fix(llm): RAG — страницы в цитатах, метки scrub, выбор КР по заболеванию (#62) #63

Merged
Eleboba merged 1 commits from fix/62-rag-fixes into dev 2026-10-04 11:14:21 +03:00
1 Commits
Author SHA1 Message Date
ElebobaandClaude Opus 5.5 fe29ebd629 fix(llm): RAG citation pages, scrub placeholders, disease-aware document choice
CI / ruff · pytest (pull_request) Successful in 1m2s
- converter marks a paragraph glued across a page break with ⟦стр. N⟧; the chunker
  strips the marker and extends the chunk's page range (wrong-page citations 24 -> 3,
  the rest are scale-form table rows split by a page)
- [NAME]/[PHONE] placeholders from privacy.scrub() no longer count as unknown words
  (a scrubbed question used to fall below the coverage gate)
- a question naming one disease boosts its guideline in retrieval and passage choice
  ("ТМС при депрессии" was answered from the PTSD guideline); "антидепрессант" is not a cue

Refs #62

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-04 04:31:59 +03:00