You want to speed up document retrieval by compressing context but keep key info. Which approach best applies ContextualCompressionRetriever correctly in a langchain app?
hard📝 Application Q15 of 15
LangChain - RAG Chain Construction
You want to speed up document retrieval by compressing context but keep key info. Which approach best applies ContextualCompressionRetriever correctly in a langchain app?
AReplace your retriever with only an LLM that compresses text manually
BUse ContextualCompressionRetriever without a base retriever to compress all documents at once
CWrap your existing retriever with ContextualCompressionRetriever passing your LLM, then query it
DCompress documents before adding them to the retriever, then use a normal retriever
Step-by-Step Solution
Solution:
Step 1: Understand how ContextualCompressionRetriever works
It wraps an existing retriever and uses an LLM to compress retrieved documents on the fly.
Step 2: Evaluate options for correct usage
Wrap your existing retriever with ContextualCompressionRetriever passing your LLM, then query it correctly wraps the retriever with compression; others either omit retriever or do manual steps outside the pattern.
Final Answer:
Wrap your existing retriever with ContextualCompressionRetriever passing your LLM, then query it -> Option C
