Runnable接口，其中invoke等方法通过带有RunnableConfig类型注解的配置参数接受运行时信息。

在以下示例中，我们将设置一个代理，使用工具来管理用户的最爱宠物——添加、读取和删除条目——同时通过应用程序逻辑修复用户ID，并让聊天模型控制其他参数。

设置¶

首先，让我们安装所需的包并设置API密钥

%%capture --no-stderr
%pip install --quiet -U langgraph langchain_anthropic

import getpass
import os


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


_set_env("ANTHROPIC_API_KEY")

为LangGraph开发设置LangSmith

注册LangSmith，可以快速发现并解决您的LangGraph项目中的问题，提高项目性能。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应用程序——更多关于如何开始的信息，请参阅这里。

定义工具和模型¶

配置类型注解

每个工具函数都可以接受一个config参数。为了确保配置能够正确地传递给函数，你必须始终为你的config参数添加RunnableConfig类型注解。例如：

def my_tool(tool_arg: str, config: RunnableConfig):
    ...

from typing import List

from langchain_core.tools import tool
from langchain_core.runnables.config import RunnableConfig

from langgraph.prebuilt import ToolNode

user_to_pets = {}


@tool(parse_docstring=True)
def update_favorite_pets(
    # NOTE: config arg does not need to be added to docstring, as we don't want it to be included in the function signature attached to the LLM
    pets: List[str],
    config: RunnableConfig,
) -> None:
    """Add the list of favorite pets.

    Args:
        pets: List of favorite pets to set.
    """
    user_id = config.get("configurable", {}).get("user_id")
    user_to_pets[user_id] = pets


@tool
def delete_favorite_pets(config: RunnableConfig) -> None:
    """Delete the list of favorite pets."""
    user_id = config.get("configurable", {}).get("user_id")
    if user_id in user_to_pets:
        del user_to_pets[user_id]


@tool
def list_favorite_pets(config: RunnableConfig) -> None:
    """List favorite pets if asked to."""
    user_id = config.get("configurable", {}).get("user_id")
    return ", ".join(user_to_pets.get(user_id, []))


tools = [update_favorite_pets, delete_favorite_pets, list_favorite_pets]

API Reference: tool | RunnableConfig | ToolNode

我们将在这个示例中使用Anthropic提供的一个小型聊天模型。

from langchain_anthropic import ChatAnthropic
from langgraph.graph import StateGraph, MessagesState
from langgraph.prebuilt import ToolNode


model = ChatAnthropic(model="claude-3-5-haiku-latest")

API Reference: ChatAnthropic | StateGraph | ToolNode

ReAct 代理¶

让我们设置一个ReAct 代理的图实现。该代理接收一些查询作为输入，然后反复调用工具，直到它拥有足够的信息来解决该查询。我们将使用预构建的create_react_agent和Anthropic模型，以及我们刚刚定义的工具。注意：工具会通过model.bind_tools在create_react_agent实现中自动添加到模型中。

from langgraph.prebuilt import create_react_agent
from IPython.display import Image, display

graph = create_react_agent(model, tools)

try:
    display(Image(graph.get_graph().draw_mermaid_png()))
except Exception:
    # This requires some extra dependencies and is optional
    pass

API Reference: create_react_agent

使用它！¶

from langchain_core.messages import HumanMessage

user_to_pets.clear()  # Clear the state

print(f"User information prior to run: {user_to_pets}")

inputs = {"messages": [HumanMessage(content="my favorite pets are cats and dogs")]}
for chunk in graph.stream(
    inputs, {"configurable": {"user_id": "123"}}, stream_mode="values"
):
    chunk["messages"][-1].pretty_print()

print(f"User information after the run: {user_to_pets}")

API Reference: HumanMessage

User information prior to run: {}
================================[1m Human Message [0m=================================

my favorite pets are cats and dogs
==================================[1m Ai Message [0m==================================

[{'text': "I'll help you update your favorite pets using the `update_favorite_pets` function.", 'type': 'text'}, {'id': 'toolu_015jtecJ4jnosAfXEC3KADS2', 'input': {'pets': ['cats', 'dogs']}, 'name': 'update_favorite_pets', 'type': 'tool_use'}]
Tool Calls:
  update_favorite_pets (toolu_015jtecJ4jnosAfXEC3KADS2)
 Call ID: toolu_015jtecJ4jnosAfXEC3KADS2
  Args:
    pets: ['cats', 'dogs']
=================================[1m Tool Message [0m=================================
Name: update_favorite_pets

null
==================================[1m Ai Message [0m==================================

Great! I've added cats and dogs to your list of favorite pets. Would you like to confirm the list or do anything else with it?
User information after the run: {'123': ['cats', 'dogs']}

from langchain_core.messages import HumanMessage

print(f"User information prior to run: {user_to_pets}")

inputs = {"messages": [HumanMessage(content="what are my favorite pets")]}
for chunk in graph.stream(
    inputs, {"configurable": {"user_id": "123"}}, stream_mode="values"
):
    chunk["messages"][-1].pretty_print()

print(f"User information prior to run: {user_to_pets}")

API Reference: HumanMessage

User information prior to run: {'123': ['cats', 'dogs']}
================================[1m Human Message [0m=================================

what are my favorite pets
==================================[1m Ai Message [0m==================================

[{'text': "I'll help you check your favorite pets by using the list_favorite_pets function.", 'type': 'text'}, {'id': 'toolu_01EMTtX5WtKJXMJ4WqXpxPUw', 'input': {}, 'name': 'list_favorite_pets', 'type': 'tool_use'}]
Tool Calls:
  list_favorite_pets (toolu_01EMTtX5WtKJXMJ4WqXpxPUw)
 Call ID: toolu_01EMTtX5WtKJXMJ4WqXpxPUw
  Args:
=================================[1m Tool Message [0m=================================
Name: list_favorite_pets

cats, dogs
==================================[1m Ai Message [0m==================================

Based on the results, your favorite pets are cats and dogs.

Is there anything else you'd like to know about your favorite pets, or would you like to update the list?
User information prior to run: {'123': ['cats', 'dogs']}

print(f"User information prior to run: {user_to_pets}")

inputs = {
    "messages": [
        HumanMessage(content="please forget what i told you about my favorite animals")
    ]
}
for chunk in graph.stream(
    inputs, {"configurable": {"user_id": "123"}}, stream_mode="values"
):
    chunk["messages"][-1].pretty_print()

print(f"User information prior to run: {user_to_pets}")

User information prior to run: {'123': ['cats', 'dogs']}
================================[1m Human Message [0m=================================

please forget what i told you about my favorite animals
==================================[1m Ai Message [0m==================================

[{'text': "I'll help you delete the list of favorite pets. I'll use the delete_favorite_pets function to remove any previously saved list.", 'type': 'text'}, {'id': 'toolu_01JqpxgxdsDJFMzSLeogoRtG', 'input': {}, 'name': 'delete_favorite_pets', 'type': 'tool_use'}]
Tool Calls:
  delete_favorite_pets (toolu_01JqpxgxdsDJFMzSLeogoRtG)
 Call ID: toolu_01JqpxgxdsDJFMzSLeogoRtG
  Args:
=================================[1m Tool Message [0m=================================
Name: delete_favorite_pets

null
==================================[1m Ai Message [0m==================================

The list of favorite pets has been deleted. If you'd like to create a new list of favorite pets in the future, just let me know.
User information prior to run: {}

如何将配置传递给工具¶

设置¶

定义工具和模型¶

ReAct 代理¶

使用它！¶

Comments