version: '3.8'

services:
  # Redis cache for translations
  redis:
    image: redis:7-alpine
    container_name: vibeon-translation-cache
    restart: unless-stopped
    ports:
      - "6379:6379"
    volumes:
      - redis-data:/data
    command: redis-server --appendonly yes --maxmemory 2gb --maxmemory-policy lru
    networks:
      - translation-net

  # Translation API server (multiple instances for load balancing)
  translation-api-1:
    build:
      context: .
      dockerfile: Dockerfile.ml
    container_name: vibeon-translation-api-1
    restart: unless-stopped
    ports:
      - "8081:8080"
    environment:
      - NODE_ENV=production
      - REDIS_URL=redis://redis:6379
      - MODEL_PATH=/models
      - WORKERS=4
      - CUDA_VISIBLE_DEVICES=0
    volumes:
      - ./models:/models:ro
      - ./logs:/logs
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    depends_on:
      - redis
    networks:
      - translation-net

  translation-api-2:
    build:
      context: .
      dockerfile: Dockerfile.ml
    container_name: vibeon-translation-api-2
    restart: unless-stopped
    ports:
      - "8082:8080"
    environment:
      - NODE_ENV=production
      - REDIS_URL=redis://redis:6379
      - MODEL_PATH=/models
      - WORKERS=4
      - CUDA_VISIBLE_DEVICES=1
    volumes:
      - ./models:/models:ro
      - ./logs:/logs
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    depends_on:
      - redis
    networks:
      - translation-net

  # Nginx load balancer
  nginx:
    image: nginx:alpine
    container_name: vibeon-translation-lb
    restart: unless-stopped
    ports:
      - "8080:80"
    volumes:
      - ./nginx.conf:/etc/nginx/nginx.conf:ro
    depends_on:
      - translation-api-1
      - translation-api-2
    networks:
      - translation-net

  # Model updater service (runs periodically)
  model-updater:
    build:
      context: .
      dockerfile: Dockerfile.updater
    container_name: vibeon-model-updater
    restart: unless-stopped
    environment:
      - UPDATE_INTERVAL=3600  # 1 hour
      - MODEL_REGISTRY=s3://vibeon-models
      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
    volumes:
      - ./models:/models
      - ./config:/config:ro
    networks:
      - translation-net

  # Prometheus monitoring
  prometheus:
    image: prom/prometheus:latest
    container_name: vibeon-prometheus
    restart: unless-stopped
    ports:
      - "9090:9090"
    volumes:
      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus-data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
    networks:
      - translation-net

  # Grafana dashboards
  grafana:
    image: grafana/grafana:latest
    container_name: vibeon-grafana
    restart: unless-stopped
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin
      - GF_USERS_ALLOW_SIGN_UP=false
    volumes:
      - grafana-data:/var/lib/grafana
      - ./monitoring/grafana/dashboards:/etc/grafana/provisioning/dashboards
      - ./monitoring/grafana/datasources:/etc/grafana/provisioning/datasources
    depends_on:
      - prometheus
    networks:
      - translation-net

  # Jupyter notebook for experimentation
  jupyter:
    build:
      context: .
      dockerfile: Dockerfile.jupyter
    container_name: vibeon-ml-notebook
    restart: unless-stopped
    ports:
      - "8888:8888"
    environment:
      - JUPYTER_ENABLE_LAB=yes
    volumes:
      - ./notebooks:/home/jovyan/work
      - ./models:/home/jovyan/models:ro
      - ./data:/home/jovyan/data
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    networks:
      - translation-net

volumes:
  redis-data:
  prometheus-data:
  grafana-data:

networks:
  translation-net:
    driver: bridge