Skip to main content

How to use the MultiQueryRetriever

Distance-based vector database retrieval embeds (represents) queries in high-dimensional space and finds similar embedded documents based on a distance metric. But, retrieval may produce different results with subtle changes in query wording, or if the embeddings do not capture the semantics of the data well. Prompt engineering / tuning is sometimes done to manually address these problems, but can be tedious.

The MultiQueryRetriever automates the process of prompt tuning by using an LLM to generate multiple queries from different perspectives for a given user input query. For each query, it retrieves a set of relevant documents and takes the unique union across all queries to get a larger set of potentially relevant documents. By generating multiple perspectives on the same question, the MultiQueryRetriever can mitigate some of the limitations of the distance-based retrieval and get a richer set of results.

Let's build a vectorstore using the LLM Powered Autonomous Agents blog post by Lilian Weng from the RAG tutorial:

# 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("")
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)

Simple usage​

Specify the LLM to use for query generation, and the retriever will do the rest.

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

unique_docs = retriever_from_llm.invoke(question)
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 techniques for breaking down tasks in Task Decomposition?']

Note that the underlying queries generated by the retriever are logged at the INFO level.

Supplying your own prompt​

Under the hood, MultiQueryRetriever generates queries using a specific prompt. To customize this prompt:

  1. Make a PromptTemplate with an input variable for the question;
  2. Implement an output parser like the one below to split the result into a list of queries.

The prompt and output parser together must support the generation of a list of queries.

from typing import List

from langchain_core.output_parsers import BaseOutputParser
from langchain_core.prompts import PromptTemplate
from langchain_core.pydantic_v1 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 lines

output_parser = LineListOutputParser()

QUERY_PROMPT = PromptTemplate(
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?")
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 about regression?', '4. In what way is regression covered in the course?', '5. What are the teachings of the course regarding regression?']

Was this page helpful?

You can leave detailed feedback on GitHub.