Skip to main content
Open In ColabOpen on GitHub

如何使用 MultiQueryRetriever

基于距离的向量数据库检索将查询嵌入（表示）到高维空间，并根据距离度量查找相似的嵌入文档。但是，检索结果可能会因查询措辞的细微变化或嵌入未能很好地捕捉数据语义而产生差异。有时会通过提示工程/调优来手动解决这些问题，但这可能很繁琐。

MultiQueryRetriever 通过利用大语言模型（LLM）从不同角度为给定的用户输入查询生成多个查询，从而自动化提示调优过程。对于每个查询，它会检索一组相关文档，并取所有查询的唯一并集，以获得一个更大的潜在相关文档集合。通过对同一问题生成多个视角，MultiQueryRetriever 可以缓解基于距离的检索的一些局限性，并获得更丰富的结果集。

让我们使用来自 Lilian Weng 的《LLM 驱动的自主智能体》博客文章 和 RAG 教程 的内容来构建一个向量存储：

# Build a sample vectorDB
from langchain_chroma import Chroma
from langchain_community.document_loaders import WebBaseLoader
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter

# Load blog post
loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
data = loader.load()

# Split
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
splits = text_splitter.split_documents(data)

# VectorDB
embedding = OpenAIEmbeddings()
vectordb = Chroma.from_documents(documents=splits, embedding=embedding)
USER_AGENT environment variable not set, consider setting it to identify your requests.

简单用法​

指定要用于查询生成的 LLM，检索器将处理其余部分。

from langchain.retrievers.multi_query import MultiQueryRetriever
from langchain_openai import ChatOpenAI

question = "What are the approaches to Task Decomposition?"
llm = ChatOpenAI(temperature=0)
retriever_from_llm = MultiQueryRetriever.from_llm(
    retriever=vectordb.as_retriever(), llm=llm
)
# Set logging for the queries
import logging

logging.basicConfig()
logging.getLogger("langchain.retrievers.multi_query").setLevel(logging.INFO)
unique_docs = retriever_from_llm.invoke(question)
len(unique_docs)
INFO:langchain.retrievers.multi_query:Generated queries: ['1. How can Task Decomposition be achieved through different methods?', '2. What strategies are commonly used for Task Decomposition?', '3. What are the various ways to break down tasks in Task Decomposition?']
5

请注意，由 检索器 生成的底层查询会记录在 INFO 级别。

提供您自己的提示​

在底层，MultiQueryRetriever使用特定的提示词（prompt）生成查询。若要自定义此提示词：

  1. 使用输入变量创建一个用于问题的 PromptTemplate；
  2. 实现一个像下面的输出解析器，将结果拆分为查询列表。

提示词和输出解析器必须共同支持生成查询列表。

from typing import List

from langchain_core.output_parsers import BaseOutputParser
from langchain_core.prompts import PromptTemplate
from pydantic import BaseModel, Field


# Output parser will split the LLM result into a list of queries
class LineListOutputParser(BaseOutputParser[List[str]]):
    """Output parser for a list of lines."""

    def parse(self, text: str) -> List[str]:
        lines = text.strip().split("\n")
        return list(filter(None, lines))  # Remove empty lines


output_parser = LineListOutputParser()

QUERY_PROMPT = PromptTemplate(
    input_variables=["question"],
    template="""You are an AI language model assistant. Your task is to generate five 
    different versions of the given user question to retrieve relevant documents from a vector 
    database. By generating multiple perspectives on the user question, your goal is to help
    the user overcome some of the limitations of the distance-based similarity search. 
    Provide these alternative questions separated by newlines.
    Original question: {question}""",
)
llm = ChatOpenAI(temperature=0)

# Chain
llm_chain = QUERY_PROMPT | llm | output_parser

# Other inputs
question = "What are the approaches to Task Decomposition?"
# Run
retriever = MultiQueryRetriever(
    retriever=vectordb.as_retriever(), llm_chain=llm_chain, parser_key="lines"
)  # "lines" is the key (attribute name) of the parsed output

# Results
unique_docs = retriever.invoke("What does the course say about regression?")
len(unique_docs)
INFO:langchain.retrievers.multi_query:Generated queries: ['1. Can you provide insights on regression from the course material?', '2. How is regression discussed in the course content?', '3. What information does the course offer regarding regression?', '4. In what way is regression covered in the course?', "5. What are the course's teachings on regression?"]
9