如何将运行时值传递给工具¶
有时，您可能希望让一个调用工具的 LLM 填充工具函数参数的子集，并在运行时为其他参数提供其他值。如果您使用 LangChain 风格的 工具，处理此问题的简单方法是使用 InjectedArg 对函数参数进行标注。此标注将该参数排除在向 LLM 显示之外。
在 LangGraph 应用程序中，您可能希望在运行时将图状态或 共享内存（存储）传递给工具。这种类型的有状态工具在工具的输出受过去代理步骤影响（例如，如果您使用子代理作为工具，并且想要将消息历史传递给子代理）或工具的输入需要根据过去代理步骤的上下文进行验证时很有用。
在本指南中，我们将演示如何使用 LangGraph 的预构建 ToolNode 执行此操作。
先决条件
本指南针对 **LangChain 工具调用**，假设您熟悉以下内容：
您仍然可以使用您的提供程序 SDK 在 LangGraph 中使用工具调用，而不会丢失 LangGraph 的任何核心功能。以下示例使用的核心技术是将参数标注为“注入”，这意味着它将由您的程序注入，并且不应该被 LLM 看到或填充。请以下面的代码片段作为摘要：
from typing import Annotated
from langchain_core.runnables import RunnableConfig
from langchain_core.tools import InjectedToolArg
from langgraph.store.base import BaseStore
from langgraph.prebuilt import InjectedState, InjectedStore
# Can be sync or async; @tool decorator not required
async def my_tool(
# These arguments are populated by the LLM
some_arg: str,
another_arg: float,
# The config: RunnableConfig is always available in LangChain calls
# This is not exposed to the LLM
config: RunnableConfig,
# The following three are specific to the prebuilt ToolNode
# (and `create_react_agent` by extension). If you are invoking the
# tool on its own (in your own node), then you would need to provide these yourself.
store: Annotated[BaseStore, InjectedStore],
# This passes in the full state.
state: Annotated[State, InjectedState],
# You can also inject single fields from your state if you
messages: Annotated[list, InjectedState("messages")]
# The following is not compatible with create_react_agent or ToolNode
# You can also exclude other arguments from being shown to the model.
# These must be provided manually and are useful if you call the tools/functions in your own node
# some_other_arg=Annotated["MyPrivateClass", InjectedToolArg],
):
"""Call my_tool to have an impact on the real world.
Args:
some_arg: a very important argument
another_arg: another argument the LLM will provide
""" # The docstring becomes the description for your tool and is passed to the model
print(some_arg, another_arg, config, store, state, messages)
# Config, some_other_rag, store, and state are all "hidden" from
# LangChain models when passed to bind_tools or with_structured_output
return "... some response"
在 [ ]
已复制！
设置¶
首先，我们需要安装所需的软件包
在 [1]
已复制！
%%capture --no-stderr
%pip install --quiet -U langgraph langchain-openai
%%capture --no-stderr %pip install --quiet -U langgraph langchain-openai
接下来，我们需要为 OpenAI（我们将使用的聊天模型）设置 API 密钥。
在 [2]
已复制！
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")
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")
OPENAI_API_KEY: ········
将图状态传递给工具¶
首先，让我们看看如何让我们的工具访问图状态。我们需要定义我们的图状态
在 [3]
已复制！
from typing import List
# this is the state schema used by the prebuilt create_react_agent we'll be using below
from langgraph.prebuilt.chat_agent_executor import AgentState
from langchain_core.documents import Document
class State(AgentState):
docs: List[str]
from typing import List # 这是我们将要使用的预构建 create_react_agent 所使用的状态模式 from langgraph.prebuilt.chat_agent_executor import AgentState from langchain_core.documents import Document class State(AgentState): docs: List[str]
定义工具¶
我们希望我们的工具将图状态作为输入，但我们不希望模型在调用工具时尝试生成此输入。我们可以使用 InjectedState 标注将参数标记为必需的图状态（或图状态的某个字段）。这些参数将不会由模型生成。使用 ToolNode 时，图状态将自动传递到相关的工具和参数中。
在此示例中，我们将创建一个返回 Documents 的工具，然后创建一个实际引用证明断言的 Documents 的工具。
在 LangChain 中使用 Pydantic
此笔记本使用 Pydantic v2 BaseModel，这需要 langchain-core >= 0.3。使用 langchain-core < 0.3 将导致错误，因为混合了 Pydantic v1 和 v2 BaseModels。
在 [4]
已复制！
from typing import List, Tuple
from typing_extensions import Annotated
from langchain_core.messages import ToolMessage
from langchain_core.tools import tool
from langgraph.prebuilt import InjectedState
@tool
def get_context(question: str, state: Annotated[dict, InjectedState]):
"""Get relevant context for answering the question."""
return "\n\n".join(doc for doc in state["docs"])
from typing import List, Tuple from typing_extensions import Annotated from langchain_core.messages import ToolMessage from langchain_core.tools import tool from langgraph.prebuilt import InjectedState @tool def get_context(question: str, state: Annotated[dict, InjectedState]): """获取与回答问题相关的上下文。""" return "\n\n".join(doc for doc in state["docs"])
如果我们查看这些工具的输入模式，我们会看到 state 仍然列出
在 [5]
已复制！
get_context.get_input_schema().schema()
get_context.get_input_schema().schema()
Out[5]
{'description': 'Get relevant context for answering the question.',
'properties': {'question': {'title': 'Question', 'type': 'string'},
'state': {'title': 'State', 'type': 'object'}},
'required': ['question', 'state'],
'title': 'get_context',
'type': 'object'}
但是，如果我们查看工具调用模式（即传递给模型以进行工具调用的模式），state 已被移除
在 [6]
已复制！
get_context.tool_call_schema.schema()
get_context.tool_call_schema.schema()
Out[6]
{'description': 'Get relevant context for answering the question.',
'properties': {'question': {'title': 'Question', 'type': 'string'}},
'required': ['question'],
'title': 'get_context',
'type': 'object'}
定义图¶
在此示例中，我们将使用 预构建 ReAct 代理。我们首先需要定义我们的模型和一个工具调用节点 (ToolNode)
在 [7]
已复制！
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import ToolNode, create_react_agent
from langgraph.checkpoint.memory import MemorySaver
model = ChatOpenAI(model="gpt-4o", temperature=0)
tools = [get_context]
# ToolNode will automatically take care of injecting state into tools
tool_node = ToolNode(tools)
checkpointer = MemorySaver()
graph = create_react_agent(model, tools, state_schema=State, checkpointer=checkpointer)
from langchain_openai import ChatOpenAI from langgraph.prebuilt import ToolNode, create_react_agent from langgraph.checkpoint.memory import MemorySaver model = ChatOpenAI(model="gpt-4o", temperature=0) tools = [get_context] # ToolNode 将自动处理将状态注入工具 tool_node = ToolNode(tools) checkpointer = MemorySaver() graph = create_react_agent(model, tools, state_schema=State, checkpointer=checkpointer)
使用它！¶
在 [8]
已复制！
docs = [
"FooBar company just raised 1 Billion dollars!",
"FooBar company was founded in 2019",
]
inputs = {
"messages": [{"type": "user", "content": "what's the latest news about FooBar"}],
"docs": docs,
}
config = {"configurable": {"thread_id": "1"}}
for chunk in graph.stream(inputs, config, stream_mode="values"):
chunk["messages"][-1].pretty_print()
docs = [ "FooBar 公司刚刚筹集了 10 亿美元！", "FooBar 公司成立于 2019 年", ] inputs = { "messages": [{"type": "user", "content": "关于 FooBar 的最新消息是什么"}], "docs": docs, } config = {"configurable": {"thread_id": "1"}} for chunk in graph.stream(inputs, config, stream_mode="values"): chunk["messages"][-1].pretty_print()
================================ Human Message ================================= what's the latest news about FooBar ================================== Ai Message ================================== Tool Calls: get_context (call_UkqfR7z2cLJQjhatUpDeEa5H) Call ID: call_UkqfR7z2cLJQjhatUpDeEa5H Args: question: latest news about FooBar ================================= Tool Message ================================= Name: get_context FooBar company just raised 1 Billion dollars! FooBar company was founded in 2019 ================================== Ai Message ================================== The latest news about FooBar is that the company has just raised 1 billion dollars.
注意
Store API 和 InjectedStore 的支持是在 LangGraph v0.2.34 中添加的。InjectedStore 标注需要 langchain-core >= 0.3.8在 [9]
已复制！
from langgraph.store.memory import InMemoryStore
doc_store = InMemoryStore()
namespace = ("documents", "1") # user ID
doc_store.put(
namespace, "doc_0", {"doc": "FooBar company just raised 1 Billion dollars!"}
)
namespace = ("documents", "2") # user ID
doc_store.put(namespace, "doc_1", {"doc": "FooBar company was founded in 2019"})
from langgraph.store.memory import InMemoryStore doc_store = InMemoryStore() namespace = ("documents", "1") # 用户 ID doc_store.put( namespace, "doc_0", {"doc": "FooBar 公司刚刚筹集了 10 亿美元！"} ) namespace = ("documents", "2") # 用户 ID doc_store.put(namespace, "doc_1", {"doc": "FooBar 公司成立于 2019 年"})
定义工具¶
在 [10]
已复制！
from langgraph.store.base import BaseStore
from langchain_core.runnables import RunnableConfig
from langgraph.prebuilt import InjectedStore
@tool
def get_context(
question: str,
config: RunnableConfig,
store: Annotated[BaseStore, InjectedStore()],
) -> Tuple[str, List[Document]]:
"""Get relevant context for answering the question."""
user_id = config.get("configurable", {}).get("user_id")
docs = [item.value["doc"] for item in store.search(("documents", user_id))]
return "\n\n".join(doc for doc in docs)
from langgraph.store.base import BaseStore from langchain_core.runnables import RunnableConfig from langgraph.prebuilt import InjectedStore @tool def get_context( question: str, config: RunnableConfig, store: Annotated[BaseStore, InjectedStore()], ) -> Tuple[str, List[Document]]: """获取与回答问题相关的上下文。""" user_id = config.get("configurable", {}).get("user_id") docs = [item.value["doc"] for item in store.search(("documents", user_id))] return "\n\n".join(doc for doc in docs)
我们还可以验证工具调用模型是否会忽略 get_context 工具的 store 参数
在 [11]
已复制！
get_context.tool_call_schema.schema()
get_context.tool_call_schema.schema()
Out[11]
{'description': 'Get relevant context for answering the question.',
'properties': {'question': {'title': 'Question', 'type': 'string'}},
'required': ['question'],
'title': 'get_context',
'type': 'object'}
定义图¶
让我们更新我们的 ReAct 代理
在 [12]
已复制！
tools = [get_context]
# ToolNode will automatically take care of injecting Store into tools
tool_node = ToolNode(tools)
checkpointer = MemorySaver()
# NOTE: we need to pass our store to `create_react_agent` to make sure our graph is aware of it
graph = create_react_agent(model, tools, checkpointer=checkpointer, store=doc_store)
tools = [get_context] # ToolNode 将自动处理将 Store 注入工具 tool_node = ToolNode(tools) checkpointer = MemorySaver() # 注意：我们需要将我们的存储传递给 `create_react_agent` 以确保我们的图知道它 graph = create_react_agent(model, tools, checkpointer=checkpointer, store=doc_store)
使用它！¶
让我们尝试使用配置中的 "user_id" 运行我们的图。
在 [13]
已复制！
messages = [{"type": "user", "content": "what's the latest news about FooBar"}]
config = {"configurable": {"thread_id": "1", "user_id": "1"}}
for chunk in graph.stream({"messages": messages}, config, stream_mode="values"):
chunk["messages"][-1].pretty_print()
messages = [{"type": "user", "content": "关于 FooBar 的最新消息是什么"}] config = {"configurable": {"thread_id": "1", "user_id": "1"}} for chunk in graph.stream({"messages": messages}, config, stream_mode="values"): chunk["messages"][-1].pretty_print()
================================ Human Message ================================= what's the latest news about FooBar ================================== Ai Message ================================== Tool Calls: get_context (call_ocyHBpGgF3LPFOgRKURBfkGG) Call ID: call_ocyHBpGgF3LPFOgRKURBfkGG Args: question: latest news about FooBar ================================= Tool Message ================================= Name: get_context FooBar company just raised 1 Billion dollars! ================================== Ai Message ================================== The latest news about FooBar is that the company has just raised 1 billion dollars.
我们可以看到，该工具在存储中查找信息时只检索了用户“1”的正确文档。现在让我们尝试对另一个用户再次执行此操作
在 [14]
已复制！
messages = [{"type": "user", "content": "what's the latest news about FooBar"}]
config = {"configurable": {"thread_id": "2", "user_id": "2"}}
for chunk in graph.stream({"messages": messages}, config, stream_mode="values"):
chunk["messages"][-1].pretty_print()
messages = [{"type": "user", "content": "关于 FooBar 的最新消息是什么"}] config = {"configurable": {"thread_id": "2", "user_id": "2"}} for chunk in graph.stream({"messages": messages}, config, stream_mode="values"): chunk["messages"][-1].pretty_print()
================================ Human Message ================================= what's the latest news about FooBar ================================== Ai Message ================================== Tool Calls: get_context (call_zxO9KVlL8UxFQUMb8ETeHNvs) Call ID: call_zxO9KVlL8UxFQUMb8ETeHNvs Args: question: latest news about FooBar ================================= Tool Message ================================= Name: get_context FooBar company was founded in 2019 ================================== Ai Message ================================== FooBar company was founded in 2019. If you need more specific or recent news, please let me know!
我们可以看到，该工具这次拉取了一个不同的文档。