如何处理未生成查询的情况

有时，查询分析技术可能允许生成任意数量的查询 - 包括不生成查询！在这种情况下，我们的整体链需要检查查询分析的结果，然后决定是否调用检索器。

在本示例中，我们将使用模拟数据。

设置

安装依赖项

%pip install -qU langchain langchain-community langchain-openai langchain-chroma

Note: you may need to restart the kernel to use updated packages.

设置环境变量

在本示例中，我们将使用 OpenAI

import getpass
import os

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass.getpass()

# Optional, uncomment to trace runs with LangSmith. Sign up here: https://smith.langchain.com.
# os.environ["LANGSMITH_TRACING"] = "true"
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass()

创建索引

我们将基于虚假信息创建一个向量存储。

from langchain_chroma import Chroma
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter

texts = ["Harrison worked at Kensho"]
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
vectorstore = Chroma.from_texts(
    texts,
    embeddings,
)
retriever = vectorstore.as_retriever()

API 参考:OpenAIEmbeddings | RecursiveCharacterTextSplitter

查询分析

我们将使用函数调用来构建输出结构。但是，我们将配置 LLM，使其不需要调用表示搜索查询的函数（如果它决定不调用）。然后，我们还将使用提示来执行查询分析，明确说明何时应该以及何时不应该进行搜索。

from typing import Optional

from pydantic import BaseModel, Field


class Search(BaseModel):
    """Search over a database of job records."""

    query: str = Field(
        ...,
        description="Similarity search query applied to job record.",
    )

from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI

system = """You have the ability to issue search queries to get information to help answer user information.

You do not NEED to look things up. If you don't need to, then just respond normally."""
prompt = ChatPromptTemplate.from_messages(
    [
        ("system", system),
        ("human", "{question}"),
    ]
)
llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
structured_llm = llm.bind_tools([Search])
query_analyzer = {"question": RunnablePassthrough()} | prompt | structured_llm

API 参考:ChatPromptTemplate | RunnablePassthrough | ChatOpenAI

我们可以看到，通过调用此方法，我们得到一条消息，该消息有时（但并非总是）返回工具调用。

query_analyzer.invoke("where did Harrison Work")

AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_korLZrh08PTRL94f4L7rFqdj', 'function': {'arguments': '{"query":"Harrison"}', 'name': 'Search'}, 'type': 'function'}], 'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 95, 'total_tokens': 109}, 'model_name': 'gpt-4o-mini-2024-07-18', 'system_fingerprint': 'fp_483d39d857', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-ea94d376-37bf-4f80-abe6-e3b42b767ea0-0', tool_calls=[{'name': 'Search', 'args': {'query': 'Harrison'}, 'id': 'call_korLZrh08PTRL94f4L7rFqdj', 'type': 'tool_call'}], usage_metadata={'input_tokens': 95, 'output_tokens': 14, 'total_tokens': 109})

query_analyzer.invoke("hi!")

AIMessage(content='Hello! How can I assist you today?', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 10, 'prompt_tokens': 93, 'total_tokens': 103}, 'model_name': 'gpt-4o-mini-2024-07-18', 'system_fingerprint': 'fp_483d39d857', 'finish_reason': 'stop', 'logprobs': None}, id='run-ebdfc44a-455a-4ca6-be85-84559886b1e1-0', usage_metadata={'input_tokens': 93, 'output_tokens': 10, 'total_tokens': 103})

使用查询分析进行检索

那么，我们如何将其包含在链中呢？让我们看下面的示例。

from langchain_core.output_parsers.openai_tools import PydanticToolsParser
from langchain_core.runnables import chain

output_parser = PydanticToolsParser(tools=[Search])

API 参考:PydanticToolsParser | chain

@chain
def custom_chain(question):
    response = query_analyzer.invoke(question)
    if "tool_calls" in response.additional_kwargs:
        query = output_parser.invoke(response)
        docs = retriever.invoke(query[0].query)
        # Could add more logic - like another LLM call - here
        return docs
    else:
        return response

custom_chain.invoke("where did Harrison Work")

Number of requested results 4 is greater than number of elements in index 1, updating n_results = 1

[Document(page_content='Harrison worked at Kensho')]

custom_chain.invoke("hi!")

AIMessage(content='Hello! How can I assist you today?', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 10, 'prompt_tokens': 93, 'total_tokens': 103}, 'model_name': 'gpt-4o-mini-2024-07-18', 'system_fingerprint': 'fp_483d39d857', 'finish_reason': 'stop', 'logprobs': None}, id='run-e87f058d-30c0-4075-8a89-a01b982d557e-0', usage_metadata={'input_tokens': 93, 'output_tokens': 10, 'total_tokens': 103})