ElebobaandClaude Opus 5.5 fe29ebd629 fix(llm): RAG citation pages, scrub placeholders, disease-aware document choice ...

- 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

..

figures

feat(llm): RAG knowledge base over clinical guidelines with cited extractive answers

2026-10-04 04:11:06 +03:00

manual

feat(llm): RAG knowledge base over clinical guidelines with cited extractive answers

2026-10-04 04:11:06 +03:00

check_txt.py

feat(llm): RAG knowledge base over clinical guidelines with cited extractive answers

2026-10-04 04:11:06 +03:00

kr_depression.pdf

feat(llm): RAG knowledge base over clinical guidelines with cited extractive answers

2026-10-04 04:11:06 +03:00

kr_ptsd.pdf

feat(llm): RAG knowledge base over clinical guidelines with cited extractive answers

2026-10-04 04:11:06 +03:00

meds_module_spec.pdf

feat(llm): RAG knowledge base over clinical guidelines with cited extractive answers

2026-10-04 04:11:06 +03:00

pdf_to_txt.py

fix(llm): RAG citation pages, scrub placeholders, disease-aware document choice

2026-10-04 04:31:59 +03:00