docker-compose.yml

version: '3.8'

services:
  # Main API Service
  api:
    build:
      context: .
      dockerfile: Dockerfile
      target: production
    container_name: predictive-maintenance-api
    ports:
      - "8000:8000"
    volumes:
      - ./artifacts:/app/artifacts
      - ./data:/app/data
      - ./config:/app/config
    environment:
      - PYTHONPATH=/app
      - MLFLOW_TRACKING_URI=http://mlflow:5000
      - ENVIRONMENT=production
    depends_on:
      - mlflow
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
    networks:
      - ml-network

  # MLflow Tracking Server
  mlflow:
    image: ghcr.io/mlflow/mlflow:v2.9.2
    container_name: mlflow-server
    ports:
      - "5000:5000"
    volumes:
      - mlflow-data:/mlflow
    environment:
      - MLFLOW_BACKEND_STORE_URI=sqlite:///mlflow/mlflow.db
      - MLFLOW_DEFAULT_ARTIFACT_ROOT=/mlflow/artifacts
    command: >
      mlflow server
      --backend-store-uri sqlite:///mlflow/mlflow.db
      --default-artifact-root /mlflow/artifacts
      --host 0.0.0.0
      --port 5000
    restart: unless-stopped
    networks:
      - ml-network

  # Streamlit Dashboard
  dashboard:
    build:
      context: .
      dockerfile: Dockerfile
      target: production
    container_name: predictive-maintenance-dashboard
    ports:
      - "8501:8501"
    volumes:
      - ./artifacts:/app/artifacts
      - ./data:/app/data
    environment:
      - PYTHONPATH=/app
      - API_URL=http://api:8000
    command: ["streamlit", "run", "dashboard/app.py", "--server.port=8501", "--server.address=0.0.0.0"]
    depends_on:
      - api
    restart: unless-stopped
    networks:
      - ml-network

  # MongoDB for data storage
  mongodb:
    image: mongo:7.0
    container_name: mongodb
    ports:
      - "27017:27017"
    volumes:
      - mongodb-data:/data/db
    environment:
      - MONGO_INITDB_ROOT_USERNAME=admin
      - MONGO_INITDB_ROOT_PASSWORD=password
    restart: unless-stopped
    networks:
      - ml-network

  # Prometheus for monitoring
  prometheus:
    image: prom/prometheus:v2.47.0
    container_name: prometheus
    ports:
      - "9090:9090"
    volumes:
      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml
      - prometheus-data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
    restart: unless-stopped
    networks:
      - ml-network

  # Grafana for visualization
  grafana:
    image: grafana/grafana:10.2.0
    container_name: grafana
    ports:
      - "3000:3000"
    volumes:
      - grafana-data:/var/lib/grafana
      - ./monitoring/grafana/provisioning:/etc/grafana/provisioning
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin
      - GF_USERS_ALLOW_SIGN_UP=false
    depends_on:
      - prometheus
    restart: unless-stopped
    networks:
      - ml-network

  # Training Job (run on-demand)
  training:
    build:
      context: .
      dockerfile: Dockerfile
      target: training
    container_name: training-job
    volumes:
      - ./:/app
      - ./artifacts:/app/artifacts
      - ./data:/app/data
    environment:
      - PYTHONPATH=/app
      - MLFLOW_TRACKING_URI=http://mlflow:5000
    depends_on:
      - mlflow
    profiles:
      - training
    networks:
      - ml-network

networks:
  ml-network:
    driver: bridge

volumes:
  mlflow-data:
  mongodb-data:
  prometheus-data:
  grafana-data: