Category: Retrieval Performance
Priority: Medium
Phase: Phase 4 (Hybrid retrieval + reranking)
Problem
Postgres tsvector/ts_rank approximates BM25 but diverges from true term-frequency/length-normalized scoring, which can skew RRF fusion on keyword-heavy queries.
Solution
Document ts_rank as the explicit approximation and validate against the eval harness first; only adopt pg_bm25 (ParadeDB) if evals show a real gap.
Category: Retrieval Performance
Priority: Medium
Phase: Phase 4 (Hybrid retrieval + reranking)
Problem
Postgres
tsvector/ts_rankapproximates BM25 but diverges from true term-frequency/length-normalized scoring, which can skew RRF fusion on keyword-heavy queries.Solution
Document
ts_rankas the explicit approximation and validate against the eval harness first; only adoptpg_bm25(ParadeDB) if evals show a real gap.