Benjamin Admin ff21bc258a docs: session handover — D2-D5 complete, quality report, NIST plan ...

Major session achievements:
- Structural metadata end-to-end (D2-D4)
- 430 docs re-ingested with new chunking
- HTML stripping + charset detection (0% → 97.6%)
- 20 EU regulations from EUR-Lex HTML (DSGVO: 0% → 92%)
- Quality report script (500 controls: 13% fully correct)
- Frontend requirements.map fix

Open: NIST/ENISA text normalization, citation backfill,
D5 script safety (upload-before-delete), BEG IV ingestion.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-05-02 22:22:55 +02:00

..

import_backup.py

…

ingest_bag_urteile.py

…

migrate_jsonb.py

…

quality_report.py

docs: session handover — D2-D5 complete, quality report, NIST plan

2026-05-02 22:22:55 +02:00

reingest_d5_config.py

fix(rag): strip HTML tags before chunking + D5 re-ingestion scripts

2026-05-02 08:18:25 +02:00

reingest_d5.py

feat(embedding): add pdfplumber backend for multi-column PDF extraction

2026-05-02 15:42:25 +02:00

replace_eu_pdfs_with_html.py

feat(embedding): add NIST/ENISA/standard section numbering to chunker

2026-05-02 19:24:10 +02:00

test_d4_integration.py

feat(pipeline): structural metadata end-to-end (Blocks D2-D4)

2026-05-01 20:34:00 +02:00

test_qwen_backfill.py

perf(pipeline): switch to v3 prompt for generation, v4 fields via Haiku backfill

2026-04-27 00:14:47 +02:00