production/docker-compose.yml

version: "3.8"

services:
  api:
    build:
      context: .
      dockerfile: Dockerfile.prod
    ports:
      - "8000:8000"
    environment:
      - PORT=8000
      - WORKERS=4
      - REDIS_URL=redis://redis:6379
      - DATABASE_URL=postgresql://ml_intern:ml_intern@postgres:5432/ml_intern
      - MAX_CONCURRENT_REQUESTS=200
      - DEFAULT_RPM_LIMIT=40
      - REQUEST_TIMEOUT=120
      - CACHE_TTL_SECONDS=300
      - BUDGET_USD_PER_SESSION=10.0
      - CIRCUIT_BREAKER_FAILURE_THRESHOLD=5
      - CIRCUIT_BREAKER_RECOVERY_TIMEOUT=60
      - HF_TOKEN=${HF_TOKEN}
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
      - OPENAI_API_KEY=${OPENAI_API_KEY:-}
      - GROQ_API_KEY=${GROQ_API_KEY:-}
      - NVIDIA_API_KEY=${NVIDIA_API_KEY:-}
      - LOG_LEVEL=INFO
    depends_on:
      redis:
        condition: service_healthy
      postgres:
        condition: service_healthy
    networks:
      - ml_intern_network
    deploy:
      replicas: 2
      resources:
        limits:
          cpus: '4'
          memory: 4G
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s
    restart: unless-stopped

  worker:
    build:
      context: .
      dockerfile: Dockerfile.prod
    command: ["python", "-m", "worker"]
    environment:
      - REDIS_URL=redis://redis:6379
      - DATABASE_URL=postgresql://ml_intern:ml_intern@postgres:5432/ml_intern
      - LOG_LEVEL=INFO
    depends_on:
      redis:
        condition: service_healthy
      postgres:
        condition: service_healthy
    networks:
      - ml_intern_network
    deploy:
      replicas: 2
      resources:
        limits:
          cpus: '2'
          memory: 2G
    restart: unless-stopped

  redis:
    image: redis:7-alpine
    ports:
      - "6379:6379"
    volumes:
      - redis_data:/data
    command: redis-server --appendonly yes --maxmemory 1gb --maxmemory-policy allkeys-lru
    networks:
      - ml_intern_network
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 3s
      retries: 3
    restart: unless-stopped

  postgres:
    image: postgres:16-alpine
    ports:
      - "5432:5432"
    environment:
      - POSTGRES_USER=ml_intern
      - POSTGRES_PASSWORD=ml_intern
      - POSTGRES_DB=ml_intern
    volumes:
      - postgres_data:/var/lib/postgresql/data
      - ./init.sql:/docker-entrypoint-initdb.d/init.sql:ro
    networks:
      - ml_intern_network
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ml_intern"]
      interval: 10s
      timeout: 3s
      retries: 5
    restart: unless-stopped

  nginx:
    image: nginx:alpine
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./nginx.conf:/etc/nginx/nginx.conf:ro
      - ./ssl:/etc/nginx/ssl:ro
    depends_on:
      - api
    networks:
      - ml_intern_network
    restart: unless-stopped

  prometheus:
    image: prom/prometheus:latest
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--web.enable-lifecycle'
    networks:
      - ml_intern_network
    restart: unless-stopped

  grafana:
    image: grafana/grafana:latest
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_PASSWORD:-admin}
      - GF_INSTALL_PLUGINS=grafana-piechart-panel
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/dashboards:/etc/grafana/provisioning/dashboards:ro
      - ./grafana/datasources:/etc/grafana/provisioning/datasources:ro
    depends_on:
      - prometheus
    networks:
      - ml_intern_network
    restart: unless-stopped

  jaeger:
    image: jaegertracing/all-in-one:latest
    ports:
      - "16686:16686"
      - "14268:14268"
    environment:
      - COLLECTOR_OTLP_ENABLED=true
    networks:
      - ml_intern_network
    restart: unless-stopped

  pgadmin:
    image: dpage/pgadmin4:latest
    ports:
      - "5050:80"
    environment:
      - PGADMIN_DEFAULT_EMAIL=admin@mlintern.local
      - PGADMIN_DEFAULT_PASSWORD=${PGADMIN_PASSWORD:-admin}
    depends_on:
      - postgres
    networks:
      - ml_intern_network
    restart: unless-stopped

volumes:
  redis_data:
  postgres_data:
  prometheus_data:
  grafana_data:

networks:
  ml_intern_network:
    driver: bridge