Add Docling corpus pipeline, retrieval evaluation and hybrid search with reranking

- prepare_corpus.py: split double-page scans (split_spreads.py), re-OCR with
  OCRmyPDF/Tesseract only where the existing text layer is worse, Docling
  layout extraction with heading hierarchy, QA report per PDF
- docling_loader.py: cleanup (margin noise, split paragraphs, footnote marks,
  OCR comma/period repair), page mapping back to the original PDF, chunk
  headers with author, title and section
- local_rag.py: bge-m3 embeddings, configurable chunking and loader, index
  settings check (index_info.json), hybrid/union BM25 search with Reciprocal
  Rank Fusion and bge-reranker-v2-m3 cross-encoder; query instruction text
  removed after it lowered recall
- eval_retrieval.py: CLI options, same retrieval path as the chat, tolerant
  file name matching; goldsets and evaluation reports for the Kafka corpus
- grobid_test.py, grobid_qa.py, extract_docling.py, compare_extractors.py:
  extractor tests and quality checks
- .gitignore: corpus PDFs, vector stores and extractor output stay local
- server.py: uses ./vectorstore_docling_hdr

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

.gitignore

@@ -8,12 +8,29 @@ venv/
 env/
 ENV/
 
+# Korpus-PDFs (urheberrechtlich geschützt, nicht ins Repository)
+data/
+data_test/
+
 # Vector store
 vectorstore/
 
 # Uploads
 uploads/
 
+# GROBID-Testausgabe
+grobid_out/
+
+# Extraktor-Vergleich (Docling u. a.)
+extract_out/
+
+# Tesseract-Sprachmodelle (heruntergeladen)
+tessdata/
+
+# Aufbereitetes Korpus (prepare_corpus.py) und Vergleichsindizes
+corpus_processed/
+vectorstore_*/
+
 # IDE
 .vscode/
 .idea/
@@ -23,3 +40,12 @@ uploads/
 # OS
 .DS_Store
 Thumbs.db
+
+# Secrets / API keys (never commit these)
+.env
+.env.*
+*.key
+*.pem
+*key*.txt
+*key*.docx
+*key*.zip