Reference architectures
Advanced RAG with hybrid search and reranking
Dense and keyword retrieval combined, then a reranker that keeps only the best passages.
Basic RAG misses exact terms such as product codes or names. Hybrid search runs a vector query and a keyword query (BM25) side by side. A reranker scores the merged candidates against the question and passes only the top few to the answer model. A small model can rewrite the question first, and tracing records what was retrieved for each answer. This is the usual next step when a basic RAG setup returns the wrong passages.
