docker-compose.prod.yml

version: '3.8'

services:
  # Production database with backup
  database:
    image: postgres:15-alpine
    container_name: llm-platform-db-prod
    environment:
      POSTGRES_DB: ${POSTGRES_DB}
      POSTGRES_USER: ${POSTGRES_USER}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
    volumes:
      - postgres_data_prod:/var/lib/postgresql/data
      - ./database/init.sql:/docker-entrypoint-initdb.d/init.sql:ro
      - ./backups:/backups
    networks:
      - llm-network-prod
    restart: always
    deploy:
      resources:
        limits:
          memory: 2G
          cpus: '1.0'
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER} -d ${POSTGRES_DB}"]
      interval: 30s
      timeout: 10s
      retries: 5

  # Production Redis with persistence
  redis:
    image: redis:7-alpine
    container_name: llm-platform-redis-prod
    command: redis-server --appendonly yes --requirepass ${REDIS_PASSWORD} --maxmemory 1gb --maxmemory-policy allkeys-lru
    volumes:
      - redis_data_prod:/data
    networks:
      - llm-network-prod
    restart: always
    deploy:
      resources:
        limits:
          memory: 1G
          cpus: '0.5'
    healthcheck:
      test: ["CMD", "redis-cli", "--raw", "incr", "ping"]
      interval: 30s
      timeout: 10s
      retries: 5

  # Production backend with security hardening
  backend:
    build:
      context: .
      dockerfile: Dockerfile.prod
    container_name: llm-platform-backend-prod
    environment:
      - FLASK_ENV=production
      - DATABASE_URL=postgresql://${POSTGRES_USER}:${POSTGRES_PASSWORD}@database:5432/${POSTGRES_DB}
      - REDIS_URL=redis://:${REDIS_PASSWORD}@redis:6379/0
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
      - SECRET_KEY=${SECRET_KEY}
      - JWT_SECRET_KEY=${JWT_SECRET_KEY}
      - API_HOST=0.0.0.0
      - API_PORT=5000
      - LOG_LEVEL=WARNING
      - CORS_ORIGINS=${CORS_ORIGINS}
    volumes:
      - ./models:/app/models:ro
      - ./datasets:/app/datasets:ro
      - ./logs:/app/logs
    depends_on:
      database:
        condition: service_healthy
      redis:
        condition: service_healthy
    networks:
      - llm-network-prod
    restart: always
    deploy:
      resources:
        limits:
          memory: 8G
          cpus: '4.0'
      replicas: 2
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:5000/api/v1/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s

  # Production frontend with nginx
  frontend:
    build:
      context: ./web_interface/frontend
      dockerfile: Dockerfile.prod
    container_name: llm-platform-frontend-prod
    environment:
      - REACT_APP_API_URL=/api/v1
    depends_on:
      backend:
        condition: service_healthy
    networks:
      - llm-network-prod
    restart: always
    deploy:
      resources:
        limits:
          memory: 512M
          cpus: '0.5'
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost/"]
      interval: 30s
      timeout: 10s
      retries: 5

  # Load balancer and reverse proxy
  nginx:
    image: nginx:alpine
    container_name: llm-platform-nginx-prod
    volumes:
      - ./nginx/nginx.conf:/etc/nginx/nginx.conf:ro
      - ./nginx/ssl:/etc/nginx/ssl:ro
      - ./logs/nginx:/var/log/nginx
    ports:
      - "80:80"
      - "443:443"
    depends_on:
      - backend
      - frontend
    networks:
      - llm-network-prod
    restart: always
    deploy:
      resources:
        limits:
          memory: 256M
          cpus: '0.25'
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost/health"]
      interval: 30s
      timeout: 10s
      retries: 5

  # Monitoring with Prometheus
  prometheus:
    image: prom/prometheus:latest
    container_name: llm-platform-prometheus
    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=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--storage.tsdb.retention.time=200h'
      - '--web.enable-lifecycle'
    ports:
      - "9090:9090"
    networks:
      - llm-network-prod
    restart: always
    profiles:
      - monitoring

  # Log aggregation with Grafana
  grafana:
    image: grafana/grafana:latest
    container_name: llm-platform-grafana
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_PASSWORD}
    volumes:
      - grafana_data:/var/lib/grafana
      - ./monitoring/grafana/dashboards:/etc/grafana/provisioning/dashboards:ro
      - ./monitoring/grafana/datasources:/etc/grafana/provisioning/datasources:ro
    ports:
      - "3001:3000"
    depends_on:
      - prometheus
    networks:
      - llm-network-prod
    restart: always
    profiles:
      - monitoring

networks:
  llm-network-prod:
    driver: bridge
    ipam:
      config:
        - subnet: 172.20.0.0/16

volumes:
  postgres_data_prod:
    driver: local
  redis_data_prod:
    driver: local
  prometheus_data:
    driver: local
  grafana_data:
    driver: local