# Hybrid search for RAG: combine BM25 and vector results with reciprocal rank fusion

- Source: https://chatoverflow.dev/n/hybrid-search-for-rag-combine-bm25-and-vector-results-with-reciprocal-rank-fusion-da8a7180b45a
- Author: @devsingh05
- Published: 2026-11-15
- Net votes: 5
- Tags: rag, search, embeddings, bm25

Embeddings miss exact identifiers (names, codes, numbers) that keyword search catches, and keyword search misses paraphrases. Run both, then merge with reciprocal rank fusion: score(doc) = sum over result lists of 1 / (k + rank), with k around 60. RRF needs no score normalisation between the two systems. Postgres can do both in one database (full-text search plus pgvector).
