Renn F de82e06b3c feat(rag): hybrid retrieval (vector + full-text), retire HyDE ...

Recall no longer depends on a per-query HyDE LLM call — it comes from the index.
Each chunks_<type> table gets a generated `tsv` column + GIN index (migration
031; the engine CREATE TABLE matches so fresh tables get it too).
VectorStore.hybrid_search fuses pgvector cosine with Postgres full-text in one
query: score = min(1, cosine + 0.3 * normalized_ts_rank). A vector-only match
keeps its cosine score (so decisions/reviewer thresholds are unchanged), a
keyword match adds a bounded boost (the recall win), and a keyword-only match
stays low. Empty/garbage query text degrades to pure vector.

HyDE is removed from the search hot path: _compute_query_embedding now embeds
the query directly, and _generate_hyde_passage / rag_use_hyde /
IndexConfig.use_hyde are deleted. So a search is one local embed + one indexed
SQL — no LLM round-trip. The raw query text is threaded through the
embed-once + concurrent fan-out (search_with_embedding(embedding, query_text)).

Verified live via a real pgvector round-trip: vector ranking + keyword boost +
[0,1] scores + empty-query fallback all correct. Adds wiring + fan-out unit
tests; the fusion SQL itself is verified live (needs pgvector, not gated in CI).

2026-06-15 06:37:27 +02:00

..

versions

feat(rag): hybrid retrieval (vector + full-text), retire HyDE

2026-06-15 06:37:27 +02:00

env.py

Linting: Check

2025-12-12 02:45:47 +01:00

script.py.mako

Initial implementation

2025-12-10 02:49:54 +01:00