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

- docs/source/rag: PDF sources (KR PTSD 2023, KR depression 2024, meds module spec),
  pdf->txt converter (tables as markdown, page markers, hand-transcribed figures),
  word-level check against pdftotext; fixes HAM-D/MADRS fake headers and split rows
- config/rag: corpus txt + sources.yaml (documents, audiences, retrieval params, synonyms)
- app/llm/rag: Snowball stemmer, section-aware chunker with page citations,
  BM25 + synonym expansion + densest-passage reranking, extractive answer()
  with coverage gate, patient dose/prescribing filter, optional LLM rephrasing
  rejected when it adds content; CLI python -m app.llm.rag
- tests: gold retrieval set (hit@3 >= 15/18), off-topic, safety, faithfulness
- ADR-011

Refs #60

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

app/llm/rag/__init__.py

@@ -0,0 +1,24 @@
+"""Knowledge base (RAG, #60): clinical guidelines -> citable chunks -> BM25 retrieval -> grounded answers.
+
+    from app.llm.rag import answer, retrieve
+    hits = retrieve("синдром отмены антидепрессантов", audience="doctor")
+    reply = await answer(scrub(text), audience="patient")   # None -> rag.fallback_text()
+
+Corpus and parameters: `config/rag/sources.yaml`; PDF sources and the converter: `docs/source/rag/`.
+"""
+
+from app.llm.rag.corpus import Chunk, load_chunks
+from app.llm.rag.index import Hit, get_index, retrieve
+from app.llm.rag.qa import Citation, RagAnswer, answer, fallback_text
+
+__all__ = [
+    "Chunk",
+    "Citation",
+    "Hit",
+    "RagAnswer",
+    "answer",
+    "fallback_text",
+    "get_index",
+    "load_chunks",
+    "retrieve",
+]