docs: update MkDocs for 3-project architecture (core/lehrer/compliance)
- Rewrite system-architecture.md with new 3-project diagram - Update index.md with Core services table and nginx routing - Replace service docs that moved to lehrer/compliance with redirects (klausur-service, voice-service, agent-core, ki-daten-pipeline -> lehrer) (ai-compliance-sdk -> compliance) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Benjamin Boenisch
@@ -1,254 +1,163 @@
|
|||||||
# BreakPilot PWA - System-Architektur
|
# BreakPilot - System-Architektur
|
||||||
|
|
||||||
## Übersicht
|
## Uebersicht
|
||||||
|
|
||||||
BreakPilot ist eine modulare Bildungsplattform für Lehrkräfte mit folgenden Hauptkomponenten:
|
BreakPilot ist eine modulare Bildungs- und Compliance-Plattform, aufgeteilt in drei unabhaengige Docker Compose Projekte:
|
||||||
|
|
||||||
```
|
```
|
||||||
┌─────────────────────────────────────────────────────────────────────┐
|
┌────────────────────────────────────────────────────────────────────────────┐
|
||||||
│ Browser │
|
│ Browser │
|
||||||
│ ┌───────────────────────────────────────────────────────────────┐ │
|
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
|
||||||
│ │ Frontend (Studio UI) │ │
|
│ │ Studio v2 │ │ Admin Lehrer │ │ Admin Compl. │ │ Dev Portal │ │
|
||||||
│ │ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────────────┐ │ │
|
│ │ (443) │ │ (3002) │ │ (3007) │ │ (3006) │ │
|
||||||
│ │ │Dashboard │ │Worksheets│ │Correction│ │Letters/Companion │ │ │
|
│ └──────┬───────┘ └──────┬───────┘ └──────┬───────┘ └──────┬───────┘ │
|
||||||
│ │ └──────────┘ └──────────┘ └──────────┘ └──────────────────┘ │ │
|
└─────────┼──────────────────┼──────────────────┼──────────────────┼─────────┘
|
||||||
│ └───────────────────────────────────────────────────────────────┘ │
|
│ │ │ │
|
||||||
└───────────────────────────┬─────────────────────────────────────────┘
|
▼ ▼ ▼ ▼
|
||||||
│ HTTP/REST
|
┌─────────────────────────────────────────────────────────────────────────────┐
|
||||||
▼
|
│ bp-core-nginx (Reverse Proxy + TLS) │
|
||||||
┌─────────────────────────────────────────────────────────────────────┐
|
│ Ports: 80, 443, 3000-3008, 8000-8097 │
|
||||||
│ Python Backend (FastAPI) │
|
└────────┬──────────────────┬──────────────────┬──────────────────────────────┘
|
||||||
│ Port 8000 │
|
│ │ │
|
||||||
│ ┌────────────────────────────────────────────────────────────────┐ │
|
▼ ▼ ▼
|
||||||
│ │ API Layer │ │
|
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
|
||||||
│ │ /api/worksheets /api/corrections /api/letters /api/state │ │
|
│ breakpilot-core │ │breakpilot-lehrer│ │breakpilot-compl.│
|
||||||
│ │ /api/school /api/certificates /api/messenger /api/jitsi │ │
|
│ (Shared) │ │ (Team A) │ │ (Team B) │
|
||||||
│ └────────────────────────────────────────────────────────────────┘ │
|
│ │ │ │ │ │
|
||||||
│ ┌────────────────────────────────────────────────────────────────┐ │
|
│ PostgreSQL │ │ Studio v2 │ │ Admin Compliance│
|
||||||
│ │ Service Layer │ │
|
│ Valkey │ │ Admin Lehrer │ │ Developer Portal│
|
||||||
│ │ FileProcessor │ PDFService │ ContentGenerators │ StateEngine │ │
|
│ Vault │ │ Website │ │ Backend Compl. │
|
||||||
│ └────────────────────────────────────────────────────────────────┘ │
|
│ Qdrant │ │ Backend Lehrer │ │ AI Compliance │
|
||||||
└───────────────────────────┬─────────────────────────────────────────┘
|
│ MinIO │ │ Klausur Service │ │ SDK (Go) │
|
||||||
│
|
│ Embedding │ │ Voice Service │ │ DSMS (IPFS) │
|
||||||
┌─────────────┼─────────────┐
|
│ RAG Service │ │ School Service │ │ Document Crawler│
|
||||||
▼ ▼ ▼
|
│ Consent (Go) │ │ Geo Service │ │ │
|
||||||
┌─────────────────┐ ┌───────────────┐ ┌──────────────┐ ┌──────────────┐
|
│ Billing (Go) │ │ PaddleOCR │ │ │
|
||||||
│ Go Consent │ │ PostgreSQL │ │ LLM Gateway │ │ HashiCorp │
|
│ Backend Core │ │ Agent Core │ │ │
|
||||||
│ Service │ │ Database │ │ (optional) │ │ Vault │
|
│ Admin Core │ │ Transcription │ │ │
|
||||||
│ Port 8081 │ │ Port 5432 │ │ │ │ Port 8200 │
|
│ Jitsi (5x) │ │ BreakPilot Drive│ │ │
|
||||||
└─────────────────┘ └───────────────┘ └──────────────┘ └──────────────┘
|
│ Night Scheduler │ │ │ │ │
|
||||||
|
│ Health Agg. │ │ │ │ │
|
||||||
|
│ Gitea/Woodpecker│ │ │ │ │
|
||||||
|
│ ERP (optional) │ │ │ │ │
|
||||||
|
└─────────────────┘ └─────────────────┘ └─────────────────┘
|
||||||
|
│ │ │
|
||||||
|
└──────────────────┴──────────────────┘
|
||||||
|
breakpilot-network
|
||||||
|
(gemeinsames Docker-Netzwerk)
|
||||||
```
|
```
|
||||||
|
|
||||||
## Komponenten
|
---
|
||||||
|
|
||||||
### 1. Admin Frontend (Next.js Website)
|
## Drei-Projekt-Architektur
|
||||||
|
|
||||||
Das **Admin Frontend** ist eine vollständige Next.js 15 Anwendung für Developer und Administratoren:
|
### breakpilot-core (Shared Infrastructure)
|
||||||
|
|
||||||
**Technologie:** Next.js 15, React 18, TypeScript, Tailwind CSS
|
Stellt gemeinsam genutzte Infrastruktur bereit. Beide Teams (Lehrer + Compliance) haengen von Core ab.
|
||||||
|
|
||||||
**Container:** `breakpilot-pwa-website` auf **Port 3000**
|
**Container-Prefix:** `bp-core-*`
|
||||||
|
|
||||||
**Verzeichnis:** `/website`
|
| Kategorie | Services |
|
||||||
|
|-----------|----------|
|
||||||
|
| Datenbank & Cache | PostgreSQL (PostGIS 16), Valkey |
|
||||||
|
| Security | Vault, Vault-Init, Vault-Agent |
|
||||||
|
| AI/ML | Embedding Service, RAG Service, Qdrant |
|
||||||
|
| Storage | MinIO (S3) |
|
||||||
|
| Business Logic | Consent Service (Go), Billing Service (Go), Backend Core (Python) |
|
||||||
|
| Frontend | Admin Core (Next.js, Port 3008) |
|
||||||
|
| Networking | Nginx (Reverse Proxy + TLS) |
|
||||||
|
| Monitoring | Health Aggregator |
|
||||||
|
| DevOps | Gitea, Woodpecker CI/CD, Night Scheduler, Mailpit |
|
||||||
|
| Kommunikation | Jitsi Meet (5 Container), Synapse (Matrix Chat) |
|
||||||
|
| ERP | ERPNext (optional, 9 Container) |
|
||||||
|
|
||||||
| Modul | Route | Beschreibung |
|
### breakpilot-lehrer (Team A: Bildung)
|
||||||
|-------|-------|--------------|
|
|
||||||
| Dashboard | `/admin` | Übersicht & Statistiken |
|
|
||||||
| GPU Infrastruktur | `/admin/gpu` | vast.ai GPU Management |
|
|
||||||
| Consent Verwaltung | `/admin/consent` | Rechtliche Dokumente & Versionen |
|
|
||||||
| Datenschutzanfragen | `/admin/dsr` | DSGVO Art. 15-21 Anfragen |
|
|
||||||
| DSMS | `/admin/dsms` | Datenschutz-Management-System |
|
|
||||||
| Education Search | `/admin/edu-search` | Bildungsquellen & Crawler |
|
|
||||||
| Personensuche | `/admin/staff-search` | Uni-Mitarbeiter & Publikationen |
|
|
||||||
| Uni-Crawler | `/admin/uni-crawler` | Universitäts-Crawling Orchestrator |
|
|
||||||
| LLM Vergleich | `/admin/llm-compare` | KI-Provider Vergleich |
|
|
||||||
| PCA Platform | `/admin/pca-platform` | Bot-Erkennung & Monetarisierung |
|
|
||||||
| Production Backlog | `/admin/backlog` | Go-Live Checkliste |
|
|
||||||
| Developer Docs | `/admin/docs` | API & Architektur Dokumentation |
|
|
||||||
| Kommunikation | `/admin/communication` | Matrix & Jitsi Monitoring |
|
|
||||||
| **Security** | `/admin/security` | DevSecOps Dashboard, Scans, Findings |
|
|
||||||
| **SBOM** | `/admin/sbom` | Software Bill of Materials |
|
|
||||||
|
|
||||||
### 2. Lehrer Frontend (Studio UI)
|
Alle Services fuer Lehrkraefte und den Bildungsbereich.
|
||||||
|
|
||||||
Das **Lehrer Frontend** ist ein Single-Page-Application-ähnliches System für Lehrkräfte, das in Python-Modulen organisiert ist:
|
**Container-Prefix:** `bp-lehrer-*`
|
||||||
|
|
||||||
| Modul | Datei | Beschreibung |
|
| Service | Container | Port | Beschreibung |
|
||||||
|-------|-------|--------------|
|
|---------|-----------|------|--------------|
|
||||||
| Base | `frontend/modules/base.py` | TopBar, Sidebar, Theme, Login |
|
| Admin Lehrer | bp-lehrer-admin | 3002 | Lehrer-Dashboard (Next.js) |
|
||||||
| Dashboard | `frontend/modules/dashboard.py` | Übersichtsseite |
|
| Studio v2 | bp-lehrer-studio-v2 | 443 | Lehrer-/Schueler-Studio (Next.js) |
|
||||||
| Worksheets | `frontend/modules/worksheets.py` | Lerneinheiten-Generator |
|
| Website | bp-lehrer-website | 3000 | Oeffentliche Website (Next.js) |
|
||||||
| Correction | `frontend/modules/correction.py` | OCR-Klausurkorrektur |
|
| Backend Lehrer | bp-lehrer-backend | 8001 | API Backend (Python/FastAPI) |
|
||||||
| Letters | `frontend/modules/letters.py` | Elternkommunikation |
|
| Klausur Service | bp-lehrer-klausur-service | 8086 | Pruefungen, OCR, RAG (Python) |
|
||||||
| Companion | `frontend/modules/companion.py` | Begleiter-Modus mit State Engine |
|
| School Service | bp-lehrer-school-service | 8084 | Schulverwaltung (Go) |
|
||||||
| School | `frontend/modules/school.py` | Schulverwaltung |
|
| Voice Service | bp-lehrer-voice-service | 8091 | Spracheingabe (Python) |
|
||||||
| Gradebook | `frontend/modules/gradebook.py` | Notenbuch |
|
| Geo Service | bp-lehrer-geo-service | 8088 | Geo-Daten/PostGIS (Python) |
|
||||||
| ContentCreator | `frontend/modules/content_creator.py` | H5P Content Creator |
|
| PaddleOCR | bp-lehrer-paddleocr | - | OCR Engine (Profil: ocr) |
|
||||||
| ContentFeed | `frontend/modules/content_feed.py` | Content Discovery |
|
| BreakPilot Drive | bp-lehrer-breakpilot-drive | - | Lernspiel (Profil: game) |
|
||||||
| Messenger | `frontend/modules/messenger.py` | Matrix Messenger |
|
| Agent Core | bp-lehrer-agent-core | - | Multi-Agent System (Profil: dev) |
|
||||||
| Jitsi | `frontend/modules/jitsi.py` | Videokonferenzen |
|
| Transcription Worker | bp-lehrer-transcription | - | Audio-Transkription (Profil: recording) |
|
||||||
| **KlausurKorrektur** | `frontend/modules/klausur_korrektur.py` | **Abitur-Klausurkorrektur (15-Punkte-System)** |
|
|
||||||
| **AbiturDocsAdmin** | `frontend/modules/abitur_docs_admin.py` | **Admin für Abitur-Dokumente (NiBiS)** |
|
|
||||||
|
|
||||||
Jedes Modul exportiert:
|
### breakpilot-compliance (Team B: DSGVO/Compliance)
|
||||||
- `get_css()` - CSS-Styles
|
|
||||||
- `get_html()` - HTML-Template
|
|
||||||
- `get_js()` - JavaScript-Logik
|
|
||||||
|
|
||||||
### 3. Python Backend (FastAPI)
|
Alle Services fuer das Compliance-Produkt (DSGVO, AI Act, BSI).
|
||||||
|
|
||||||
#### API-Router
|
**Container-Prefix:** `bp-compliance-*`
|
||||||
|
|
||||||
| Router | Präfix | Beschreibung |
|
| Service | Container | Port | Beschreibung |
|
||||||
|--------|--------|--------------|
|
|---------|-----------|------|--------------|
|
||||||
| `worksheets_api` | `/api/worksheets` | Content-Generatoren (MC, Cloze, Mindmap, Quiz) |
|
| Admin Compliance | bp-compliance-admin | 3007 | Compliance-Dashboard (Next.js) |
|
||||||
| `correction_api` | `/api/corrections` | OCR-Pipeline für Klausurkorrektur |
|
| Developer Portal | bp-compliance-developer-portal | 3006 | API-Dokumentation (Next.js) |
|
||||||
| `letters_api` | `/api/letters` | Elternbriefe mit GFK-Integration |
|
| Backend Compliance | bp-compliance-backend | 8002 | Compliance API (Python/FastAPI) |
|
||||||
| `state_engine_api` | `/api/state` | Begleiter-Modus Phasen & Vorschläge |
|
| AI Compliance SDK | bp-compliance-ai-sdk | 8090/8093 | DSGVO-konforme KI (Go) |
|
||||||
| `school_api` | `/api/school` | Schulverwaltung (Proxy zu school-service) |
|
| DSMS Node | bp-compliance-dsms-node | 4001/5001 | IPFS Node |
|
||||||
| `certificates_api` | `/api/certificates` | Zeugniserstellung |
|
| DSMS Gateway | bp-compliance-dsms-gateway | 8082 | IPFS Gateway (Node.js) |
|
||||||
| `messenger_api` | `/api/messenger` | Matrix Messenger Integration |
|
| Document Crawler | bp-compliance-document-crawler | 8098 | Web-Crawler (Python) |
|
||||||
| `jitsi_api` | `/api/jitsi` | Jitsi Meeting-Einladungen |
|
|
||||||
| `consent_api` | `/api/consent` | DSGVO Consent-Verwaltung |
|
|
||||||
| `gdpr_api` | `/api/gdpr` | GDPR-Export |
|
|
||||||
| **`klausur_korrektur_api`** | `/api/klausur-korrektur` | **Abitur-Klausuren (15-Punkte, Gutachten, Fairness)** |
|
|
||||||
| **`abitur_docs_api`** | `/api/abitur-docs` | **NiBiS-Dokumentenverwaltung für RAG** |
|
|
||||||
|
|
||||||
#### Services
|
---
|
||||||
|
|
||||||
| Service | Datei | Beschreibung |
|
## Netzwerk-Architektur
|
||||||
|---------|-------|--------------|
|
|
||||||
| FileProcessor | `services/file_processor.py` | OCR mit PaddleOCR |
|
|
||||||
| PDFService | `services/pdf_service.py` | PDF-Generierung |
|
|
||||||
| ContentGenerators | `services/content_generators/` | MC, Cloze, Mindmap, Quiz |
|
|
||||||
| StateEngine | `state_engine/` | Phasen-Management & Antizipation |
|
|
||||||
|
|
||||||
### 4. Klausur-Korrektur System (Abitur)
|
### Gemeinsames Docker-Netzwerk
|
||||||
|
|
||||||
Das Klausur-Korrektur-System implementiert die vollständige Abitur-Bewertungspipeline:
|
Alle drei Projekte nutzen dasselbe Docker-Netzwerk `breakpilot-network`:
|
||||||
|
|
||||||
```
|
```yaml
|
||||||
┌─────────────────────────────────────────────────────────────────────┐
|
# In jedem docker-compose.yml:
|
||||||
│ Klausur-Korrektur Modul │
|
networks:
|
||||||
│ │
|
breakpilot-network:
|
||||||
│ ┌─────────────┐ ┌──────────────────┐ ┌─────────────────┐ │
|
external: true
|
||||||
│ │ Modus-Wahl │───►│ Text-Quellen & │───►│ Erwartungs- │ │
|
|
||||||
│ │ LandesAbi/ │ │ Rights-Gate │ │ horizont │ │
|
|
||||||
│ │ Vorabitur │ └──────────────────┘ └─────────────────┘ │
|
|
||||||
│ └─────────────┘ │ │
|
|
||||||
│ ▼ │
|
|
||||||
│ ┌─────────────────────────────────────────────────────────────┐ │
|
|
||||||
│ │ Schülerarbeiten-Pipeline │ │
|
|
||||||
│ │ Upload → OCR → KI-Bewertung → Gutachten → 15-Punkte-Note │ │
|
|
||||||
│ └─────────────────────────────────────────────────────────────┘ │
|
|
||||||
│ │ │
|
|
||||||
│ ▼ │
|
|
||||||
│ ┌────────────────────┐ ┌──────────────────────────────────┐ │
|
|
||||||
│ │ Erst-/Zweitprüfer │───►│ Fairness-Analyse & PDF-Export │ │
|
|
||||||
│ └────────────────────┘ └──────────────────────────────────┘ │
|
|
||||||
└─────────────────────────────────────────────────────────────────────┘
|
|
||||||
```
|
```
|
||||||
|
|
||||||
#### 15-Punkte-Notensystem
|
Container koennen sich gegenseitig ueber ihre Container-Namen erreichen:
|
||||||
|
- `bp-lehrer-backend` → `bp-core-postgres:5432`
|
||||||
|
- `bp-compliance-ai-sdk` → `bp-core-qdrant:6333`
|
||||||
|
- `bp-core-nginx` → `bp-lehrer-studio-v2:3001`
|
||||||
|
|
||||||
Das System verwendet den deutschen Abitur-Notenschlüssel:
|
### Nginx Routing
|
||||||
|
|
||||||
| Punkte | Prozent | Note |
|
Der zentrale Nginx in Core routet alle Anfragen an die richtigen Container:
|
||||||
|--------|---------|------|
|
|
||||||
| 15-13 | 95-85% | 1+/1/1- |
|
|
||||||
| 12-10 | 80-70% | 2+/2/2- |
|
|
||||||
| 9-7 | 65-55% | 3+/3/3- |
|
|
||||||
| 6-4 | 50-40% | 4+/4/4- |
|
|
||||||
| 3-1 | 33-20% | 5+/5/5- |
|
|
||||||
| 0 | <20% | 6 |
|
|
||||||
|
|
||||||
#### Bewertungskriterien
|
| Port | Upstream | Projekt |
|
||||||
|
|------|----------|---------|
|
||||||
|
| 443 | bp-lehrer-studio-v2:3001 + Jitsi | Lehrer + Core |
|
||||||
|
| 3000 | bp-lehrer-website:3000 | Lehrer |
|
||||||
|
| 3002 | bp-lehrer-admin:3000 | Lehrer |
|
||||||
|
| 3006 | bp-compliance-developer-portal:3000 | Compliance |
|
||||||
|
| 3007 | bp-compliance-admin:3000 | Compliance |
|
||||||
|
| 3008 | bp-core-admin:3000 | Core |
|
||||||
|
| 8000 | bp-core-backend:8000 | Core |
|
||||||
|
| 8001 | bp-lehrer-backend:8001 | Lehrer |
|
||||||
|
| 8002 | bp-compliance-backend:8002 | Compliance |
|
||||||
|
| 8086 | bp-lehrer-klausur-service:8086 | Lehrer |
|
||||||
|
| 8091 | bp-lehrer-voice-service:8091 | Lehrer |
|
||||||
|
| 8093 | bp-compliance-ai-sdk:8090 | Compliance |
|
||||||
|
| 8443 | bp-core-jitsi-web:80 | Core |
|
||||||
|
|
||||||
| Kriterium | Gewicht | Beschreibung |
|
---
|
||||||
|-----------|---------|--------------|
|
|
||||||
| Rechtschreibung | 15% | Orthografie |
|
|
||||||
| Grammatik | 15% | Grammatik & Syntax |
|
|
||||||
| **Inhalt** | **40%** | Inhaltliche Qualität (höchste Gewichtung) |
|
|
||||||
| Struktur | 15% | Aufbau & Gliederung |
|
|
||||||
| Stil | 15% | Ausdruck & Stil |
|
|
||||||
|
|
||||||
### 5. Go Consent Service
|
|
||||||
|
|
||||||
Verwaltet DSGVO-Einwilligungen:
|
|
||||||
|
|
||||||
```
|
|
||||||
consent-service/
|
|
||||||
├── cmd/server/ # Main entry point
|
|
||||||
├── internal/
|
|
||||||
│ ├── handlers/ # HTTP Handler
|
|
||||||
│ ├── services/ # Business Logic
|
|
||||||
│ ├── models/ # Data Models
|
|
||||||
│ └── middleware/ # Auth Middleware
|
|
||||||
└── migrations/ # SQL Migrations
|
|
||||||
```
|
|
||||||
|
|
||||||
### 6. LLM Gateway (Optional)
|
|
||||||
|
|
||||||
Wenn `LLM_GATEWAY_ENABLED=true`:
|
|
||||||
|
|
||||||
```
|
|
||||||
llm_gateway/
|
|
||||||
├── routes/
|
|
||||||
│ ├── chat.py # Chat-Completion API
|
|
||||||
│ ├── communication.py # GFK-Validierung
|
|
||||||
│ ├── edu_search_seeds.py # Bildungssuche
|
|
||||||
│ └── legal_crawler.py # Schulgesetz-Crawler
|
|
||||||
└── services/
|
|
||||||
└── communication_service.py
|
|
||||||
```
|
|
||||||
|
|
||||||
## Datenfluss
|
|
||||||
|
|
||||||
### Worksheet-Generierung
|
|
||||||
|
|
||||||
```
|
|
||||||
User Input → Frontend (worksheets.py)
|
|
||||||
↓
|
|
||||||
POST /api/worksheets/generate/multiple-choice
|
|
||||||
↓
|
|
||||||
worksheets_api.py → MCGenerator (services/content_generators/)
|
|
||||||
↓
|
|
||||||
Optional: LLM für erweiterte Generierung
|
|
||||||
↓
|
|
||||||
Response: WorksheetContent → Frontend rendert Ergebnis
|
|
||||||
```
|
|
||||||
|
|
||||||
### Klausurkorrektur
|
|
||||||
|
|
||||||
```
|
|
||||||
File Upload → Frontend (correction.py)
|
|
||||||
↓
|
|
||||||
POST /api/corrections/ (erstellen)
|
|
||||||
POST /api/corrections/{id}/upload (Datei)
|
|
||||||
↓
|
|
||||||
Background Task: OCR via FileProcessor
|
|
||||||
↓
|
|
||||||
Poll GET /api/corrections/{id} bis status="ocr_complete"
|
|
||||||
↓
|
|
||||||
POST /api/corrections/{id}/analyze
|
|
||||||
↓
|
|
||||||
Review Interface → PUT /api/corrections/{id} (Anpassungen)
|
|
||||||
↓
|
|
||||||
GET /api/corrections/{id}/export-pdf
|
|
||||||
```
|
|
||||||
|
|
||||||
## Sicherheit
|
## Sicherheit
|
||||||
|
|
||||||
### Authentifizierung & Autorisierung
|
### Authentifizierung & Autorisierung
|
||||||
|
|
||||||
BreakPilot verwendet einen **Hybrid-Ansatz**:
|
|
||||||
|
|
||||||
| Schicht | Komponente | Beschreibung |
|
| Schicht | Komponente | Beschreibung |
|
||||||
|---------|------------|--------------|
|
|---------|------------|--------------|
|
||||||
| **Authentifizierung** | Keycloak (Prod) / Lokales JWT (Dev) | Token-Validierung via JWKS oder HS256 |
|
| **Authentifizierung** | Keycloak (Prod) / Lokales JWT (Dev) | Token-Validierung via JWKS oder HS256 |
|
||||||
| **Autorisierung** | rbac.py (Eigenentwicklung) | Domaenenspezifische Berechtigungen |
|
| **Autorisierung** | RBAC (Eigenentwicklung) | Domaenenspezifische Berechtigungen |
|
||||||
|
|
||||||
Siehe: [Auth-System](auth-system.md)
|
|
||||||
|
|
||||||
### Basis-Rollen
|
### Basis-Rollen
|
||||||
|
|
||||||
@@ -259,53 +168,60 @@ Siehe: [Auth-System](auth-system.md)
|
|||||||
| `admin` | Administrator |
|
| `admin` | Administrator |
|
||||||
| `data_protection_officer` | Datenschutzbeauftragter |
|
| `data_protection_officer` | Datenschutzbeauftragter |
|
||||||
|
|
||||||
### Erweiterte Rollen (rbac.py)
|
|
||||||
|
|
||||||
15+ domaenenspezifische Rollen fuer Klausurkorrektur und Zeugnisse:
|
|
||||||
- `erstkorrektor`, `zweitkorrektor`, `drittkorrektor`
|
|
||||||
- `klassenlehrer`, `fachlehrer`, `fachvorsitz`
|
|
||||||
- `schulleitung`, `zeugnisbeauftragter`, `sekretariat`
|
|
||||||
|
|
||||||
### Sicherheitsfeatures
|
### Sicherheitsfeatures
|
||||||
|
|
||||||
- JWT-basierte Authentifizierung (RS256/HS256)
|
- JWT-basierte Authentifizierung (RS256/HS256)
|
||||||
- CORS konfiguriert für Frontend-Zugriff
|
- CORS konfiguriert pro Service
|
||||||
- DSGVO-konformes Consent-Management
|
- DSGVO-konformes Consent-Management (Core)
|
||||||
- **HashiCorp Vault** fuer Secrets-Management (keine hardcodierten Secrets)
|
- **HashiCorp Vault** fuer Secrets-Management
|
||||||
- Bundesland-spezifische Policy-Sets
|
- **DevSecOps Pipeline** mit Trivy, Semgrep, Gitleaks
|
||||||
- **DevSecOps Pipeline** mit automatisierten Security-Scans (SAST, SCA, Secrets Detection)
|
|
||||||
|
|
||||||
Siehe:
|
Siehe:
|
||||||
|
- [Auth-System](auth-system.md)
|
||||||
- [Secrets Management](secrets-management.md)
|
- [Secrets Management](secrets-management.md)
|
||||||
- [DevSecOps](devsecops.md)
|
- [DevSecOps](devsecops.md)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
## Deployment
|
## Deployment
|
||||||
|
|
||||||
```yaml
|
### Start-Reihenfolge
|
||||||
services:
|
|
||||||
backend:
|
|
||||||
build: ./backend
|
|
||||||
ports: ["8000:8000"]
|
|
||||||
environment:
|
|
||||||
- DATABASE_URL=postgresql://...
|
|
||||||
- LLM_GATEWAY_ENABLED=false
|
|
||||||
|
|
||||||
consent-service:
|
```bash
|
||||||
build: ./consent-service
|
# 1. Core zuerst (Infrastruktur)
|
||||||
ports: ["8081:8081"]
|
docker compose -f breakpilot-core/docker-compose.yml up -d
|
||||||
|
|
||||||
postgres:
|
# 2. Lehrer-Stack
|
||||||
image: postgres:15
|
docker compose -f breakpilot-lehrer/docker-compose.yml up -d
|
||||||
volumes:
|
|
||||||
- pgdata:/var/lib/postgresql/data
|
# 3. Compliance-Stack
|
||||||
|
docker compose -f breakpilot-compliance/docker-compose.yml up -d
|
||||||
```
|
```
|
||||||
|
|
||||||
|
### Health-Checks
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Core Health (alle Infrastruktur-Services)
|
||||||
|
curl https://macmini:8099/health
|
||||||
|
|
||||||
|
# Lehrer Backend
|
||||||
|
curl https://macmini:8001/health
|
||||||
|
|
||||||
|
# Compliance Backend
|
||||||
|
curl https://macmini:8002/health
|
||||||
|
|
||||||
|
# AI SDK
|
||||||
|
curl https://macmini:8093/health
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
## Erweiterung
|
## Erweiterung
|
||||||
|
|
||||||
Neues Frontend-Modul hinzufügen:
|
### Neuen Service zu einem Projekt hinzufuegen
|
||||||
|
|
||||||
1. Modul erstellen: `frontend/modules/new_module.py`
|
1. Service-Definition in das jeweilige `docker-compose.yml` hinzufuegen
|
||||||
2. Klasse mit `get_css()`, `get_html()`, `get_js()` implementieren
|
2. Container-Name mit dem richtigen Prefix versehen (`bp-core-*`, `bp-lehrer-*`, `bp-compliance-*`)
|
||||||
3. In `frontend/modules/__init__.py` importieren und exportieren
|
3. Netzwerk `breakpilot-network` zuweisen
|
||||||
4. Optional: Zugehörige API in `new_module_api.py` erstellen
|
4. Falls HTTPS noetig: Nginx-Route in `breakpilot-core/nginx/conf.d/default.conf` hinzufuegen
|
||||||
5. In `main.py` Router registrieren
|
5. Dokumentation in der jeweiligen MkDocs-Instanz aktualisieren
|
||||||
|
|||||||
@@ -1,124 +1,71 @@
|
|||||||
# Breakpilot Dokumentation
|
# BreakPilot Core - Dokumentation
|
||||||
|
|
||||||
Willkommen zur zentralen Dokumentation des Breakpilot-Projekts.
|
Zentrale Infrastruktur-Dokumentation fuer das BreakPilot-Oekosystem.
|
||||||
|
|
||||||
## Was ist Breakpilot?
|
## Drei-Projekt-Architektur
|
||||||
|
|
||||||
Breakpilot ist eine DSGVO-konforme Bildungsplattform fuer Lehrkraefte mit folgenden Kernfunktionen:
|
BreakPilot besteht aus drei unabhaengigen Projekten:
|
||||||
|
|
||||||
- **Consent-Management** - Datenschutzkonforme Einwilligungsverwaltung
|
| Projekt | Beschreibung | Container-Prefix | Farbe |
|
||||||
- **KI-gestuetzte Klausurkorrektur** - Automatische Bewertungsvorschlaege fuer Abiturklausuren
|
|---------|-------------|-------------------|-------|
|
||||||
- **Zeugnisgenerierung** - Workflow-basierte Zeugniserstellung mit Rollenkonzept
|
| **breakpilot-core** (dieses Projekt) | Shared Infrastructure | `bp-core-*` | Teal |
|
||||||
- **Lernmaterial-Generator** - MC-Tests, Lueckentexte, Mindmaps, Quiz
|
| **breakpilot-lehrer** | Bildungs-Stack (Team A) | `bp-lehrer-*` | Blau |
|
||||||
- **Elternbriefe** - GFK-basierte Kommunikation mit PDF-Export
|
| **breakpilot-compliance** | DSGVO/Compliance-Stack (Team B) | `bp-compliance-*` | Lila |
|
||||||
|
|
||||||
## Schnellstart
|
## Core Services
|
||||||
|
|
||||||
<div class="grid cards" markdown>
|
| Service | Container | Port | Beschreibung |
|
||||||
|
|---------|-----------|------|--------------|
|
||||||
|
| Nginx | bp-core-nginx | 80/443 | Reverse Proxy + TLS fuer alle drei Projekte |
|
||||||
|
| PostgreSQL | bp-core-postgres | 5432 | Zentrale Datenbank (PostGIS 16) |
|
||||||
|
| Valkey | bp-core-valkey | 6379 | Session Cache (Redis-Fork) |
|
||||||
|
| Vault | bp-core-vault | 8200 | Secrets Management |
|
||||||
|
| Qdrant | bp-core-qdrant | 6333 | Vector DB fuer RAG |
|
||||||
|
| MinIO | bp-core-minio | 9000 | S3-kompatibler Object Storage |
|
||||||
|
| Embedding Service | bp-core-embedding-service | 8087 | Text-Embeddings |
|
||||||
|
| RAG Service | bp-core-rag-service | 8097 | Retrieval Augmented Generation |
|
||||||
|
| Consent Service | bp-core-consent-service | 8081 | DSGVO Consent (Go) |
|
||||||
|
| Billing Service | bp-core-billing-service | 8083 | Abrechnung (Go) |
|
||||||
|
| Backend Core | bp-core-backend | 8000 | Shared API (Python) |
|
||||||
|
| Admin Core | bp-core-admin | 3008 | Admin-Dashboard (Next.js) |
|
||||||
|
| Health Aggregator | bp-core-health | 8099 | Service-Health Monitoring |
|
||||||
|
| Night Scheduler | bp-core-night-scheduler | 8096 | Nachtabschaltung |
|
||||||
|
| Pitch Deck | bp-core-pitch-deck | 3012 | Investor-Praesentation |
|
||||||
|
| Mailpit | bp-core-mailpit | 8025 | E-Mail (Entwicklung) |
|
||||||
|
| Gitea | bp-core-gitea | 3003 | Git-Server |
|
||||||
|
| Woodpecker | bp-core-woodpecker-server | 8090 | CI/CD |
|
||||||
|
| Jitsi (5 Container) | bp-core-jitsi-* | 8443 | Videokonferenzen |
|
||||||
|
|
||||||
- :material-rocket-launch:{ .lg .middle } **Erste Schritte**
|
## Nginx Routing-Tabelle
|
||||||
|
|
||||||
---
|
| Port | Upstream | Projekt |
|
||||||
|
|------|----------|---------|
|
||||||
Entwicklungsumgebung einrichten und das Projekt starten.
|
| 443 | bp-lehrer-studio-v2:3001 | Lehrer |
|
||||||
|
| 3000 | bp-lehrer-website:3000 | Lehrer |
|
||||||
[:octicons-arrow-right-24: Umgebung einrichten](getting-started/environment-setup.md)
|
| 3002 | bp-lehrer-admin:3000 | Lehrer |
|
||||||
|
| 3006 | bp-compliance-developer-portal:3000 | Compliance |
|
||||||
- :material-server:{ .lg .middle } **Mac Mini Setup**
|
| 3007 | bp-compliance-admin:3000 | Compliance |
|
||||||
|
| 3008 | bp-core-admin:3000 | Core |
|
||||||
---
|
| 8000 | bp-core-backend:8000 | Core |
|
||||||
|
| 8001 | bp-lehrer-backend:8001 | Lehrer |
|
||||||
Headless Server-Konfiguration fuer den Entwicklungsserver.
|
| 8002 | bp-compliance-backend:8002 | Compliance |
|
||||||
|
| 8086 | bp-lehrer-klausur-service:8086 | Lehrer |
|
||||||
[:octicons-arrow-right-24: Mac Mini Setup](getting-started/mac-mini-setup.md)
|
| 8087 | bp-core-embedding-service:8087 | Core |
|
||||||
|
| 8091 | bp-lehrer-voice-service:8091 | Lehrer |
|
||||||
</div>
|
| 8093 | bp-compliance-ai-sdk:8090 | Compliance |
|
||||||
|
| 8097 | bp-core-rag-service:8097 | Core |
|
||||||
|
| 8443 | bp-core-jitsi-web:80 | Core |
|
||||||
|
|
||||||
## Architektur
|
## Architektur
|
||||||
|
|
||||||
<div class="grid cards" markdown>
|
- [System-Architektur](architecture/system-architecture.md)
|
||||||
|
- [Auth-System](architecture/auth-system.md)
|
||||||
- :material-sitemap:{ .lg .middle } **System-Architektur**
|
- [Secrets Management](architecture/secrets-management.md)
|
||||||
|
- [DevSecOps](architecture/devsecops.md)
|
||||||
---
|
- [Multi-Agent System](architecture/multi-agent.md)
|
||||||
|
|
||||||
Ueberblick ueber alle Komponenten und deren Zusammenspiel.
|
|
||||||
|
|
||||||
[:octicons-arrow-right-24: Architektur](architecture/system-architecture.md)
|
|
||||||
|
|
||||||
- :material-shield-lock:{ .lg .middle } **Auth-System**
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
Hybrid-Authentifizierung mit Keycloak und lokalem JWT.
|
|
||||||
|
|
||||||
[:octicons-arrow-right-24: Auth-System](architecture/auth-system.md)
|
|
||||||
|
|
||||||
- :material-robot:{ .lg .middle } **Multi-Agent System**
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
Verteilte Agent-Architektur fuer KI-Funktionen.
|
|
||||||
|
|
||||||
[:octicons-arrow-right-24: Multi-Agent](architecture/multi-agent.md)
|
|
||||||
|
|
||||||
- :material-key-chain:{ .lg .middle } **Secrets Management**
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
HashiCorp Vault Integration fuer sichere Credentials.
|
|
||||||
|
|
||||||
[:octicons-arrow-right-24: Secrets](architecture/secrets-management.md)
|
|
||||||
|
|
||||||
</div>
|
|
||||||
|
|
||||||
## Services
|
|
||||||
|
|
||||||
| Service | Port | Beschreibung |
|
|
||||||
|---------|------|--------------|
|
|
||||||
| [Backend (Python)](api/backend-api.md) | 8000 | FastAPI Backend mit Panel UI |
|
|
||||||
| [Consent Service (Go)](architecture/auth-system.md) | 8081 | DSGVO-konforme Einwilligungsverwaltung |
|
|
||||||
| [Klausur Service](services/klausur-service/index.md) | 8086 | KI-gestuetzte Klausurkorrektur |
|
|
||||||
| [Agent Core](services/agent-core/index.md) | - | Multi-Agent Infrastructure |
|
|
||||||
| PostgreSQL | 5432 | Relationale Datenbank |
|
|
||||||
| Qdrant | 6333 | Vektor-Datenbank fuer RAG |
|
|
||||||
| MinIO | 9000 | Object Storage |
|
|
||||||
| Vault | 8200 | Secrets Management |
|
|
||||||
|
|
||||||
## Entwicklung
|
## Entwicklung
|
||||||
|
|
||||||
- [Testing](development/testing.md) - Test-Standards und Ausfuehrung
|
- [Testing](development/testing.md)
|
||||||
- [Dokumentation](development/documentation.md) - Dokumentations-Richtlinien
|
- [Dokumentation](development/documentation.md)
|
||||||
- [DevSecOps](architecture/devsecops.md) - Security Pipeline
|
- [CI/CD Pipeline](development/ci-cd-pipeline.md)
|
||||||
- [Umgebungen](architecture/environments.md) - Dev/Staging/Prod
|
|
||||||
|
|
||||||
## Weitere Ressourcen
|
|
||||||
|
|
||||||
- **GitHub Repository**: Internes GitLab
|
|
||||||
- **Issue Tracker**: GitLab Issues
|
|
||||||
- **API Playground**: [http://macmini:8000/docs](http://macmini:8000/docs)
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Projektstruktur
|
|
||||||
|
|
||||||
```
|
|
||||||
breakpilot-pwa/
|
|
||||||
├── backend/ # Python FastAPI Backend
|
|
||||||
├── consent-service/ # Go Consent Service
|
|
||||||
├── klausur-service/ # Klausur-Korrektur Service
|
|
||||||
├── agent-core/ # Multi-Agent Infrastructure
|
|
||||||
├── voice-service/ # Voice/Audio Processing
|
|
||||||
├── website/ # Next.js Frontend
|
|
||||||
├── studio-v2/ # Admin Dashboard (Next.js)
|
|
||||||
├── docs-src/ # Diese Dokumentation
|
|
||||||
└── docker-compose.yml # Container-Orchestrierung
|
|
||||||
```
|
|
||||||
|
|
||||||
## Support
|
|
||||||
|
|
||||||
Bei Fragen oder Problemen:
|
|
||||||
|
|
||||||
1. Pruefen Sie zuerst die relevante Dokumentation
|
|
||||||
2. Suchen Sie im Issue Tracker nach aehnlichen Problemen
|
|
||||||
3. Erstellen Sie ein neues Issue mit detaillierter Beschreibung
|
|
||||||
|
|||||||
@@ -1,420 +1,10 @@
|
|||||||
# Breakpilot Agent Core
|
# Agent Core
|
||||||
|
|
||||||
Multi-Agent Architecture Infrastructure fuer Breakpilot.
|
!!! info "Verschoben nach breakpilot-lehrer"
|
||||||
|
Agent Core gehoert zum **breakpilot-lehrer** Projekt (Team A).
|
||||||
## Uebersicht
|
|
||||||
|
Die aktuelle Dokumentation befindet sich in der [Lehrer MkDocs-Instanz](http://macmini:8010/services/agent-core/).
|
||||||
Das `agent-core` Modul stellt die gemeinsame Infrastruktur fuer Breakpilots Multi-Agent-System bereit:
|
|
||||||
|
**Container:** `bp-lehrer-agent-core`
|
||||||
- **Session Management**: Agent-Sessions mit Checkpoints und Recovery
|
**Profil:** `dev`
|
||||||
- **Shared Brain**: Langzeit-Gedaechtnis und Kontext-Verwaltung
|
**Repo:** `breakpilot-lehrer/agent-core/`
|
||||||
- **Orchestration**: Message Bus, Supervisor und Task-Routing
|
|
||||||
|
|
||||||
## Architektur
|
|
||||||
|
|
||||||
```
|
|
||||||
┌─────────────────────────────────────────────────────────────────┐
|
|
||||||
│ Breakpilot Services │
|
|
||||||
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────────────────┐ │
|
|
||||||
│ │Voice Service│ │Klausur Svc │ │ Admin-v2 / AlertAgent │ │
|
|
||||||
│ └──────┬──────┘ └──────┬──────┘ └───────────┬─────────────┘ │
|
|
||||||
│ │ │ │ │
|
|
||||||
│ └────────────────┼──────────────────────┘ │
|
|
||||||
│ │ │
|
|
||||||
│ ┌───────────────────────▼───────────────────────────────────┐ │
|
|
||||||
│ │ Agent Core │ │
|
|
||||||
│ │ ┌─────────────┐ ┌─────────────┐ ┌───────────────────┐ │ │
|
|
||||||
│ │ │ Sessions │ │Shared Brain │ │ Orchestrator │ │ │
|
|
||||||
│ │ │ - Manager │ │ - Memory │ │ - Message Bus │ │ │
|
|
||||||
│ │ │ - Heartbeat │ │ - Context │ │ - Supervisor │ │ │
|
|
||||||
│ │ │ - Checkpoint│ │ - Knowledge │ │ - Task Router │ │ │
|
|
||||||
│ │ └─────────────┘ └─────────────┘ └───────────────────┘ │ │
|
|
||||||
│ └───────────────────────────────────────────────────────────┘ │
|
|
||||||
│ │ │
|
|
||||||
│ ┌───────────────────────▼───────────────────────────────────┐ │
|
|
||||||
│ │ Infrastructure │ │
|
|
||||||
│ │ Valkey (Redis) PostgreSQL Qdrant │ │
|
|
||||||
│ └───────────────────────────────────────────────────────────┘ │
|
|
||||||
└─────────────────────────────────────────────────────────────────┘
|
|
||||||
```
|
|
||||||
|
|
||||||
## Verzeichnisstruktur
|
|
||||||
|
|
||||||
```
|
|
||||||
agent-core/
|
|
||||||
├── __init__.py # Modul-Exports
|
|
||||||
├── README.md # Diese Datei
|
|
||||||
├── requirements.txt # Python-Abhaengigkeiten
|
|
||||||
├── pytest.ini # Test-Konfiguration
|
|
||||||
│
|
|
||||||
├── soul/ # Agent SOUL Files (Persoenlichkeiten)
|
|
||||||
│ ├── tutor-agent.soul.md
|
|
||||||
│ ├── grader-agent.soul.md
|
|
||||||
│ ├── quality-judge.soul.md
|
|
||||||
│ ├── alert-agent.soul.md
|
|
||||||
│ └── orchestrator.soul.md
|
|
||||||
│
|
|
||||||
├── brain/ # Shared Brain Implementation
|
|
||||||
│ ├── __init__.py
|
|
||||||
│ ├── memory_store.py # Langzeit-Gedaechtnis
|
|
||||||
│ ├── context_manager.py # Konversations-Kontext
|
|
||||||
│ └── knowledge_graph.py # Entity-Beziehungen
|
|
||||||
│
|
|
||||||
├── sessions/ # Session Management
|
|
||||||
│ ├── __init__.py
|
|
||||||
│ ├── session_manager.py # Session-Lifecycle
|
|
||||||
│ ├── heartbeat.py # Liveness-Monitoring
|
|
||||||
│ └── checkpoint.py # Recovery-Checkpoints
|
|
||||||
│
|
|
||||||
├── orchestrator/ # Multi-Agent Orchestration
|
|
||||||
│ ├── __init__.py
|
|
||||||
│ ├── message_bus.py # Inter-Agent Kommunikation
|
|
||||||
│ ├── supervisor.py # Agent-Ueberwachung
|
|
||||||
│ └── task_router.py # Intent-basiertes Routing
|
|
||||||
│
|
|
||||||
└── tests/ # Unit Tests
|
|
||||||
├── conftest.py
|
|
||||||
├── test_session_manager.py
|
|
||||||
├── test_heartbeat.py
|
|
||||||
├── test_message_bus.py
|
|
||||||
├── test_memory_store.py
|
|
||||||
└── test_task_router.py
|
|
||||||
```
|
|
||||||
|
|
||||||
## Komponenten
|
|
||||||
|
|
||||||
### 1. Session Management
|
|
||||||
|
|
||||||
Verwaltet Agent-Sessions mit State-Machine und Recovery-Faehigkeiten.
|
|
||||||
|
|
||||||
```python
|
|
||||||
from agent_core.sessions import SessionManager, AgentSession
|
|
||||||
|
|
||||||
# Session Manager erstellen
|
|
||||||
manager = SessionManager(
|
|
||||||
redis_client=redis,
|
|
||||||
db_pool=pg_pool,
|
|
||||||
namespace="breakpilot"
|
|
||||||
)
|
|
||||||
|
|
||||||
# Session erstellen
|
|
||||||
session = await manager.create_session(
|
|
||||||
agent_type="tutor-agent",
|
|
||||||
user_id="user-123",
|
|
||||||
context={"subject": "math"}
|
|
||||||
)
|
|
||||||
|
|
||||||
# Checkpoint setzen
|
|
||||||
session.checkpoint("task_started", {"task_id": "abc"})
|
|
||||||
|
|
||||||
# Session beenden
|
|
||||||
session.complete({"result": "success"})
|
|
||||||
```
|
|
||||||
|
|
||||||
**Session States:**
|
|
||||||
|
|
||||||
- `ACTIVE` - Session laeuft
|
|
||||||
- `PAUSED` - Session pausiert
|
|
||||||
- `COMPLETED` - Session erfolgreich beendet
|
|
||||||
- `FAILED` - Session fehlgeschlagen
|
|
||||||
|
|
||||||
### 2. Heartbeat Monitoring
|
|
||||||
|
|
||||||
Ueberwacht Agent-Liveness und triggert Recovery bei Timeout.
|
|
||||||
|
|
||||||
```python
|
|
||||||
from agent_core.sessions import HeartbeatMonitor, HeartbeatClient
|
|
||||||
|
|
||||||
# Monitor starten
|
|
||||||
monitor = HeartbeatMonitor(
|
|
||||||
timeout_seconds=30,
|
|
||||||
check_interval_seconds=5,
|
|
||||||
max_missed_beats=3
|
|
||||||
)
|
|
||||||
await monitor.start_monitoring()
|
|
||||||
|
|
||||||
# Agent registrieren
|
|
||||||
monitor.register("agent-1", "tutor-agent")
|
|
||||||
|
|
||||||
# Heartbeat senden
|
|
||||||
async with HeartbeatClient("agent-1", monitor) as client:
|
|
||||||
# Agent-Arbeit...
|
|
||||||
pass
|
|
||||||
```
|
|
||||||
|
|
||||||
### 3. Memory Store
|
|
||||||
|
|
||||||
Langzeit-Gedaechtnis fuer Agents mit TTL und Access-Tracking.
|
|
||||||
|
|
||||||
```python
|
|
||||||
from agent_core.brain import MemoryStore
|
|
||||||
|
|
||||||
store = MemoryStore(redis_client=redis, db_pool=pg_pool)
|
|
||||||
|
|
||||||
# Erinnerung speichern
|
|
||||||
await store.remember(
|
|
||||||
key="evaluation:math:student-1",
|
|
||||||
value={"score": 85, "feedback": "Gut gemacht!"},
|
|
||||||
agent_id="grader-agent",
|
|
||||||
ttl_days=30
|
|
||||||
)
|
|
||||||
|
|
||||||
# Erinnerung abrufen
|
|
||||||
result = await store.recall("evaluation:math:student-1")
|
|
||||||
|
|
||||||
# Nach Pattern suchen
|
|
||||||
similar = await store.search("evaluation:math:*")
|
|
||||||
```
|
|
||||||
|
|
||||||
### 4. Context Manager
|
|
||||||
|
|
||||||
Verwaltet Konversationskontext mit automatischer Komprimierung.
|
|
||||||
|
|
||||||
```python
|
|
||||||
from agent_core.brain import ContextManager, MessageRole
|
|
||||||
|
|
||||||
ctx_manager = ContextManager(redis_client=redis)
|
|
||||||
|
|
||||||
# Kontext erstellen
|
|
||||||
context = ctx_manager.create_context(
|
|
||||||
session_id="session-123",
|
|
||||||
system_prompt="Du bist ein hilfreicher Tutor...",
|
|
||||||
max_messages=50
|
|
||||||
)
|
|
||||||
|
|
||||||
# Nachrichten hinzufuegen
|
|
||||||
context.add_message(MessageRole.USER, "Was ist Photosynthese?")
|
|
||||||
context.add_message(MessageRole.ASSISTANT, "Photosynthese ist...")
|
|
||||||
|
|
||||||
# Fuer LLM API formatieren
|
|
||||||
messages = context.get_messages_for_llm()
|
|
||||||
```
|
|
||||||
|
|
||||||
### 5. Message Bus
|
|
||||||
|
|
||||||
Inter-Agent Kommunikation via Redis Pub/Sub.
|
|
||||||
|
|
||||||
```python
|
|
||||||
from agent_core.orchestrator import MessageBus, AgentMessage, MessagePriority
|
|
||||||
|
|
||||||
bus = MessageBus(redis_client=redis)
|
|
||||||
await bus.start()
|
|
||||||
|
|
||||||
# Handler registrieren
|
|
||||||
async def handle_message(msg):
|
|
||||||
return {"status": "processed"}
|
|
||||||
|
|
||||||
await bus.subscribe("grader-agent", handle_message)
|
|
||||||
|
|
||||||
# Nachricht senden
|
|
||||||
await bus.publish(AgentMessage(
|
|
||||||
sender="orchestrator",
|
|
||||||
receiver="grader-agent",
|
|
||||||
message_type="grade_request",
|
|
||||||
payload={"exam_id": "exam-1"},
|
|
||||||
priority=MessagePriority.HIGH
|
|
||||||
))
|
|
||||||
|
|
||||||
# Request-Response Pattern
|
|
||||||
response = await bus.request(message, timeout=30.0)
|
|
||||||
```
|
|
||||||
|
|
||||||
### 6. Agent Supervisor
|
|
||||||
|
|
||||||
Ueberwacht und koordiniert alle Agents.
|
|
||||||
|
|
||||||
```python
|
|
||||||
from agent_core.orchestrator import AgentSupervisor, RestartPolicy
|
|
||||||
|
|
||||||
supervisor = AgentSupervisor(message_bus=bus, heartbeat_monitor=monitor)
|
|
||||||
|
|
||||||
# Agent registrieren
|
|
||||||
await supervisor.register_agent(
|
|
||||||
agent_id="tutor-1",
|
|
||||||
agent_type="tutor-agent",
|
|
||||||
restart_policy=RestartPolicy.ON_FAILURE,
|
|
||||||
max_restarts=3,
|
|
||||||
capacity=10
|
|
||||||
)
|
|
||||||
|
|
||||||
# Agent starten
|
|
||||||
await supervisor.start_agent("tutor-1")
|
|
||||||
|
|
||||||
# Load Balancing
|
|
||||||
available = supervisor.get_available_agent("tutor-agent")
|
|
||||||
```
|
|
||||||
|
|
||||||
### 7. Task Router
|
|
||||||
|
|
||||||
Intent-basiertes Routing mit Fallback-Ketten.
|
|
||||||
|
|
||||||
```python
|
|
||||||
from agent_core.orchestrator import TaskRouter, RoutingRule, RoutingStrategy
|
|
||||||
|
|
||||||
router = TaskRouter(supervisor=supervisor)
|
|
||||||
|
|
||||||
# Eigene Regel hinzufuegen
|
|
||||||
router.add_rule(RoutingRule(
|
|
||||||
intent_pattern="learning_*",
|
|
||||||
agent_type="tutor-agent",
|
|
||||||
priority=10,
|
|
||||||
fallback_agent="orchestrator"
|
|
||||||
))
|
|
||||||
|
|
||||||
# Task routen
|
|
||||||
result = await router.route(
|
|
||||||
intent="learning_math",
|
|
||||||
context={"grade": 10},
|
|
||||||
strategy=RoutingStrategy.LEAST_LOADED
|
|
||||||
)
|
|
||||||
|
|
||||||
if result.success:
|
|
||||||
print(f"Routed to {result.agent_id}")
|
|
||||||
```
|
|
||||||
|
|
||||||
## SOUL Files
|
|
||||||
|
|
||||||
SOUL-Dateien definieren die Persoenlichkeit und Verhaltensregeln jedes Agents.
|
|
||||||
|
|
||||||
| Agent | SOUL File | Verantwortlichkeit |
|
|
||||||
|-------|-----------|-------------------|
|
|
||||||
| TutorAgent | tutor-agent.soul.md | Lernbegleitung, Fragen beantworten |
|
|
||||||
| GraderAgent | grader-agent.soul.md | Klausur-Korrektur, Bewertung |
|
|
||||||
| QualityJudge | quality-judge.soul.md | BQAS Qualitaetspruefung |
|
|
||||||
| AlertAgent | alert-agent.soul.md | Monitoring, Benachrichtigungen |
|
|
||||||
| Orchestrator | orchestrator.soul.md | Task-Koordination |
|
|
||||||
|
|
||||||
## Datenbank-Schema
|
|
||||||
|
|
||||||
### agent_sessions
|
|
||||||
|
|
||||||
```sql
|
|
||||||
CREATE TABLE agent_sessions (
|
|
||||||
id UUID PRIMARY KEY,
|
|
||||||
agent_type VARCHAR(50) NOT NULL,
|
|
||||||
user_id UUID REFERENCES users(id),
|
|
||||||
state VARCHAR(20) NOT NULL DEFAULT 'active',
|
|
||||||
context JSONB DEFAULT '{}',
|
|
||||||
checkpoints JSONB DEFAULT '[]',
|
|
||||||
created_at TIMESTAMPTZ DEFAULT NOW(),
|
|
||||||
updated_at TIMESTAMPTZ DEFAULT NOW(),
|
|
||||||
last_heartbeat TIMESTAMPTZ DEFAULT NOW()
|
|
||||||
);
|
|
||||||
```
|
|
||||||
|
|
||||||
### agent_memory
|
|
||||||
|
|
||||||
```sql
|
|
||||||
CREATE TABLE agent_memory (
|
|
||||||
id UUID PRIMARY KEY,
|
|
||||||
namespace VARCHAR(100) NOT NULL,
|
|
||||||
key VARCHAR(500) NOT NULL,
|
|
||||||
value JSONB NOT NULL,
|
|
||||||
agent_id VARCHAR(50) NOT NULL,
|
|
||||||
access_count INTEGER DEFAULT 0,
|
|
||||||
created_at TIMESTAMPTZ DEFAULT NOW(),
|
|
||||||
expires_at TIMESTAMPTZ,
|
|
||||||
UNIQUE(namespace, key)
|
|
||||||
);
|
|
||||||
```
|
|
||||||
|
|
||||||
### agent_messages
|
|
||||||
|
|
||||||
```sql
|
|
||||||
CREATE TABLE agent_messages (
|
|
||||||
id UUID PRIMARY KEY,
|
|
||||||
sender VARCHAR(50) NOT NULL,
|
|
||||||
receiver VARCHAR(50) NOT NULL,
|
|
||||||
message_type VARCHAR(50) NOT NULL,
|
|
||||||
payload JSONB NOT NULL,
|
|
||||||
priority INTEGER DEFAULT 1,
|
|
||||||
correlation_id UUID,
|
|
||||||
created_at TIMESTAMPTZ DEFAULT NOW()
|
|
||||||
);
|
|
||||||
```
|
|
||||||
|
|
||||||
## Integration
|
|
||||||
|
|
||||||
### Mit Voice-Service
|
|
||||||
|
|
||||||
```python
|
|
||||||
from services.enhanced_task_orchestrator import EnhancedTaskOrchestrator
|
|
||||||
|
|
||||||
orchestrator = EnhancedTaskOrchestrator(
|
|
||||||
redis_client=redis,
|
|
||||||
db_pool=pg_pool
|
|
||||||
)
|
|
||||||
|
|
||||||
await orchestrator.start()
|
|
||||||
|
|
||||||
# Session fuer Voice-Interaktion
|
|
||||||
session = await orchestrator.create_session(
|
|
||||||
voice_session_id="voice-123",
|
|
||||||
user_id="teacher-1"
|
|
||||||
)
|
|
||||||
|
|
||||||
# Task verarbeiten (nutzt Multi-Agent wenn noetig)
|
|
||||||
await orchestrator.process_task(task)
|
|
||||||
```
|
|
||||||
|
|
||||||
### Mit BQAS
|
|
||||||
|
|
||||||
```python
|
|
||||||
from bqas.quality_judge_agent import QualityJudgeAgent
|
|
||||||
|
|
||||||
judge = QualityJudgeAgent(
|
|
||||||
message_bus=bus,
|
|
||||||
memory_store=memory
|
|
||||||
)
|
|
||||||
|
|
||||||
await judge.start()
|
|
||||||
|
|
||||||
# Direkte Evaluation
|
|
||||||
result = await judge.evaluate(
|
|
||||||
response="Der Satz des Pythagoras...",
|
|
||||||
task_type="learning_math",
|
|
||||||
context={"user_input": "Was ist Pythagoras?"}
|
|
||||||
)
|
|
||||||
|
|
||||||
if result["verdict"] == "production_ready":
|
|
||||||
# Response ist OK
|
|
||||||
pass
|
|
||||||
```
|
|
||||||
|
|
||||||
## Tests
|
|
||||||
|
|
||||||
```bash
|
|
||||||
# In agent-core Verzeichnis
|
|
||||||
cd agent-core
|
|
||||||
|
|
||||||
# Alle Tests ausfuehren
|
|
||||||
pytest -v
|
|
||||||
|
|
||||||
# Mit Coverage
|
|
||||||
pytest --cov=. --cov-report=html
|
|
||||||
|
|
||||||
# Einzelnes Test-Modul
|
|
||||||
pytest tests/test_session_manager.py -v
|
|
||||||
|
|
||||||
# Async-Tests
|
|
||||||
pytest tests/test_message_bus.py -v
|
|
||||||
```
|
|
||||||
|
|
||||||
## Metriken
|
|
||||||
|
|
||||||
Das Agent-Core exportiert folgende Metriken:
|
|
||||||
|
|
||||||
| Metrik | Beschreibung |
|
|
||||||
|--------|--------------|
|
|
||||||
| `agent_session_duration_seconds` | Dauer von Agent-Sessions |
|
|
||||||
| `agent_heartbeat_delay_seconds` | Zeit seit letztem Heartbeat |
|
|
||||||
| `agent_message_latency_ms` | Latenz der Inter-Agent Kommunikation |
|
|
||||||
| `agent_memory_access_total` | Memory-Zugriffe pro Agent |
|
|
||||||
| `agent_error_total` | Fehler pro Agent-Typ |
|
|
||||||
|
|
||||||
## Naechste Schritte
|
|
||||||
|
|
||||||
1. **Migration ausfuehren**: `psql -f backend/migrations/add_agent_core_tables.sql`
|
|
||||||
2. **Voice-Service erweitern**: Enhanced Orchestrator aktivieren
|
|
||||||
3. **BQAS integrieren**: Quality Judge Agent starten
|
|
||||||
4. **Monitoring aufsetzen**: Metriken in Grafana integrieren
|
|
||||||
|
|||||||
@@ -1,97 +1,10 @@
|
|||||||
# AI Compliance SDK
|
# AI Compliance SDK
|
||||||
|
|
||||||
Das AI Compliance SDK ist ein Go-basierter Service zur Compliance-Bewertung von KI-Anwendungsfällen.
|
!!! info "Verschoben nach breakpilot-compliance"
|
||||||
|
Das AI Compliance SDK gehoert zum **breakpilot-compliance** Projekt (Team B).
|
||||||
## Übersicht
|
|
||||||
|
Die aktuelle Dokumentation befindet sich in der [Compliance MkDocs-Instanz](http://macmini:8011/services/ai-compliance-sdk/).
|
||||||
| Eigenschaft | Wert |
|
|
||||||
|-------------|------|
|
**Container:** `bp-compliance-ai-sdk`
|
||||||
| **Port** | 8090 |
|
**Ports:** 8090 (intern), 8093 (via Nginx)
|
||||||
| **Framework** | Go (Gin) |
|
**Repo:** `breakpilot-compliance/ai-compliance-sdk/`
|
||||||
| **Datenbank** | PostgreSQL |
|
|
||||||
| **Vector DB** | Qdrant (Legal RAG) |
|
|
||||||
|
|
||||||
## Kernkomponenten
|
|
||||||
|
|
||||||
```
|
|
||||||
┌─────────────────────────────────────────────────────────────────────────────┐
|
|
||||||
│ UCCA System │
|
|
||||||
├─────────────────────────────────────────────────────────────────────────────┤
|
|
||||||
│ │
|
|
||||||
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
|
|
||||||
│ │ Frontend │───>│ SDK API │───>│ PostgreSQL │ │
|
|
||||||
│ │ (Next.js) │ │ (Go) │ │ Database │ │
|
|
||||||
│ └──────────────┘ └──────┬───────┘ └──────────────┘ │
|
|
||||||
│ │ │
|
|
||||||
│ ┌────────────────────┼────────────────────┐ │
|
|
||||||
│ │ │ │ │
|
|
||||||
│ ▼ ▼ ▼ │
|
|
||||||
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
|
|
||||||
│ │ Policy │ │ Escalation │ │ Legal RAG │ │
|
|
||||||
│ │ Engine │ │ Workflow │ │ (Qdrant) │ │
|
|
||||||
│ │ (45 Regeln) │ │ (E0-E3) │ │ 2,274 Chunks │ │
|
|
||||||
│ └──────────────┘ └──────────────┘ └──────────────┘ │
|
|
||||||
│ │
|
|
||||||
└─────────────────────────────────────────────────────────────────────────────┘
|
|
||||||
```
|
|
||||||
|
|
||||||
## Features
|
|
||||||
|
|
||||||
- **UCCA (Use-Case Compliance Advisor)**: Deterministische Bewertung von KI-Anwendungsfällen
|
|
||||||
- **Policy Engine**: 45 regelbasierte Compliance-Prüfungen
|
|
||||||
- **License Policy Engine**: Standards/Normen-Compliance (DIN, ISO, VDI)
|
|
||||||
- **Legal RAG**: Semantische Suche in EU-Verordnungen (DSGVO, AI Act, NIS2)
|
|
||||||
- **Eskalations-Workflow**: E0-E3 Stufen mit Human-in-the-Loop
|
|
||||||
- **Wizard & Legal Assistant**: Geführte Eingabe mit Rechtsassistent
|
|
||||||
- **Generic Obligations Framework**: NIS2, DSGVO, AI Act Module
|
|
||||||
|
|
||||||
## Kernprinzip
|
|
||||||
|
|
||||||
> **"LLM ist NICHT die Quelle der Wahrheit. Wahrheit = Regeln + Evidenz. LLM = Übersetzer + Subsumptionshelfer"**
|
|
||||||
|
|
||||||
Das System folgt einem strikten **Human-in-the-Loop** Ansatz:
|
|
||||||
|
|
||||||
1. **Deterministische Regeln** treffen alle Compliance-Entscheidungen
|
|
||||||
2. **LLM** erklärt nur Ergebnisse, überschreibt nie BLOCK-Entscheidungen
|
|
||||||
3. **Menschen** (DSB, Legal) treffen finale Entscheidungen bei kritischen Fällen
|
|
||||||
|
|
||||||
## API-Endpunkte
|
|
||||||
|
|
||||||
### Assessment
|
|
||||||
|
|
||||||
| Method | Endpoint | Beschreibung |
|
|
||||||
|--------|----------|--------------|
|
|
||||||
| POST | `/sdk/v1/ucca/assess` | Assessment erstellen |
|
|
||||||
| GET | `/sdk/v1/ucca/assessments` | Assessments auflisten |
|
|
||||||
| GET | `/sdk/v1/ucca/assessments/:id` | Assessment abrufen |
|
|
||||||
| POST | `/sdk/v1/ucca/assessments/:id/explain` | LLM-Erklärung generieren |
|
|
||||||
|
|
||||||
### Eskalation
|
|
||||||
|
|
||||||
| Method | Endpoint | Beschreibung |
|
|
||||||
|--------|----------|--------------|
|
|
||||||
| GET | `/sdk/v1/ucca/escalations` | Eskalationen auflisten |
|
|
||||||
| POST | `/sdk/v1/ucca/escalations/:id/decide` | Entscheidung treffen |
|
|
||||||
|
|
||||||
### Obligations Framework
|
|
||||||
|
|
||||||
| Method | Endpoint | Beschreibung |
|
|
||||||
|--------|----------|--------------|
|
|
||||||
| POST | `/sdk/v1/ucca/obligations/assess` | Pflichten-Assessment |
|
|
||||||
| POST | `/sdk/v1/ucca/obligations/export/memo` | PDF-Export |
|
|
||||||
|
|
||||||
## Weiterführende Dokumentation
|
|
||||||
|
|
||||||
- [Architektur](./ARCHITECTURE.md) - Detaillierte Systemarchitektur
|
|
||||||
- [Entwickler-Guide](./DEVELOPER.md) - Entwickler-Dokumentation
|
|
||||||
- [Auditor-Dokumentation](./AUDITOR_DOCUMENTATION.md) - Dokumentation für externe Auditoren
|
|
||||||
|
|
||||||
## Tests
|
|
||||||
|
|
||||||
```bash
|
|
||||||
cd ai-compliance-sdk
|
|
||||||
go test -v ./...
|
|
||||||
|
|
||||||
# Mit Coverage
|
|
||||||
go test -cover ./...
|
|
||||||
```
|
|
||||||
|
|||||||
@@ -1,215 +1,8 @@
|
|||||||
# KI-Daten-Pipeline
|
# KI-Daten-Pipeline
|
||||||
|
|
||||||
Die KI-Daten-Pipeline ist ein zusammenhaengendes System aus drei Modulen, das den Datenfluss von der Erfassung bis zur semantischen Suche abbildet.
|
!!! info "Verschoben nach breakpilot-lehrer"
|
||||||
|
Die KI-Daten-Pipeline gehoert zum **breakpilot-lehrer** Projekt (Team A).
|
||||||
## Uebersicht
|
|
||||||
|
Die aktuelle Dokumentation befindet sich in der [Lehrer MkDocs-Instanz](http://macmini:8010/services/ki-daten-pipeline/).
|
||||||
```mermaid
|
|
||||||
flowchart LR
|
**Repo:** `breakpilot-lehrer/`
|
||||||
subgraph OCR["OCR-Labeling"]
|
|
||||||
A[Klausur-Scans] --> B[OCR Erkennung]
|
|
||||||
B --> C[Ground Truth Labels]
|
|
||||||
end
|
|
||||||
|
|
||||||
subgraph RAG["RAG Pipeline"]
|
|
||||||
D[PDF Dokumente] --> E[Text-Extraktion]
|
|
||||||
E --> F[Chunking]
|
|
||||||
F --> G[Embedding]
|
|
||||||
end
|
|
||||||
|
|
||||||
subgraph SEARCH["Daten & RAG"]
|
|
||||||
H[Qdrant Collections]
|
|
||||||
I[Semantische Suche]
|
|
||||||
end
|
|
||||||
|
|
||||||
C -->|Export| D
|
|
||||||
G -->|Indexierung| H
|
|
||||||
H --> I
|
|
||||||
I -->|Ergebnisse| J[Klausur-Korrektur]
|
|
||||||
```
|
|
||||||
|
|
||||||
## Module
|
|
||||||
|
|
||||||
| Modul | Pfad | Funktion | Backend |
|
|
||||||
|-------|------|----------|---------|
|
|
||||||
| **OCR-Labeling** | `/ai/ocr-labeling` | Ground Truth fuer Handschrift-OCR | klausur-service:8086 |
|
|
||||||
| **RAG Pipeline** | `/ai/rag-pipeline` | Dokument-Indexierung | klausur-service:8086 |
|
|
||||||
| **Daten & RAG** | `/ai/rag` | Vektor-Suche & Collection-Mapping | klausur-service:8086 |
|
|
||||||
|
|
||||||
## Datenfluss
|
|
||||||
|
|
||||||
### 1. OCR-Labeling (Eingabe)
|
|
||||||
|
|
||||||
Das OCR-Labeling-Modul erfasst Ground Truth Daten fuer das Training von Handschrift-Erkennungsmodellen:
|
|
||||||
|
|
||||||
- **Upload**: Klausur-Scans (PDF/Bilder) werden hochgeladen
|
|
||||||
- **OCR-Verarbeitung**: Mehrere OCR-Modelle erkennen den Text
|
|
||||||
- `llama3.2-vision:11b` - Vision LLM (beste Qualitaet)
|
|
||||||
- `trocr` - Microsoft Transformer (schnell)
|
|
||||||
- `paddleocr` - PaddleOCR + LLM (4x schneller)
|
|
||||||
- `donut` - Document Understanding (strukturiert)
|
|
||||||
- **Labeling**: Manuelles Pruefen und Korrigieren der OCR-Ergebnisse
|
|
||||||
- **Export**: Gelabelte Daten koennen exportiert werden fuer:
|
|
||||||
- TrOCR Fine-Tuning
|
|
||||||
- Llama Vision Fine-Tuning
|
|
||||||
- Generic JSON
|
|
||||||
|
|
||||||
### 2. RAG Pipeline (Verarbeitung)
|
|
||||||
|
|
||||||
Die RAG Pipeline verarbeitet Dokumente und macht sie suchbar:
|
|
||||||
|
|
||||||
```mermaid
|
|
||||||
flowchart TD
|
|
||||||
A[Datenquellen] --> B[OCR/Text-Extraktion]
|
|
||||||
B --> C[Chunking]
|
|
||||||
C --> D[Embedding]
|
|
||||||
D --> E[Qdrant Indexierung]
|
|
||||||
|
|
||||||
subgraph sources["Datenquellen"]
|
|
||||||
S1[NiBiS PDFs]
|
|
||||||
S2[Eigene EH]
|
|
||||||
S3[Rechtskorpus]
|
|
||||||
S4[Schulordnungen]
|
|
||||||
end
|
|
||||||
```
|
|
||||||
|
|
||||||
**Verarbeitungsschritte:**
|
|
||||||
|
|
||||||
1. **Dokumentenextraktion**: PDFs und Bilder werden per OCR in Text umgewandelt
|
|
||||||
2. **Chunking**: Lange Texte werden in Abschnitte aufgeteilt
|
|
||||||
- Chunk-Groesse: 1000 Zeichen
|
|
||||||
- Ueberlappung: 200 Zeichen
|
|
||||||
3. **Embedding**: Jeder Chunk wird in einen Vektor umgewandelt
|
|
||||||
- Modell: `text-embedding-3-small`
|
|
||||||
- Dimensionen: 1536
|
|
||||||
4. **Indexierung**: Vektoren werden in Qdrant gespeichert
|
|
||||||
|
|
||||||
### 3. Daten & RAG (Ausgabe)
|
|
||||||
|
|
||||||
Das Daten & RAG Modul ermoeglicht die Verwaltung und Suche:
|
|
||||||
|
|
||||||
- **Collection-Uebersicht**: Status aller Qdrant Collections
|
|
||||||
- **Semantische Suche**: Fragen werden in Vektoren umgewandelt und aehnliche Dokumente gefunden
|
|
||||||
- **Regulierungs-Mapping**: Zeigt welche Regulierungen indexiert sind
|
|
||||||
|
|
||||||
## Qdrant Collections
|
|
||||||
|
|
||||||
| Collection | Inhalt | Status |
|
|
||||||
|------------|--------|--------|
|
|
||||||
| `bp_nibis_eh` | Offizielle NiBiS Erwartungshorizonte | Aktiv |
|
|
||||||
| `bp_eh` | Benutzerdefinierte Erwartungshorizonte | Aktiv |
|
|
||||||
| `bp_schulordnungen` | Schulordnungen aller Bundeslaender | In Arbeit |
|
|
||||||
| `bp_legal_corpus` | Rechtskorpus (DSGVO, AI Act, BSI, etc.) | Aktiv |
|
|
||||||
|
|
||||||
## Technische Architektur
|
|
||||||
|
|
||||||
### Services
|
|
||||||
|
|
||||||
```mermaid
|
|
||||||
graph TB
|
|
||||||
subgraph Frontend["Admin-v2 (Next.js)"]
|
|
||||||
F1["/ai/ocr-labeling"]
|
|
||||||
F2["/ai/rag-pipeline"]
|
|
||||||
F3["/ai/rag"]
|
|
||||||
end
|
|
||||||
|
|
||||||
subgraph Backend["klausur-service (Python)"]
|
|
||||||
B1[OCR Endpoints]
|
|
||||||
B2[Indexierungs-Jobs]
|
|
||||||
B3[Such-API]
|
|
||||||
end
|
|
||||||
|
|
||||||
subgraph Storage["Datenbanken"]
|
|
||||||
D1[(PostgreSQL)]
|
|
||||||
D2[(Qdrant)]
|
|
||||||
D3[(MinIO)]
|
|
||||||
end
|
|
||||||
|
|
||||||
F1 --> B1
|
|
||||||
F2 --> B2
|
|
||||||
F3 --> B3
|
|
||||||
|
|
||||||
B1 --> D1
|
|
||||||
B1 --> D3
|
|
||||||
B2 --> D2
|
|
||||||
B3 --> D2
|
|
||||||
```
|
|
||||||
|
|
||||||
### Backend-Endpunkte
|
|
||||||
|
|
||||||
#### OCR-Labeling (`/api/v1/ocr-label/`)
|
|
||||||
|
|
||||||
| Endpoint | Methode | Beschreibung |
|
|
||||||
|----------|---------|--------------|
|
|
||||||
| `/sessions` | GET/POST | Session-Verwaltung |
|
|
||||||
| `/sessions/{id}/upload` | POST | Bilder hochladen |
|
|
||||||
| `/queue` | GET | Labeling-Queue |
|
|
||||||
| `/confirm` | POST | OCR bestaetigen |
|
|
||||||
| `/correct` | POST | OCR korrigieren |
|
|
||||||
| `/skip` | POST | Item ueberspringen |
|
|
||||||
| `/stats` | GET | Statistiken |
|
|
||||||
| `/export` | POST | Trainingsdaten exportieren |
|
|
||||||
|
|
||||||
#### RAG Pipeline (`/api/ai/rag-pipeline`)
|
|
||||||
|
|
||||||
| Action | Beschreibung |
|
|
||||||
|--------|--------------|
|
|
||||||
| `jobs` | Indexierungs-Jobs auflisten |
|
|
||||||
| `dataset-stats` | Datensatz-Statistiken |
|
|
||||||
| `create-job` | Neue Indexierung starten |
|
|
||||||
| `pause` | Job pausieren |
|
|
||||||
| `resume` | Job fortsetzen |
|
|
||||||
| `cancel` | Job abbrechen |
|
|
||||||
|
|
||||||
#### Legal Corpus (`/api/legal-corpus/`)
|
|
||||||
|
|
||||||
| Endpoint | Beschreibung |
|
|
||||||
|----------|--------------|
|
|
||||||
| `/status` | Collection-Status |
|
|
||||||
| `/search` | Semantische Suche |
|
|
||||||
| `/ingest` | Dokumente indexieren |
|
|
||||||
|
|
||||||
## Integration mit Klausur-Korrektur
|
|
||||||
|
|
||||||
Die KI-Daten-Pipeline liefert Erwartungshorizont-Vorschlaege fuer die Klausur-Korrektur:
|
|
||||||
|
|
||||||
```mermaid
|
|
||||||
sequenceDiagram
|
|
||||||
participant L as Lehrer
|
|
||||||
participant K as Klausur-Korrektur
|
|
||||||
participant R as RAG-Suche
|
|
||||||
participant Q as Qdrant
|
|
||||||
|
|
||||||
L->>K: Schueler-Antwort pruefen
|
|
||||||
K->>R: EH-Vorschlaege laden
|
|
||||||
R->>Q: Semantische Suche
|
|
||||||
Q->>R: Top-k Chunks
|
|
||||||
R->>K: Relevante EH-Passagen
|
|
||||||
K->>L: Bewertungsvorschlaege
|
|
||||||
```
|
|
||||||
|
|
||||||
## Deployment
|
|
||||||
|
|
||||||
Die Module werden als Teil des admin-v2 Containers deployed:
|
|
||||||
|
|
||||||
```bash
|
|
||||||
# 1. Sync
|
|
||||||
rsync -avz --delete --exclude 'node_modules' --exclude '.next' --exclude '.git' \
|
|
||||||
/Users/benjaminadmin/Projekte/breakpilot-pwa/admin-v2/ \
|
|
||||||
macmini:/Users/benjaminadmin/Projekte/breakpilot-pwa/admin-v2/
|
|
||||||
|
|
||||||
# 2. Build & Deploy
|
|
||||||
ssh macmini "/usr/local/bin/docker compose \
|
|
||||||
-f /Users/benjaminadmin/Projekte/breakpilot-pwa/docker-compose.yml \
|
|
||||||
build --no-cache admin-v2 && \
|
|
||||||
/usr/local/bin/docker compose \
|
|
||||||
-f /Users/benjaminadmin/Projekte/breakpilot-pwa/docker-compose.yml \
|
|
||||||
up -d admin-v2"
|
|
||||||
```
|
|
||||||
|
|
||||||
## Verwandte Dokumentation
|
|
||||||
|
|
||||||
- [OCR Labeling Spezifikation](../klausur-service/OCR-Labeling-Spec.md)
|
|
||||||
- [RAG Admin Spezifikation](../klausur-service/RAG-Admin-Spec.md)
|
|
||||||
- [NiBiS Ingestion Pipeline](../klausur-service/NiBiS-Ingestion-Pipeline.md)
|
|
||||||
- [Multi-Agent Architektur](../../architecture/multi-agent.md)
|
|
||||||
|
|||||||
@@ -1,173 +1,10 @@
|
|||||||
# Klausur-Service
|
# Klausur Service
|
||||||
|
|
||||||
Der Klausur-Service ist ein FastAPI-basierter Microservice fuer KI-gestuetzte Abitur-Klausurkorrektur.
|
!!! info "Verschoben nach breakpilot-lehrer"
|
||||||
|
Der Klausur Service gehoert zum **breakpilot-lehrer** Projekt (Team A).
|
||||||
## Uebersicht
|
|
||||||
|
Die aktuelle Dokumentation befindet sich in der [Lehrer MkDocs-Instanz](http://macmini:8010/services/klausur-service/).
|
||||||
| Eigenschaft | Wert |
|
|
||||||
|-------------|------|
|
**Container:** `bp-lehrer-klausur-service`
|
||||||
| **Port** | 8086 |
|
**Port:** 8086
|
||||||
| **Framework** | FastAPI (Python) |
|
**Repo:** `breakpilot-lehrer/klausur-service/`
|
||||||
| **Datenbank** | PostgreSQL + Qdrant (Vektor-DB) |
|
|
||||||
| **Speicher** | MinIO (Datei-Storage) |
|
|
||||||
|
|
||||||
## Features
|
|
||||||
|
|
||||||
- **OCR-Erkennung**: Automatische Texterkennung aus gescannten Klausuren
|
|
||||||
- **KI-Bewertung**: Automatische Bewertungsvorschlaege basierend auf Erwartungshorizont
|
|
||||||
- **BYOEH**: Bring-Your-Own-Expectation-Horizon mit Client-seitiger Verschluesselung
|
|
||||||
- **Fairness-Analyse**: Statistische Analyse der Bewertungskonsistenz
|
|
||||||
- **PDF-Export**: Gutachten und Notenuebersichten als PDF
|
|
||||||
- **Zweitkorrektur**: Vollstaendiger Workflow fuer Erst-, Zweit- und Drittkorrektur
|
|
||||||
|
|
||||||
## Architektur
|
|
||||||
|
|
||||||
```
|
|
||||||
┌─────────────────────────────────────────────────────────────┐
|
|
||||||
│ Frontend (Next.js) │
|
|
||||||
│ /website/app/admin/klausur-korrektur/ │
|
|
||||||
│ - Klausur-Liste │
|
|
||||||
│ - Studenten-Liste │
|
|
||||||
│ - Korrektur-Workspace (2/3-1/3 Layout) │
|
|
||||||
│ - Fairness-Dashboard │
|
|
||||||
└─────────────────────────────────────────────────────────────┘
|
|
||||||
│
|
|
||||||
▼
|
|
||||||
┌─────────────────────────────────────────────────────────────┐
|
|
||||||
│ klausur-service (FastAPI) │
|
|
||||||
│ Port 8086 - /klausur-service/backend/main.py │
|
|
||||||
│ - Klausur CRUD (/api/v1/klausuren) │
|
|
||||||
│ - Student Work (/api/v1/students) │
|
|
||||||
│ - Annotations (/api/v1/annotations) │
|
|
||||||
│ - BYOEH (/api/v1/eh) │
|
|
||||||
│ - PDF Export │
|
|
||||||
└─────────────────────────────────────────────────────────────┘
|
|
||||||
│
|
|
||||||
▼
|
|
||||||
┌─────────────────────────────────────────────────────────────┐
|
|
||||||
│ Infrastruktur │
|
|
||||||
│ - Qdrant (Vektor-DB fuer RAG) │
|
|
||||||
│ - MinIO (Datei-Storage) │
|
|
||||||
│ - PostgreSQL (Metadaten) │
|
|
||||||
│ - Embedding-Service (Port 8087) │
|
|
||||||
└─────────────────────────────────────────────────────────────┘
|
|
||||||
```
|
|
||||||
|
|
||||||
## API Endpoints
|
|
||||||
|
|
||||||
### Klausur-Verwaltung
|
|
||||||
|
|
||||||
| Method | Endpoint | Beschreibung |
|
|
||||||
|--------|----------|--------------|
|
|
||||||
| GET | `/api/v1/klausuren` | Liste aller Klausuren |
|
|
||||||
| POST | `/api/v1/klausuren` | Neue Klausur erstellen |
|
|
||||||
| GET | `/api/v1/klausuren/{id}` | Klausur-Details |
|
|
||||||
| DELETE | `/api/v1/klausuren/{id}` | Klausur loeschen |
|
|
||||||
|
|
||||||
### Studenten-Arbeiten
|
|
||||||
|
|
||||||
| Method | Endpoint | Beschreibung |
|
|
||||||
|--------|----------|--------------|
|
|
||||||
| POST | `/api/v1/klausuren/{id}/students` | Arbeit hochladen |
|
|
||||||
| GET | `/api/v1/klausuren/{id}/students` | Studenten-Liste |
|
|
||||||
| GET | `/api/v1/students/{id}` | Einzelne Arbeit |
|
|
||||||
| PUT | `/api/v1/students/{id}/criteria` | Kriterien bewerten |
|
|
||||||
| PUT | `/api/v1/students/{id}/gutachten` | Gutachten speichern |
|
|
||||||
|
|
||||||
### KI-Funktionen
|
|
||||||
|
|
||||||
| Method | Endpoint | Beschreibung |
|
|
||||||
|--------|----------|--------------|
|
|
||||||
| POST | `/api/v1/students/{id}/gutachten/generate` | Gutachten generieren |
|
|
||||||
| GET | `/api/v1/klausuren/{id}/fairness` | Fairness-Analyse |
|
|
||||||
| POST | `/api/v1/students/{id}/eh-suggestions` | EH-Vorschlaege via RAG |
|
|
||||||
|
|
||||||
### PDF-Export
|
|
||||||
|
|
||||||
| Method | Endpoint | Beschreibung |
|
|
||||||
|--------|----------|--------------|
|
|
||||||
| GET | `/api/v1/students/{id}/export/gutachten` | Einzelgutachten PDF |
|
|
||||||
| GET | `/api/v1/students/{id}/export/annotations` | Anmerkungen PDF |
|
|
||||||
| GET | `/api/v1/klausuren/{id}/export/overview` | Notenuebersicht PDF |
|
|
||||||
| GET | `/api/v1/klausuren/{id}/export/all-gutachten` | Alle Gutachten PDF |
|
|
||||||
|
|
||||||
## Notensystem
|
|
||||||
|
|
||||||
Das System verwendet das deutsche 15-Punkte-System fuer Abiturklausuren:
|
|
||||||
|
|
||||||
| Punkte | Prozent | Note |
|
|
||||||
|--------|---------|------|
|
|
||||||
| 15 | >= 95% | 1+ |
|
|
||||||
| 14 | >= 90% | 1 |
|
|
||||||
| 13 | >= 85% | 1- |
|
|
||||||
| 12 | >= 80% | 2+ |
|
|
||||||
| 11 | >= 75% | 2 |
|
|
||||||
| 10 | >= 70% | 2- |
|
|
||||||
| 9 | >= 65% | 3+ |
|
|
||||||
| 8 | >= 60% | 3 |
|
|
||||||
| 7 | >= 55% | 3- |
|
|
||||||
| 6 | >= 50% | 4+ |
|
|
||||||
| 5 | >= 45% | 4 |
|
|
||||||
| 4 | >= 40% | 4- |
|
|
||||||
| 3 | >= 33% | 5+ |
|
|
||||||
| 2 | >= 27% | 5 |
|
|
||||||
| 1 | >= 20% | 5- |
|
|
||||||
| 0 | < 20% | 6 |
|
|
||||||
|
|
||||||
## Bewertungskriterien
|
|
||||||
|
|
||||||
| Kriterium | Gewicht | Beschreibung |
|
|
||||||
|-----------|---------|--------------|
|
|
||||||
| Rechtschreibung | 15% | Orthografie |
|
|
||||||
| Grammatik | 15% | Grammatik & Syntax |
|
|
||||||
| Inhalt | 40% | Inhaltliche Qualitaet |
|
|
||||||
| Struktur | 15% | Aufbau & Gliederung |
|
|
||||||
| Stil | 15% | Ausdruck & Stil |
|
|
||||||
|
|
||||||
## Verzeichnisstruktur
|
|
||||||
|
|
||||||
```
|
|
||||||
klausur-service/
|
|
||||||
├── backend/
|
|
||||||
│ ├── main.py # API Endpoints + Datenmodelle
|
|
||||||
│ ├── qdrant_service.py # Vektor-Datenbank Operationen
|
|
||||||
│ ├── eh_pipeline.py # BYOEH Verarbeitung
|
|
||||||
│ ├── hybrid_search.py # Hybrid Search (BM25 + Semantic)
|
|
||||||
│ └── requirements.txt # Python Dependencies
|
|
||||||
├── frontend/
|
|
||||||
│ └── src/
|
|
||||||
│ ├── components/ # React Komponenten
|
|
||||||
│ ├── pages/ # Seiten
|
|
||||||
│ └── services/ # API Client
|
|
||||||
└── docs/
|
|
||||||
├── BYOEH-Architecture.md
|
|
||||||
└── BYOEH-Developer-Guide.md
|
|
||||||
```
|
|
||||||
|
|
||||||
## Konfiguration
|
|
||||||
|
|
||||||
### Umgebungsvariablen
|
|
||||||
|
|
||||||
```env
|
|
||||||
# Klausur-Service
|
|
||||||
KLAUSUR_SERVICE_PORT=8086
|
|
||||||
QDRANT_URL=http://qdrant:6333
|
|
||||||
MINIO_ENDPOINT=minio:9000
|
|
||||||
MINIO_ACCESS_KEY=...
|
|
||||||
MINIO_SECRET_KEY=...
|
|
||||||
|
|
||||||
# Embedding-Service
|
|
||||||
EMBEDDING_SERVICE_URL=http://embedding:8087
|
|
||||||
OPENAI_API_KEY=sk-...
|
|
||||||
|
|
||||||
# BYOEH
|
|
||||||
BYOEH_ENCRYPTION_ENABLED=true
|
|
||||||
EH_UPLOAD_DIR=/app/eh-uploads
|
|
||||||
```
|
|
||||||
|
|
||||||
## Weiterführende Dokumentation
|
|
||||||
|
|
||||||
- [BYOEH Architektur](./BYOEH-Architecture.md) - Client-seitige Verschluesselung
|
|
||||||
- [OCR Compare](./OCR-Compare.md) - Block Review Feature fuer OCR-Vergleich
|
|
||||||
- [Zeugnis-System](../../architecture/zeugnis-system.md) - Zeugniserstellung
|
|
||||||
- [Backend API](../../api/backend-api.md) - Allgemeine API-Dokumentation
|
|
||||||
|
|||||||
@@ -1,160 +1,10 @@
|
|||||||
# Voice Service
|
# Voice Service
|
||||||
|
|
||||||
Der Voice Service ist eine Voice-First Interface für die Breakpilot-Plattform mit DSGVO-konformem Design.
|
!!! info "Verschoben nach breakpilot-lehrer"
|
||||||
|
Der Voice Service gehoert zum **breakpilot-lehrer** Projekt (Team A).
|
||||||
## Übersicht
|
|
||||||
|
Die aktuelle Dokumentation befindet sich in der [Lehrer MkDocs-Instanz](http://macmini:8010/services/voice-service/).
|
||||||
| Eigenschaft | Wert |
|
|
||||||
|-------------|------|
|
**Container:** `bp-lehrer-voice-service`
|
||||||
| **Port** | 8082 |
|
**Port:** 8091
|
||||||
| **Framework** | FastAPI (Python) |
|
**Repo:** `breakpilot-lehrer/voice-service/`
|
||||||
| **Streaming** | WebSocket |
|
|
||||||
| **DSGVO** | Privacy-by-Design |
|
|
||||||
|
|
||||||
## Architektur
|
|
||||||
|
|
||||||
```
|
|
||||||
┌─────────────────────────────────────────────────────────────────┐
|
|
||||||
│ Voice Service (Port 8082) │
|
|
||||||
├─────────────────────────────────────────────────────────────────┤
|
|
||||||
│ │
|
|
||||||
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
|
|
||||||
│ │ Sessions │───>│ Task │───>│ BQAS │ │
|
|
||||||
│ │ API │ │ Orchestrator │ │ (Quality) │ │
|
|
||||||
│ └──────────────┘ └──────────────┘ └──────────────┘ │
|
|
||||||
│ │ │
|
|
||||||
│ ┌────────────────────┼────────────────────┐ │
|
|
||||||
│ │ │ │ │
|
|
||||||
│ ▼ ▼ ▼ │
|
|
||||||
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
|
|
||||||
│ │ WebSocket │ │ Encryption │ │ Logging │ │
|
|
||||||
│ │ Streaming │ │ Service │ │ (structlog) │ │
|
|
||||||
│ └──────────────┘ └──────────────┘ └──────────────┘ │
|
|
||||||
│ │
|
|
||||||
└─────────────────────────────────────────────────────────────────┘
|
|
||||||
```
|
|
||||||
|
|
||||||
## Kernkomponenten
|
|
||||||
|
|
||||||
### PersonaPlex + TaskOrchestrator
|
|
||||||
|
|
||||||
- Voice-first Interface für Breakpilot
|
|
||||||
- Real-time Voice Processing
|
|
||||||
- Multi-Agent Integration
|
|
||||||
|
|
||||||
### DSGVO-Compliance (Privacy-by-Design)
|
|
||||||
|
|
||||||
| Feature | Beschreibung |
|
|
||||||
|---------|--------------|
|
|
||||||
| **Keine Audio-Persistenz** | Nur RAM-basiert, keine dauerhafte Speicherung |
|
|
||||||
| **Namespace-Verschlüsselung** | Schlüssel nur auf Lehrer-Gerät |
|
|
||||||
| **TTL-basierte Löschung** | Automatische Datenlöschung nach Zeitablauf |
|
|
||||||
| **Transcript-Verschlüsselung** | Verschlüsselte Transkripte |
|
|
||||||
|
|
||||||
## API-Endpunkte
|
|
||||||
|
|
||||||
### Sessions
|
|
||||||
|
|
||||||
| Method | Endpoint | Beschreibung |
|
|
||||||
|--------|----------|--------------|
|
|
||||||
| POST | `/api/v1/sessions` | Session erstellen |
|
|
||||||
| GET | `/api/v1/sessions/:id` | Session abrufen |
|
|
||||||
| DELETE | `/api/v1/sessions/:id` | Session beenden |
|
|
||||||
|
|
||||||
### Task Orchestration
|
|
||||||
|
|
||||||
| Method | Endpoint | Beschreibung |
|
|
||||||
|--------|----------|--------------|
|
|
||||||
| POST | `/api/v1/tasks` | Task erstellen |
|
|
||||||
| GET | `/api/v1/tasks/:id` | Task-Status abrufen |
|
|
||||||
|
|
||||||
### BQAS (Quality Assessment)
|
|
||||||
|
|
||||||
| Method | Endpoint | Beschreibung |
|
|
||||||
|--------|----------|--------------|
|
|
||||||
| POST | `/api/v1/bqas/evaluate` | Qualitätsbewertung |
|
|
||||||
| GET | `/api/v1/bqas/metrics` | Metriken abrufen |
|
|
||||||
|
|
||||||
### WebSocket
|
|
||||||
|
|
||||||
| Endpoint | Beschreibung |
|
|
||||||
|----------|--------------|
|
|
||||||
| `/ws/voice` | Real-time Voice Streaming |
|
|
||||||
|
|
||||||
### Health
|
|
||||||
|
|
||||||
| Method | Endpoint | Beschreibung |
|
|
||||||
|--------|----------|--------------|
|
|
||||||
| GET | `/health` | Health Check |
|
|
||||||
| GET | `/ready` | Readiness Check |
|
|
||||||
|
|
||||||
## Verzeichnisstruktur
|
|
||||||
|
|
||||||
```
|
|
||||||
voice-service/
|
|
||||||
├── main.py # FastAPI Application
|
|
||||||
├── config.py # Konfiguration
|
|
||||||
├── pyproject.toml # Projekt-Metadaten
|
|
||||||
├── requirements.txt # Dependencies
|
|
||||||
├── api/
|
|
||||||
│ ├── sessions.py # Session-Management
|
|
||||||
│ ├── streaming.py # WebSocket Voice Streaming
|
|
||||||
│ ├── tasks.py # Task Orchestration
|
|
||||||
│ └── bqas.py # Quality Assessment
|
|
||||||
├── services/
|
|
||||||
│ ├── task_orchestrator.py # Task-Routing
|
|
||||||
│ └── encryption.py # Verschlüsselung
|
|
||||||
├── bqas/
|
|
||||||
│ ├── judge.py # LLM Judge
|
|
||||||
│ └── quality_judge_agent.py # Agent-Integration
|
|
||||||
├── models/ # Datenmodelle
|
|
||||||
├── scripts/ # Utility-Scripts
|
|
||||||
└── tests/ # Test-Suite
|
|
||||||
```
|
|
||||||
|
|
||||||
## Konfiguration
|
|
||||||
|
|
||||||
```env
|
|
||||||
# .env
|
|
||||||
VOICE_SERVICE_PORT=8082
|
|
||||||
REDIS_URL=redis://localhost:6379
|
|
||||||
DATABASE_URL=postgresql://...
|
|
||||||
ENCRYPTION_KEY=...
|
|
||||||
TTL_MINUTES=60
|
|
||||||
```
|
|
||||||
|
|
||||||
## Entwicklung
|
|
||||||
|
|
||||||
```bash
|
|
||||||
# Dependencies installieren
|
|
||||||
cd voice-service
|
|
||||||
pip install -r requirements.txt
|
|
||||||
|
|
||||||
# Server starten
|
|
||||||
uvicorn main:app --reload --port 8082
|
|
||||||
|
|
||||||
# Tests ausführen
|
|
||||||
pytest -v
|
|
||||||
```
|
|
||||||
|
|
||||||
## Docker
|
|
||||||
|
|
||||||
Der Service läuft als Teil von docker-compose.yml:
|
|
||||||
|
|
||||||
```yaml
|
|
||||||
voice-service:
|
|
||||||
build:
|
|
||||||
context: ./voice-service
|
|
||||||
ports:
|
|
||||||
- "8082:8082"
|
|
||||||
environment:
|
|
||||||
- REDIS_URL=redis://valkey:6379
|
|
||||||
depends_on:
|
|
||||||
- valkey
|
|
||||||
- postgres
|
|
||||||
```
|
|
||||||
|
|
||||||
## Weiterführende Dokumentation
|
|
||||||
|
|
||||||
- [Multi-Agent Architektur](../../architecture/multi-agent.md)
|
|
||||||
- [BQAS Quality System](../../architecture/bqas.md)
|
|
||||||
|
|||||||
Reference in New Issue
Block a user