如何将可运行对象转换为工具

先决条件

本指南假定您熟悉以下概念

在这里，我们将演示如何将 LangChain Runnable 转换为可由代理 (agents)、链 (chains) 或聊天模型 (chat models) 使用的工具 (tool)。

依赖项

注意：本指南要求 langchain-core >= 0.2.13。我们还将使用 OpenAI 进行嵌入，但任何 LangChain 嵌入都应适用。我们将使用一个简单的 LangGraph 代理进行演示。

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

LangChain 工具是代理、链或聊天模型可用于与世界交互的接口。有关工具调用、内置工具、自定义工具及更多信息的操作指南，请参阅此处。

LangChain 工具—— BaseTool 的实例—— 是 Runnables，具有额外的约束，使其能够被语言模型有效调用。

它们的输入被限制为可序列化的，特别是字符串和 Python dict 对象；
它们包含名称和描述，指示应如何以及何时使用它们；
它们可能包含为其参数提供的详细 args_schema。也就是说，虽然一个工具（作为 Runnable）可能接受一个单个的 dict 输入，但填充字典所需的特定键和类型信息应在 args_schema 中指定。

接受字符串或 dict 输入的 Runnables 可以使用 as_tool 方法转换为工具，该方法允许指定名称、描述和额外的参数 schema 信息。

基本用法

带类型字典输入

from typing import List

from langchain_core.runnables import RunnableLambda
from typing_extensions import TypedDict


class Args(TypedDict):
    a: int
    b: List[int]


def f(x: Args) -> str:
    return str(x["a"] * max(x["b"]))


runnable = RunnableLambda(f)
as_tool = runnable.as_tool(
    name="My tool",
    description="Explanation of when to use tool.",
)

API 参考:RunnableLambda

print(as_tool.description)

as_tool.args_schema.model_json_schema()

Explanation of when to use tool.

{'properties': {'a': {'title': 'A', 'type': 'integer'},
  'b': {'items': {'type': 'integer'}, 'title': 'B', 'type': 'array'}},
 'required': ['a', 'b'],
 'title': 'My tool',
 'type': 'object'}

as_tool.invoke({"a": 3, "b": [1, 2]})

'6'

在没有类型信息的情况下，可以通过 arg_types 指定参数类型

from typing import Any, Dict


def g(x: Dict[str, Any]) -> str:
    return str(x["a"] * max(x["b"]))


runnable = RunnableLambda(g)
as_tool = runnable.as_tool(
    name="My tool",
    description="Explanation of when to use tool.",
    arg_types={"a": int, "b": List[int]},
)

或者，可以通过直接传递工具所需的 args_schema 来完全指定 schema

from pydantic import BaseModel, Field

class GSchema(BaseModel):
    """Apply a function to an integer and list of integers."""

    a: int = Field(..., description="Integer")
    b: List[int] = Field(..., description="List of ints")

runnable = RunnableLambda(g)
as_tool = runnable.as_tool(GSchema)

也支持字符串输入

def f(x: str) -> str:
    return x + "a"


def g(x: str) -> str:
    return x + "z"


runnable = RunnableLambda(f) | g
as_tool = runnable.as_tool()

as_tool.invoke("b")

'baz'

在代理中

下面我们将把 LangChain Runnables 作为工具整合到代理应用程序中。我们将演示以下内容：

一个文档检索器；
一个简单的 RAG 链，允许代理将相关查询委托给它。

我们首先实例化一个支持工具调用的聊天模型

选择聊天模型

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")

按照 RAG 教程，我们首先构建一个检索器

from langchain_core.documents import Document
from langchain_core.vectorstores import InMemoryVectorStore
from langchain_openai import OpenAIEmbeddings

documents = [
    Document(
        page_content="Dogs are great companions, known for their loyalty and friendliness.",
    ),
    Document(
        page_content="Cats are independent pets that often enjoy their own space.",
    ),
]

vectorstore = InMemoryVectorStore.from_documents(
    documents, embedding=OpenAIEmbeddings()
)

retriever = vectorstore.as_retriever(
    search_type="similarity",
    search_kwargs={"k": 1},
)

API 参考：Document | InMemoryVectorStore | OpenAIEmbeddings

接下来，我们使用一个简单的预构建 LangGraph 代理并为其提供工具

from langgraph.prebuilt import create_react_agent

tools = [
    retriever.as_tool(
        name="pet_info_retriever",
        description="Get information about pets.",
    )
]
agent = create_react_agent(llm, tools)

API 参考：create_react_agent

for chunk in agent.stream({"messages": [("human", "What are dogs known for?")]}):
    print(chunk)
    print("----")

{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_W8cnfOjwqEn4cFcg19LN9mYD', 'function': {'arguments': '{"__arg1":"dogs"}', 'name': 'pet_info_retriever'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 19, 'prompt_tokens': 60, 'total_tokens': 79}, 'model_name': 'gpt-4o-mini', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-d7f81de9-1fb7-4caf-81ed-16dcdb0b2ab4-0', tool_calls=[{'name': 'pet_info_retriever', 'args': {'__arg1': 'dogs'}, 'id': 'call_W8cnfOjwqEn4cFcg19LN9mYD'}], usage_metadata={'input_tokens': 60, 'output_tokens': 19, 'total_tokens': 79})]}}
----
{'tools': {'messages': [ToolMessage(content="[Document(id='86f835fe-4bbe-4ec6-aeb4-489a8b541707', page_content='Dogs are great companions, known for their loyalty and friendliness.')]", name='pet_info_retriever', tool_call_id='call_W8cnfOjwqEn4cFcg19LN9mYD')]}}
----
{'agent': {'messages': [AIMessage(content='Dogs are known for being great companions, known for their loyalty and friendliness.', response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 134, 'total_tokens': 152}, 'model_name': 'gpt-4o-mini', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-9ca5847a-a5eb-44c0-a774-84cc2c5bbc5b-0', usage_metadata={'input_tokens': 134, 'output_tokens': 18, 'total_tokens': 152})]}}
----

请参阅上述运行的LangSmith 追踪。

进一步地，我们可以创建一个简单的 RAG 链，它接受一个额外的参数——这里是答案的“风格”。

from operator import itemgetter

from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough

system_prompt = """
You are an assistant for question-answering tasks.
Use the below context to answer the question. If
you don't know the answer, say you don't know.
Use three sentences maximum and keep the answer
concise.

Answer in the style of {answer_style}.

Question: {question}

Context: {context}
"""

prompt = ChatPromptTemplate.from_messages([("system", system_prompt)])

rag_chain = (
    {
        "context": itemgetter("question") | retriever,
        "question": itemgetter("question"),
        "answer_style": itemgetter("answer_style"),
    }
    | prompt
    | llm
    | StrOutputParser()
)

API 参考：StrOutputParser | ChatPromptTemplate | RunnablePassthrough

请注意，我们链的输入 schema 包含所需的参数，因此它无需进一步指定即可转换为工具

rag_chain.input_schema.model_json_schema()

{'properties': {'question': {'title': 'Question'},
  'answer_style': {'title': 'Answer Style'}},
 'required': ['question', 'answer_style'],
 'title': 'RunnableParallel<context,question,answer_style>Input',
 'type': 'object'}

rag_tool = rag_chain.as_tool(
    name="pet_expert",
    description="Get information about pets.",
)

下面我们再次调用代理。请注意，代理在其 tool_calls 中填充了所需的参数

agent = create_react_agent(llm, [rag_tool])

for chunk in agent.stream(
    {"messages": [("human", "What would a pirate say dogs are known for?")]}
):
    print(chunk)
    print("----")

{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_17iLPWvOD23zqwd1QVQ00Y63', 'function': {'arguments': '{"question":"What are dogs known for according to pirates?","answer_style":"quote"}', 'name': 'pet_expert'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 28, 'prompt_tokens': 59, 'total_tokens': 87}, 'model_name': 'gpt-4o-mini', 'system_fingerprint': None, 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-7fef44f3-7bba-4e63-8c51-2ad9c5e65e2e-0', tool_calls=[{'name': 'pet_expert', 'args': {'question': 'What are dogs known for according to pirates?', 'answer_style': 'quote'}, 'id': 'call_17iLPWvOD23zqwd1QVQ00Y63'}], usage_metadata={'input_tokens': 59, 'output_tokens': 28, 'total_tokens': 87})]}}
----
{'tools': {'messages': [ToolMessage(content='"Dogs are known for their loyalty and friendliness, making them great companions for pirates on long sea voyages."', name='pet_expert', tool_call_id='call_17iLPWvOD23zqwd1QVQ00Y63')]}}
----
{'agent': {'messages': [AIMessage(content='According to pirates, dogs are known for their loyalty and friendliness, making them great companions for pirates on long sea voyages.', response_metadata={'token_usage': {'completion_tokens': 27, 'prompt_tokens': 119, 'total_tokens': 146}, 'model_name': 'gpt-4o-mini', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-5a30edc3-7be0-4743-b980-ca2f8cad9b8d-0', usage_metadata={'input_tokens': 119, 'output_tokens': 27, 'total_tokens': 146})]}}
----

请参阅上述运行的LangSmith 追踪。

依赖项​

基本用法​

在代理中​

依赖项

基本用法

在代理中