如何将 Runnables 转换为 Tools

先决条件

本指南假定您熟悉以下概念：

在这里，我们将演示如何转换 LangChainRunnable转换为可供代理、连锁店或聊天模型使用的工具。

依赖

注意：本指南需要langchain-core>= 0.2.13 的。我们还将使用 OpenAI 进行嵌入，但任何 LangChain 嵌入都应该足够了。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。请参阅此处，了解涵盖工具调用、内置工具、自定义工具等的操作指南。

LangChain 工具（BaseTool 的实例）是具有附加约束的 Runnable，使语言模型能够有效地调用它们：

它们的输入被限制为可序列化的，特别是字符串和 Pythondict对象;
它们包含名称和描述，指示应如何以及何时使用它们;
它们可能包含其参数的详细args_schema。也就是说，虽然工具（作为Runnable）可能会接受单个dictinput，填充 dict 所需的特定键和类型信息应在args_schema.

接受 string 或dict可以使用 as_tool 方法将 input 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 typeddict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.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'

无需键入信息，可以通过arg_types:

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所需args_schema来完全指定架构：

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)

还支持字符串输入：

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 LangChain Runnables 作为工具合并到代理应用程序中。我们将通过以下方式进行演示：

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：

选择聊天模式：

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")

按照 RAG 教程，让我们首先构造一个 retriever：

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 | InMemoryVectorStore （内存中矢量存储） | OpenAI 嵌入

接下来，我们创建一个简单的预构建 LangGraph 代理，并为其提供该工具：

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})]}}
----

有关上述运行，请参阅 LangSmith 跟踪。

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 “样式”。

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 模板 | RunnablePassthrough

请注意，我们链的 input 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.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，代理在其tool_calls:

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})]}}
----

有关上述运行，请参阅 LangSmith 跟踪。