src/deployment/docker/docker-compose.yml

version: '3.8'

services:
  # Main Cyber-LLM API service
  cyber-llm-api:
    build:
      context: ../../../
      dockerfile: src/deployment/docker/Dockerfile
      target: production
    container_name: cyber-llm-api
    ports:
      - "8000:8000"
    environment:
      - PYTHONPATH=/home/cyberllm
      - CUDA_VISIBLE_DEVICES=0
      - TRANSFORMERS_CACHE=/home/cyberllm/models/cache
    volumes:
      - ./data:/home/cyberllm/data
      - ./models:/home/cyberllm/models
      - ./logs:/home/cyberllm/logs
      - ./configs:/home/cyberllm/configs
    networks:
      - cyber-llm-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  # Training service (optional)
  cyber-llm-training:
    build:
      context: ../../../
      dockerfile: src/deployment/docker/Dockerfile
      target: training
    container_name: cyber-llm-training
    environment:
      - PYTHONPATH=/home/cyberllm
      - CUDA_VISIBLE_DEVICES=0
      - WANDB_API_KEY=${WANDB_API_KEY}
      - MLFLOW_TRACKING_URI=http://mlflow:5000
    volumes:
      - ./data:/home/cyberllm/data
      - ./models:/home/cyberllm/models
      - ./logs:/home/cyberllm/logs
      - ./configs:/home/cyberllm/configs
    networks:
      - cyber-llm-network
    profiles:
      - training
    depends_on:
      - mlflow

  # MLflow tracking server
  mlflow:
    image: python:3.10-slim
    container_name: cyber-llm-mlflow
    ports:
      - "5000:5000"
    environment:
      - MLFLOW_BACKEND_STORE_URI=sqlite:///mlflow/mlflow.db
      - MLFLOW_DEFAULT_ARTIFACT_ROOT=/mlflow/artifacts
    volumes:
      - ./mlflow:/mlflow
    networks:
      - cyber-llm-network
    command: >
      bash -c "
        pip install mlflow &&
        mlflow server 
          --backend-store-uri sqlite:///mlflow/mlflow.db 
          --default-artifact-root /mlflow/artifacts 
          --host 0.0.0.0 
          --port 5000
      "
    profiles:
      - training
      - monitoring

  # Prometheus monitoring
  prometheus:
    image: prom/prometheus:latest
    container_name: cyber-llm-prometheus
    ports:
      - "9090:9090"
    volumes:
      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml
      - ./monitoring/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'
      - '--web.enable-lifecycle'
    networks:
      - cyber-llm-network
    profiles:
      - monitoring

  # Grafana dashboard
  grafana:
    image: grafana/grafana:latest
    container_name: cyber-llm-grafana
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin123
    volumes:
      - ./monitoring/grafana_data:/var/lib/grafana
      - ./monitoring/grafana/dashboards:/etc/grafana/provisioning/dashboards
      - ./monitoring/grafana/datasources:/etc/grafana/provisioning/datasources
    networks:
      - cyber-llm-network
    profiles:
      - monitoring

  # Redis for caching (optional)
  redis:
    image: redis:7-alpine
    container_name: cyber-llm-redis
    ports:
      - "6379:6379"
    volumes:
      - ./redis_data:/data
    networks:
      - cyber-llm-network
    profiles:
      - cache

  # Nginx reverse proxy
  nginx:
    image: nginx:alpine
    container_name: cyber-llm-nginx
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./nginx/nginx.conf:/etc/nginx/nginx.conf
      - ./nginx/ssl:/etc/nginx/ssl
    networks:
      - cyber-llm-network
    depends_on:
      - cyber-llm-api
    profiles:
      - production

networks:
  cyber-llm-network:
    driver: bridge

volumes:
  data:
  models:
  logs:
  mlflow:
  prometheus_data:
  grafana_data:
  redis_data: