Hybrid Search: Using BM25 + Vector Search to Cover Each Other's Blind Spots
Vector search handles semantics; BM25 handles keywords. Combining them with RRF is what lets you handle both fuzzy queries and exact terms at the same time.
Vector search handles semantics; BM25 handles keywords. Combining them with RRF is what lets you handle both fuzzy queries and exact terms at the same time.
A single vector search on a complex query often misses relevant documents. Let the LLM rewrite the query into 3-5 sub-queries, run them in parallel, and recall improves significantly.
BM25, vector search, HyDE, and Multi-Query each produce separate result sets -- how do you merge them sensibly? RRF uses ranks instead of scores, sidestepping the fundamental problem that scores from different systems are incomparable.