Commit Graph

2 Commits

Author SHA1 Message Date
Tarik Moussa
45c3b16dd7 docs: clarify sparse-not-wired and cite-boost tie-breaker (audit C-14, U-2)
- C-14: embed.py header now states that only the dense path is wired (search
  'hybrid' is dense + Postgres FTS); encode_sparse/encode are reserved for a
  future sparse-retrieval layer, not yet consumed.
- U-2: --cite-boost help clarifies it re-ranks within the top results (a
  tie-breaker), not a hard re-ranking — matching the small alpha effect.

Accepted (documented heuristics, no change): R-3 conflict detection is a
keyword-only signal labelled as such; R-12 classify_section is mostly 'body'
because chunks are word-windows that rarely start at a section header.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-15 21:47:40 +02:00
Tarik Moussa
1698f7dcad feat(embed): BGE-M3 dense+sparse via FlagEmbedding (ADR-0002)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-04 23:48:06 +02:00