Benjamin_Boenisch/breakpilot-pwa
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(rag): Add DACH legal corpus ingestion (DE/AT/CH laws)

Browse Source 
Add 29 new regulations (7 DE + 7 AT + 4 CH + 11 P2/P3) with country
metadata, legal corpus text excerpts, and updated RAG admin UI with
AT/CH type colors and labels. Fix module path in deploy script.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
BreakPilot Dev
2026-02-11 09:24:33 +01:00
parent 9fe0a27a60
commit f927c0c205
13 changed files with 1784 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
run-ingestion.sh Executable file
View File

@@ -0,0 +1,66 @@
#!/bin/bash
# ============================================================
# RAG DACH Ingestion — Nur Ingestion (Builds schon fertig)
# ============================================================
PROJ="/Users/benjaminadmin/Projekte/breakpilot-pwa"
DOCKER="/usr/local/bin/docker"
COMPOSE="$DOCKER compose -f $PROJ/docker-compose.yml"
LOG_FILE="$PROJ/ingest-$(date +%Y%m%d-%H%M%S).log"
exec > >(tee -a "$LOG_FILE") 2>&1
echo "============================================================"
echo "RAG DACH Ingestion — Start: $(date)"
echo "Logfile: $LOG_FILE"
echo "============================================================"
# Health Check (via docker exec, Port nicht auf Host exponiert)
echo ""
echo "[1/5] Pruefe klausur-service..."
if ! $COMPOSE exec -T klausur-service python -c "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8086/health')" 2>/dev/null; then
echo "FEHLER: klausur-service nicht erreichbar!"
exit 1
fi
echo "klausur-service ist bereit."
# P1 — Deutschland
echo ""
echo "[2/5] Ingestion P1 — Deutschland (7 Gesetze)..."
$COMPOSE exec -T klausur-service python -m legal_corpus_ingestion --ingest \
DE_DDG DE_BGB_AGB DE_EGBGB DE_UWG DE_HGB_RET DE_AO_RET DE_TKG 2>&1 || echo "DE P1 hatte Fehler"
# P1 — Oesterreich
echo ""
echo "[3/5] Ingestion P1 — Oesterreich (7 Gesetze)..."
$COMPOSE exec -T klausur-service python -m legal_corpus_ingestion --ingest \
AT_ECG AT_TKG AT_KSCHG AT_FAGG AT_UGB_RET AT_BAO_RET AT_MEDIENG 2>&1 || echo "AT P1 hatte Fehler"
# P1 — Schweiz
echo ""
echo "[4/5] Ingestion P1 — Schweiz (4 Gesetze)..."
$COMPOSE exec -T klausur-service python -m legal_corpus_ingestion --ingest \
CH_DSV CH_OR_AGB CH_UWG CH_FMG 2>&1 || echo "CH P1 hatte Fehler"
# 3 fehlgeschlagene Quellen + P2 + P3
echo ""
echo "[5/5] Ingestion P2/P3 + Fixes (14 Gesetze)..."
$COMPOSE exec -T klausur-service python -m legal_corpus_ingestion --ingest \
LU_DPA_LAW DK_DATABESKYTTELSESLOVEN EDPB_GUIDELINES_1_2022 \
DE_PANGV DE_DLINFOV DE_BETRVG \
AT_ABGB_AGB AT_UWG \
CH_GEBUV CH_ZERTES \
DE_GESCHGEHG DE_BSIG DE_USTG_RET CH_ZGB_PERS 2>&1 || echo "P2/P3 hatte Fehler"
# Status
echo ""
echo "============================================================"
echo "FINAL STATUS CHECK"
echo "============================================================"
$COMPOSE exec -T klausur-service python -m legal_corpus_ingestion --status 2>&1
echo ""
echo "============================================================"
echo "Fertig: $(date)"
echo "Logfile: $LOG_FILE"
echo "============================================================"