Files
breakpilot-compliance/.gitea/workflows/rag-ingest.yaml
Benjamin Admin 995de9e0f4
Some checks failed
CI/CD / go-lint (push) Has been skipped
CI/CD / python-lint (push) Has been skipped
CI/CD / nodejs-lint (push) Has been skipped
CI/CD / test-go-ai-compliance (push) Successful in 47s
CI/CD / test-python-backend-compliance (push) Successful in 47s
CI/CD / test-python-document-crawler (push) Successful in 30s
CI/CD / test-python-dsms-gateway (push) Successful in 25s
CI/CD / deploy-hetzner (push) Failing after 2s
fix(ci): RAG ingestion uses docker:27-cli with host network access
Runner needs access to /opt/breakpilot-compliance and Docker network
for RAG service (bp-core-rag-service:8097). Falls back to
host.docker.internal if container network unavailable.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-11 16:17:16 +01:00

81 lines
2.7 KiB
YAML

# Gitea Actions — RAG Legal Corpus Ingestion
#
# Manuell triggerbarer Workflow zur Ingestion von Rechtstexten in Qdrant.
# Trigger: Gitea UI → Actions → "RAG Ingestion" → Run
#
# Phasen: gesetze, eu, templates, datenschutz, verbraucherschutz, verify, version, all
#
# Voraussetzung: RAG-Service und Qdrant muessen auf Hetzner laufen.
name: RAG Ingestion
on:
workflow_dispatch:
inputs:
phase:
description: 'Ingestion Phase (gesetze, eu, templates, datenschutz, verbraucherschutz, verify, version, all)'
required: true
default: 'verbraucherschutz'
jobs:
ingest:
runs-on: docker
container: docker:27-cli
steps:
- name: Setup
run: |
apk add --no-cache git curl bash python3 > /dev/null 2>&1
- name: Checkout
run: |
git clone --depth 1 --branch main ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git .
- name: Run Ingestion
run: |
set -euo pipefail
PHASE="${{ github.event.inputs.phase }}"
DEPLOY_DIR="/opt/breakpilot-compliance"
echo "=== RAG Ingestion: Phase ${PHASE} ==="
echo ""
# Script aus dem Deploy-Dir nutzen (aktuellster Stand nach git pull)
cd "${DEPLOY_DIR}"
# RAG-Service laeuft im Docker-Netzwerk als bp-core-rag-service
# Qdrant ist extern erreichbar
export WORK_DIR="/tmp/rag-ingestion"
export RAG_URL="http://bp-core-rag-service:8097/api/v1/documents/upload"
export QDRANT_URL="https://qdrant-dev.breakpilot.ai"
export SDK_URL="http://bp-compliance-ai-sdk:8090"
# Source .env fuer DB_URL falls vorhanden
if [ -f .env ]; then
export DB_URL=$(grep COMPLIANCE_DATABASE_URL .env 2>/dev/null | cut -d= -f2- || echo "")
fi
mkdir -p "$WORK_DIR"/{pdfs,repos,texts}
echo "RAG API: $RAG_URL"
echo "Qdrant: $QDRANT_URL"
echo "Work Dir: $WORK_DIR"
echo ""
# Health Check: RAG erreichbar?
# Runner muss im breakpilot-network sein fuer bp-core-rag-service
# Fallback: Host-Netzwerk via host.docker.internal
if ! curl -sf "$RAG_URL" -X POST 2>/dev/null | head -c 100 | grep -q .; then
echo "RAG API nicht im Container-Netzwerk erreichbar."
echo "Versuche Host-Netzwerk (host.docker.internal)..."
export RAG_URL="http://host.docker.internal:8097/api/v1/documents/upload"
fi
if [ "$PHASE" = "all" ]; then
bash scripts/ingest-legal-corpus.sh
else
bash scripts/ingest-legal-corpus.sh --only "$PHASE"
fi
echo ""
echo "=== Ingestion abgeschlossen ==="