如何将运行时值传递给工具

📚Prerequisites

• Chat models
• LangChain Tools
• How to create tools
• How to use a model to call tools

📦Compatibility

The code in this guide requires langchain-core>=0.2.21. Please ensure you have the correct packages installed.

您可能需要将仅在运行时知晓的值绑定到 工具 (tool)。例如，工具逻辑可能需要使用发出请求的用户的 ID。

大多数情况下，这些值不应由 LLM 控制。实际上，允许 LLM 控制用户 ID 可能会带来安全风险。

相反，LLM 应只控制工具中旨在由 LLM 控制的参数，而其他参数（如用户 ID）应由应用程序逻辑固定。

本指南将展示如何阻止模型生成某些工具参数，并在运行时直接注入这些参数。

与 LangGraph 一起使用

如果您正在使用 LangGraph，请参考本指南，它展示了如何创建一个代理来跟踪给定用户最喜欢的宠物。

我们可以将它们绑定到聊天模型，如下所示：

Select chat model:

OpenAI

Anthropic

Azure

Google Gemini

Google Vertex

AWS

Groq

Cohere

NVIDIA

Fireworks AI

Mistral AI

Together AI

IBM watsonx

Databricks

xAI

Perplexity

pip install -qU "langchain[google-genai]"

import getpass
import os

if not os.environ.get("GOOGLE_API_KEY"):
  os.environ["GOOGLE_API_KEY"] = getpass.getpass("Enter API key for Google Gemini: ")

from langchain.chat_models import init_chat_model

llm = init_chat_model("gemini-2.0-flash", model_provider="google_genai")

隐藏参数

我们可以使用 InjectedToolArg 注解来标记 Tool 中的某些参数，例如 user_id，表示它们将在运行时注入，这意味着模型不应为其生成值。

from typing import List

from langchain_core.tools import InjectedToolArg, tool
from typing_extensions import Annotated

user_to_pets = {}


@tool(parse_docstring=True)
def update_favorite_pets(
    pets: List[str], user_id: Annotated[str, InjectedToolArg]
) -> None:
    """Add the list of favorite pets.

    Args:
        pets: List of favorite pets to set.
        user_id: User's ID.
    """
    user_to_pets[user_id] = pets


@tool(parse_docstring=True)
def delete_favorite_pets(user_id: Annotated[str, InjectedToolArg]) -> None:
    """Delete the list of favorite pets.

    Args:
        user_id: User's ID.
    """
    if user_id in user_to_pets:
        del user_to_pets[user_id]


@tool(parse_docstring=True)
def list_favorite_pets(user_id: Annotated[str, InjectedToolArg]) -> None:
    """List favorite pets if any.

    Args:
        user_id: User's ID.
    """
    return user_to_pets.get(user_id, [])

API Reference:InjectedToolArg | tool

如果我们查看这些工具的输入 schema，会发现 user_id 仍然被列了出来：

update_favorite_pets.get_input_schema().model_json_schema()

{'description': 'Add the list of favorite pets.',
 'properties': {'pets': {'description': 'List of favorite pets to set.',
   'items': {'type': 'string'},
   'title': 'Pets',
   'type': 'array'},
  'user_id': {'description': "User's ID.",
   'title': 'User Id',
   'type': 'string'}},
 'required': ['pets', 'user_id'],
 'title': 'update_favorite_petsSchema',
 'type': 'object'}

但如果我们查看工具调用模式，也就是传递给模型的用于工具调用的模式，user_id 已经被移除了：

update_favorite_pets.tool_call_schema.model_json_schema()

{'description': 'Add the list of favorite pets.',
 'properties': {'pets': {'description': 'List of favorite pets to set.',
   'items': {'type': 'string'},
   'title': 'Pets',
   'type': 'array'}},
 'required': ['pets'],
 'title': 'update_favorite_pets',
 'type': 'object'}

所以，当我们调用我们的工具时，我们需要传入 user_id：

user_id = "123"
update_favorite_pets.invoke({"pets": ["lizard", "dog"], "user_id": user_id})
print(user_to_pets)
print(list_favorite_pets.invoke({"user_id": user_id}))

{'123': ['lizard', 'dog']}
['lizard', 'dog']

但是，当模型调用工具时，不会生成 user_id 参数：

tools = [
    update_favorite_pets,
    delete_favorite_pets,
    list_favorite_pets,
]
llm_with_tools = llm.bind_tools(tools)
ai_msg = llm_with_tools.invoke("my favorite animals are cats and parrots")
ai_msg.tool_calls

[{'name': 'update_favorite_pets',
  'args': {'pets': ['cats', 'parrots']},
  'id': 'call_pZ6XVREGh1L0BBSsiGIf1xVm',
  'type': 'tool_call'}]

在运行时注入参数

如果我们希望使用模型生成的工具调用来实际执行我们的工具，我们就需要自己注入 user_id：

from copy import deepcopy

from langchain_core.runnables import chain


@chain
def inject_user_id(ai_msg):
    tool_calls = []
    for tool_call in ai_msg.tool_calls:
        tool_call_copy = deepcopy(tool_call)
        tool_call_copy["args"]["user_id"] = user_id
        tool_calls.append(tool_call_copy)
    return tool_calls


inject_user_id.invoke(ai_msg)

API Reference:chain

[{'name': 'update_favorite_pets',
  'args': {'pets': ['cats', 'parrots'], 'user_id': '123'},
  'id': 'call_pZ6XVREGh1L0BBSsiGIf1xVm',
  'type': 'tool_call'}]

现在我们可以将模型、注入代码和实际工具链接起来，创建一个工具执行链：

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


@chain
def tool_router(tool_call):
    return tool_map[tool_call["name"]]


chain = llm_with_tools | inject_user_id | tool_router.map()
chain.invoke("my favorite animals are cats and parrots")

[ToolMessage(content='null', name='update_favorite_pets', tool_call_id='call_oYCD0THSedHTbwNAY3NW6uUj')]

查看 user_to_pets 字典，我们可以看到其中已更新，加入了猫和鹦鹉：

user_to_pets

{'123': ['cats', 'parrots']}

参数的另外几种注解方式

这里列出了几种注解我们工具参数的另外方式：

from langchain_core.tools import BaseTool
from pydantic import BaseModel, Field


class UpdateFavoritePetsSchema(BaseModel):
    """Update list of favorite pets"""

    pets: List[str] = Field(..., description="List of favorite pets to set.")
    user_id: Annotated[str, InjectedToolArg] = Field(..., description="User's ID.")


@tool(args_schema=UpdateFavoritePetsSchema)
def update_favorite_pets(pets, user_id):
    user_to_pets[user_id] = pets


update_favorite_pets.get_input_schema().model_json_schema()

API Reference:BaseTool

{'description': 'Update list of favorite pets',
 'properties': {'pets': {'description': 'List of favorite pets to set.',
   'items': {'type': 'string'},
   'title': 'Pets',
   'type': 'array'},
  'user_id': {'description': "User's ID.",
   'title': 'User Id',
   'type': 'string'}},
 'required': ['pets', 'user_id'],
 'title': 'UpdateFavoritePetsSchema',
 'type': 'object'}

update_favorite_pets.tool_call_schema.model_json_schema()

{'description': 'Update list of favorite pets',
 'properties': {'pets': {'description': 'List of favorite pets to set.',
   'items': {'type': 'string'},
   'title': 'Pets',
   'type': 'array'}},
 'required': ['pets'],
 'title': 'update_favorite_pets',
 'type': 'object'}

from typing import Optional, Type


class UpdateFavoritePets(BaseTool):
    name: str = "update_favorite_pets"
    description: str = "Update list of favorite pets"
    args_schema: Optional[Type[BaseModel]] = UpdateFavoritePetsSchema

    def _run(self, pets, user_id):
        user_to_pets[user_id] = pets


UpdateFavoritePets().get_input_schema().model_json_schema()

{'description': 'Update list of favorite pets',
 'properties': {'pets': {'description': 'List of favorite pets to set.',
   'items': {'type': 'string'},
   'title': 'Pets',
   'type': 'array'},
  'user_id': {'description': "User's ID.",
   'title': 'User Id',
   'type': 'string'}},
 'required': ['pets', 'user_id'],
 'title': 'UpdateFavoritePetsSchema',
 'type': 'object'}

UpdateFavoritePets().tool_call_schema.model_json_schema()

{'description': 'Update list of favorite pets',
 'properties': {'pets': {'description': 'List of favorite pets to set.',
   'items': {'type': 'string'},
   'title': 'Pets',
   'type': 'array'}},
 'required': ['pets'],
 'title': 'update_favorite_pets',
 'type': 'object'}

class UpdateFavoritePets2(BaseTool):
    name: str = "update_favorite_pets"
    description: str = "Update list of favorite pets"

    def _run(self, pets: List[str], user_id: Annotated[str, InjectedToolArg]) -> None:
        user_to_pets[user_id] = pets


UpdateFavoritePets2().get_input_schema().model_json_schema()

{'description': 'Use the tool.\n\nAdd run_manager: Optional[CallbackManagerForToolRun] = None\nto child implementations to enable tracing.',
 'properties': {'pets': {'items': {'type': 'string'},
   'title': 'Pets',
   'type': 'array'},
  'user_id': {'title': 'User Id', 'type': 'string'}},
 'required': ['pets', 'user_id'],
 'title': 'update_favorite_petsSchema',
 'type': 'object'}

UpdateFavoritePets2().tool_call_schema.model_json_schema()

{'description': 'Update list of favorite pets',
 'properties': {'pets': {'items': {'type': 'string'},
   'title': 'Pets',
   'type': 'array'}},
 'required': ['pets'],
 'title': 'update_favorite_pets',
 'type': 'object'}