如何将 Runnables 转换为 Tools

前置条件

本指南假设您熟悉以下概念：

我们将演示如何将 LangChain Runnable 转换为一个可供智能体、链或聊天模型使用的工具。

依赖项

注意:本指南需要 langchain-core >= 0.2.13。我们还将使用 OpenAI 进行嵌入，但任何 LangChain 嵌入都应足够。我们将使用一个简单的 LangGraph 代理用于演示目的。

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

LangChain 工具是智能体、链或聊天模型用于与外部世界交互的接口。有关工具调用、内置工具、自定义工具等内容的操操作指南，请参见此处。

LangChain 工具-- BaseTool 的实例 -- 是带有额外约束的可运行对象 (Runnables)，这些约束使它们能够被语言模型有效地调用：

它们的输入必须可序列化，具体为字符串和 Python dict 对象；
它们包含名称和描述，说明了应如何以及在何时使用它们；
它们可能包含一个详细的 args_schema 用于其参数。也就是说，虽然一个工具（作为 Runnable）可能接受单个 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可以通过as_tool方法转换为工具，该方法允许为参数指定名称、描述和其他架构信息。

基本用法

使用已类型的 dict 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:可运行Lambda

print(as_tool.description)

as_tool.args_schema.schema()

Explanation of when to use tool.

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

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

'6'

无需输入信息，参数类型可通过 arg_types 指定：

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的期望 args_schema 来完全指定模式：

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)

字符串输入也受支持:

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'

在智能体

下面我们将把 LangChain Runnables 作为工具整合到一个 agent 应用程序中。我们将通过以下内容进行演示：

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[openai]"

import getpass
import os

if not os.environ.get("OPENAI_API_KEY"):
  os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")

from langchain.chat_models import init_chat_model

llm = init_chat_model("gpt-4o-mini", model_provider="openai")

遵循 RAG 教程，让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:文档 |内存向量存储 |OpenAI 嵌入

我们接下来创建一个简单的预构建 LangGraph 代理，并向其提供该工具：

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})]}}
----

查看上述运行的 LangSmith 追踪。

更进一步，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 |聊天提示模板 |可运行传递器

请注意，我们链的输入架构包含必需的参数，因此它无需进一步说明即可转换为工具：

rag_chain.input_schema.schema()

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

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，该代理在其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})]}}
----

查看上述运行的 LangSmith 追踪。

依赖项​

基本用法​

在智能体​

依赖项

基本用法

在智能体