feat(ci): Add manual RAG ingestion workflow for Gitea Actions
Some checks failed
CI/CD / go-lint (push) Has been cancelled
CI/CD / python-lint (push) Has been cancelled
CI/CD / nodejs-lint (push) Has been cancelled
CI/CD / test-go-ai-compliance (push) Has been cancelled
CI/CD / test-python-backend-compliance (push) Has been cancelled
CI/CD / test-python-document-crawler (push) Has been cancelled
CI/CD / test-python-dsms-gateway (push) Has been cancelled
CI/CD / deploy-hetzner (push) Has been cancelled

Adds workflow_dispatch-triggered job to run ingest-legal-corpus.sh
on Hetzner. Supports phase selection (verbraucherschutz, gesetze, eu, etc.).

Usage: Gitea UI → Actions → "RAG Ingestion" → Run (select phase)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-03-11 16:14:44 +01:00
parent 7f38df9d9c
commit 4e08364bc6

View File

@@ -0,0 +1,73 @@
# 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: python:3.12-slim
steps:
- name: Setup
run: |
apt-get update -qq && apt-get install -y -qq git curl > /dev/null 2>&1
- name: Checkout
run: |
git clone --depth 1 --branch main ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git .
- name: Check RAG service
run: |
# RAG-Service laeuft auf dem Host, nicht im Container
# Qdrant ist extern erreichbar
echo "Checking Qdrant..."
curl -sf "${QDRANT_URL}/collections" > /dev/null 2>&1 \
&& echo "Qdrant: OK" \
|| echo "WARNUNG: Qdrant nicht erreichbar (${QDRANT_URL})"
echo "Checking RAG API..."
curl -sf -k "${RAG_URL}" -X POST 2>/dev/null | head -c 200 \
&& echo "" && echo "RAG API: OK" \
|| echo "WARNUNG: RAG API nicht erreichbar (${RAG_URL})"
env:
QDRANT_URL: "https://qdrant-dev.breakpilot.ai"
RAG_URL: "https://localhost:8097/api/v1/documents/upload"
- name: Run Ingestion
run: |
set -euo pipefail
PHASE="${{ github.event.inputs.phase }}"
echo "=== RAG Ingestion: Phase ${PHASE} ==="
echo ""
# Konfiguration fuer Hetzner
export WORK_DIR="/tmp/rag-ingestion"
export RAG_URL="https://localhost:8097/api/v1/documents/upload"
export QDRANT_URL="https://qdrant-dev.breakpilot.ai"
export SDK_URL="https://localhost:8093"
mkdir -p "$WORK_DIR"/{pdfs,repos,texts}
if [ "$PHASE" = "all" ]; then
bash scripts/ingest-legal-corpus.sh
else
bash scripts/ingest-legal-corpus.sh --only "$PHASE"
fi
echo ""
echo "=== Ingestion abgeschlossen ==="