π§© Unlocking Smarter Retrieval: Query Decomposition in RAG
π Introduction
Retrieval-Augmented Generation (RAG) has transformed how Large Language Models (LLMs) access and use external knowledge. But a single query β especially if it's vague or multi-step β often isn't enough to retrieve the most relevant in...
rag-query-transformation-fan-out.hashnode.dev4 min read