Skip to main content
Open In ColabOpen on GitHub

如何使用 MultiQueryRetriever

基于距离的 向量数据库 检索会在高维空间中 嵌入（表示）查询，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而产生不同的结果，或者如果嵌入未能很好地捕捉数据的语义。提示工程/调优有时用于手动解决这些问题，但这可能很繁琐。

MultiQueryRetriever 通过使用 LLM 为给定的用户输入查询生成多个不同视角的查询，来自动化提示调优过程。对于每个查询，它会检索一组相关的文档，并合并所有查询的唯一并集，以获得更大范围的潜在相关文档集。通过生成对同一问题的多个视角，MultiQueryRetriever 可以缓解基于距离的检索的一些限制，并获得更丰富的检索结果集。

下面我们使用来自 RAG 教程 的 Lilian Weng 在 LLM 驱动的自主代理 博客文章来构建一个向量库：

# 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​

指定用于生成查询的 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，检索器 (retriever) 生成的底层查询会在 INFO 级别记录下来。

提供您自己的提示词​

在底层，MultiQueryRetriever 使用特定的提示词来生成查询。要自定义此提示词：

  1. 创建一个带有问题输入变量的PromptTemplate；
  2. 实现一个输出解析器，例如下面的解析器，将结果拆分为查询列表。

提示词和输出解析器一起必须支持查询列表的生成。

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