Movatterモバイル変換


[0]ホーム

URL:


Skip to main content
OurBuilding Ambient Agents with LangGraph course is now available on LangChain Academy!
Open In ColabOpen on GitHub

How to handle multiple retrievers when doing query analysis

Sometimes, a query analysis technique may allow for selection of whichretriever to use. To use this, you will need to add some logic to select the retriever to do. We will show a simple example (using mock data) of how to do that.

Setup

Install dependencies

%pip install-qU langchain langchain-community langchain-openai langchain-chroma
Note: you may need to restart the kernel to use updated packages.

Set environment variables

We'll use OpenAI in this example:

import getpass
import os

if"OPENAI_API_KEY"notin 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()

Create Index

We will create a vectorstore over fake information.

from langchain_chromaimport Chroma
from langchain_openaiimport OpenAIEmbeddings
from langchain_text_splittersimport RecursiveCharacterTextSplitter

texts=["Harrison worked at Kensho"]
embeddings= OpenAIEmbeddings(model="text-embedding-3-small")
vectorstore= Chroma.from_texts(texts, embeddings, collection_name="harrison")
retriever_harrison= vectorstore.as_retriever(search_kwargs={"k":1})

texts=["Ankush worked at Facebook"]
embeddings= OpenAIEmbeddings(model="text-embedding-3-small")
vectorstore= Chroma.from_texts(texts, embeddings, collection_name="ankush")
retriever_ankush= vectorstore.as_retriever(search_kwargs={"k":1})

Query analysis

We will use function calling to structure the output. We will let it return multiple queries.

from typingimport List, Optional

from pydanticimport BaseModel, Field


classSearch(BaseModel):
"""Search for information about a person."""

query:str= Field(
...,
description="Query to look up",
)
person:str= Field(
...,
description="Person to look things up for. Should be `HARRISON` or `ANKUSH`.",
)
from langchain_core.output_parsers.openai_toolsimport PydanticToolsParser
from langchain_core.promptsimport ChatPromptTemplate
from langchain_core.runnablesimport RunnablePassthrough
from langchain_openaiimport ChatOpenAI

output_parser= PydanticToolsParser(tools=[Search])

system="""You have the ability to issue search queries to get information to help answer user information."""
prompt= ChatPromptTemplate.from_messages(
[
("system", system),
("human","{question}"),
]
)
llm= ChatOpenAI(model="gpt-4o-mini", temperature=0)
structured_llm= llm.with_structured_output(Search)
query_analyzer={"question": RunnablePassthrough()}| prompt| structured_llm

We can see that this allows for routing between retrievers

query_analyzer.invoke("where did Harrison Work")
Search(query='work history', person='HARRISON')
query_analyzer.invoke("where did ankush Work")
Search(query='work history', person='ANKUSH')

Retrieval with query analysis

So how would we include this in a chain? We just need some simple logic to select the retriever and pass in the search query

from langchain_core.runnablesimport chain
API Reference:chain
retrievers={
"HARRISON": retriever_harrison,
"ANKUSH": retriever_ankush,
}
@chain
defcustom_chain(question):
response= query_analyzer.invoke(question)
retriever= retrievers[response.person]
return retriever.invoke(response.query)
custom_chain.invoke("where did Harrison Work")
[Document(page_content='Harrison worked at Kensho')]
custom_chain.invoke("where did ankush Work")
[Document(page_content='Ankush worked at Facebook')]

[8]ページ先頭

©2009-2025 Movatter.jp