docker-compose.production.yml

version: '3.8'

services:
  # Redis for session storage and caching
  redis:
    image: redis:7-alpine
    container_name: agentmind-redis
    ports:
      - "6379:6379"
    volumes:
      - redis-data:/data
    command: redis-server --appendonly yes --maxmemory 512mb --maxmemory-policy allkeys-lru
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5
    restart: unless-stopped
    networks:
      - agentmind-network

  # Ollama LLM service
  ollama:
    image: ollama/ollama:latest
    container_name: agentmind-ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama-data:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s
    restart: unless-stopped
    networks:
      - agentmind-network
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

  # AgentMind API Server
  api:
    build:
      context: .
      dockerfile: Dockerfile.production
    container_name: agentmind-api
    ports:
      - "8000:8000"
    environment:
      - MODE=api
      - OLLAMA_HOST=http://ollama:11434
      - OLLAMA_MODEL=llama3.2
      - REDIS_URL=redis://redis:6379/0
      - LOG_LEVEL=info
      - ENABLE_METRICS=true
      - ENABLE_TRACING=true
      - JWT_SECRET=${JWT_SECRET:-change-me-in-production}
      - RATE_LIMIT_PER_MINUTE=60
      - MAX_WORKERS=4
    volumes:
      - ./traces:/app/traces
      - ./logs:/app/logs
      - ./data:/app/data
    depends_on:
      redis:
        condition: service_healthy
      ollama:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s
    restart: unless-stopped
    networks:
      - agentmind-network

  # Chat UI Server
  chat-ui:
    build:
      context: .
      dockerfile: Dockerfile.chat
    container_name: agentmind-chat-ui
    ports:
      - "5000:5000"
    environment:
      - API_URL=http://api:8000
      - REDIS_URL=redis://redis:6379/1
      - SESSION_SECRET=${SESSION_SECRET:-change-me-in-production}
    depends_on:
      - api
      - redis
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:5000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
    restart: unless-stopped
    networks:
      - agentmind-network

  # Monitoring Dashboard
  dashboard:
    build:
      context: .
      dockerfile: Dockerfile.dashboard
    container_name: agentmind-dashboard
    ports:
      - "3000:3000"
    environment:
      - API_URL=http://api:8000
      - REDIS_URL=redis://redis:6379/2
      - REFRESH_INTERVAL=5000
    depends_on:
      - api
      - redis
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
    restart: unless-stopped
    networks:
      - agentmind-network

  # Prometheus for metrics
  prometheus:
    image: prom/prometheus:latest
    container_name: agentmind-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'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
    restart: unless-stopped
    networks:
      - agentmind-network

  # Grafana for visualization
  grafana:
    image: grafana/grafana:latest
    container_name: agentmind-grafana
    ports:
      - "3001:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_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
    restart: unless-stopped
    networks:
      - agentmind-network

  # Nginx reverse proxy
  nginx:
    image: nginx:alpine
    container_name: agentmind-nginx
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./nginx/nginx.conf:/etc/nginx/nginx.conf
      - ./nginx/ssl:/etc/nginx/ssl
    depends_on:
      - api
      - chat-ui
      - dashboard
    restart: unless-stopped
    networks:
      - agentmind-network

volumes:
  redis-data:
    driver: local
  ollama-data:
    driver: local
  prometheus-data:
    driver: local
  grafana-data:
    driver: local

networks:
  agentmind-network:
    driver: bridge