Benjamin Admin c88653b221 fix(rag): Dedup check, BGB split, GewO timeout, arithmetic fix ...

- Add Qdrant dedup check in upload_file() — skip if regulation_id already exists
- Split BGB (2.7MB) into 5 targeted parts via XML extraction:
  AGB §§305-310, Fernabsatz §§312-312k, Kaufrecht §§433-480,
  Widerruf §§355-361, Digitale Produkte §§327-327u
- Lower large-file threshold 512KB→384KB (fixes GewO 432KB timeout)
- Fix arithmetic syntax error when collection_count returns "?"
- Replace EGBGB PDF (was empty) with XML extraction
- Add unzip to Alpine container for XML archives

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-12 09:39:09 +01:00

..

apply_block_markers_022.py

fix: Migration 022 — Regex an echte Template-Struktur angepasst (bold-headings)

2026-03-04 13:42:30 +01:00

apply_consent_history_migration.sh

feat: Package 4 Nachbesserungen — History-Tracking, Pagination, Frontend-Fixes

2026-03-03 11:54:25 +01:00

apply_consent_templates_migration.sh

feat: Betrieb-Module → 100% — Echte CRUD-Flows, kein Mock-Data

2026-03-03 12:48:43 +01:00

apply_einwilligungen_migration.sh

feat: Package 4 Rechtliche Texte — DB-Persistenz fuer Legal Documents, Einwilligungen und Cookie Banner

2026-03-03 08:25:13 +01:00

apply_escalations_migration.sh

feat: Betrieb-Module → 100% — Echte CRUD-Flows, kein Mock-Data

2026-03-03 12:48:43 +01:00

apply_legal_docs_migration.sh

feat: Package 4 Rechtliche Texte — DB-Persistenz fuer Legal Documents, Einwilligungen und Cookie Banner

2026-03-03 08:25:13 +01:00

apply_legal_templates_020_migration.sh

feat: Dokumentengenerator — Vollständige Vorlage-Bibliothek + Frontend-Redesign

2026-03-04 10:47:38 +01:00

apply_legal_templates_attribution_migration.sh

feat: Legal Templates — Attribution-Tracking + 6 neue Templates (DE/EN)

2026-03-04 09:00:25 +01:00

apply_legal_templates_migration.sh

feat: Legal Templates Service — eigene Vorlagen für Dokumentengenerator

2026-03-03 23:12:07 +01:00

apply_notfallplan_migration.sh

feat: Betrieb-Module → 100% — Echte CRUD-Flows, kein Mock-Data

2026-03-03 12:48:43 +01:00

apply_templates_023.py

fix: apply_templates_023.py — placeholders als JSONB + version/status Felder

2026-03-04 14:45:50 +01:00

apply_training_migrations.sh

feat: 6 Dokumentations-Module auf 100% — VVT Backend, Filter, PDF-Export

2026-03-02 17:14:58 +01:00

apply_vvt_migration.sh

feat: 6 Dokumentations-Module auf 100% — VVT Backend, Filter, PDF-Export

2026-03-02 17:14:58 +01:00

edpb-crawler.py

fix(crawler): korrigierte URLs fuer DSK-OH, BayLDA-TOM (404-Fixes)

2026-03-05 12:12:25 +01:00

ingest-ce-corpus.sh

feat(iace): Hazard-Library v2, Controls-Library, SEPA Avoidance, CE RAG-Ingest

2026-03-05 17:13:01 +01:00

ingest-dsfa-bundesland.sh

feat: DSFA vollständiges DB-Schema + PDF-Ingest + Tests

2026-03-05 10:03:09 +01:00

ingest-industry-compliance.sh

fix: add User-Agent header to PDF downloads

2026-02-28 09:33:06 +01:00

ingest-legal-corpus.sh

fix(rag): Dedup check, BGB split, GewO timeout, arithmetic fix

2026-03-12 09:39:09 +01:00

migrate-qdrant.py

feat(qdrant): Migrate to hosted qdrant-dev.breakpilot.ai with API-Key auth

2026-03-06 13:55:21 +01:00

migrate-qdrant.sh

feat(qdrant): Migrate to hosted qdrant-dev.breakpilot.ai with API-Key auth

2026-03-06 13:55:21 +01:00

populate-rag-originals.sh

fix: correct EDPB/ENISA/EDPS PDF download URLs

2026-03-01 11:17:12 +01:00

rag-sources.md

feat(rag): Expand Phase H to Layer 1 Safe Core (~60 documents)

2026-03-11 16:54:07 +01:00

wait-for-core.sh

Initial commit: breakpilot-compliance - Compliance SDK Platform

2026-02-11 23:47:28 +01:00