Reciprocal Rank Fusion Hybrid Search in PostgreSQL with pg_search

ParadeDB·high signal

ParadeDB's pg_search extension brings BM25 directly into PostgreSQL alongside pgvector, enabling hybrid search without an Elasticsearch dependency. Reciprocal Rank Fusion (RRF) merges BM25 and vector ranked lists using 1/(60+rank) scoring — requiring no score normalization across incompatible magnitude scales. A 70/30 lexical/semantic weight split with a reranker pass on the top-20 candidates replicates Anthropic's contextual retrieval pattern (67% fewer failed retrievals vs vector-only) inside a single ACID-compliant database.