ai-server/docker-compose.yml

version: '3.8'

services:
  # Основной веб-интерфейс с поддержкой GPU
  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: ai-server-webui
    ports:
      - "3000:8080"
    environment:
      # Подключение к Ollama
      - OLLAMA_BASE_URL=http://host.docker.internal:11434
      
      # Настройки безопасности
      - WEBUI_SECRET_KEY=ai-server-ubuntu-rtx2060-2024
      - WEBUI_NAME=AI Server RTX 2060
      
      # Локализация
      - DEFAULT_LOCALE=ru-RU
      - DEFAULT_MODELS=llama3.2:3b,codellama:7b
      
      # Настройки интерфейса
      - SHOW_ADMIN_DETAILS=false
      - ENABLE_SIGNUP=true
      - ENABLE_LOGIN_FORM=true
      - ENABLE_COMMUNITY_SHARING=false
      
      # Настройки чатов
      - DEFAULT_USER_ROLE=user
      - ENABLE_MODEL_FILTER=true
      - MODEL_FILTER_LIST=llama3.2:1b;llama3.2:3b;codellama:7b;mistral:7b
      
      # Настройки производительности
      - WEBUI_SESSION_COOKIE_SAME_SITE=lax
      - WEBUI_SESSION_COOKIE_SECURE=false
      
    volumes:
      # Постоянное хранение данных
      - open-webui-data:/app/backend/data
      
      # Кастомные настройки
      - ./config:/app/backend/config:ro
      - ./logs:/app/backend/logs
      
    extra_hosts:
      # Доступ к хосту для подключения к Ollama
      - "host.docker.internal:host-gateway"
      
    restart: unless-stopped
    networks:
      - ai-network
    
    # Ограничения ресурсов (оптимизировано для RTX 2060)
    deploy:
      resources:
        limits:
          cpus: '4.0'
          memory: 6G
        reservations:
          cpus: '1.0'
          memory: 2G
    
    # Healthcheck
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  # Мониторинг GPU и системы
  nvidia-exporter:
    image: mindprince/nvidia_gpu_prometheus_exporter:0.1
    container_name: ai-server-gpu-exporter
    ports:
      - "9445:9445"
    volumes:
      - /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:ro
      - /usr/bin/nvidia-smi:/usr/bin/nvidia-smi:ro
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
    restart: unless-stopped
    networks:
      - ai-network
    profiles:
      - monitoring

  # Веб-интерфейс для управления Docker
  portainer:
    image: portainer/portainer-ce:latest
    container_name: ai-server-portainer
    ports:
      - "9000:9000"
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock
      - portainer-data:/data
    restart: unless-stopped
    networks:
      - ai-network
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 512M
    profiles:
      - monitoring

  # Grafana для мониторинга (опционально)
  grafana:
    image: grafana/grafana:latest
    container_name: ai-server-grafana
    ports:
      - "3001:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin
      - GF_USERS_ALLOW_SIGN_UP=false
    volumes:
      - grafana-data:/var/lib/grafana
    restart: unless-stopped
    networks:
      - ai-network
    profiles:
      - monitoring

  # Prometheus для сбора метрик (опционально)
  prometheus:
    image: prom/prometheus:latest
    container_name: ai-server-prometheus
    ports:
      - "9090:9090"
    volumes:
      - ./config/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'
    restart: unless-stopped
    networks:
      - ai-network
    profiles:
      - monitoring

  # Reverse proxy для безопасности (опционально)
  nginx:
    image: nginx:alpine
    container_name: ai-server-nginx
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./config/nginx.conf:/etc/nginx/nginx.conf:ro
      - ./ssl:/etc/nginx/ssl:ro
    depends_on:
      - open-webui
    restart: unless-stopped
    networks:
      - ai-network
    profiles:
      - production

networks:
  ai-network:
    driver: bridge
    ipam:
      config:
        - subnet: 172.20.0.0/16
          gateway: 172.20.0.1

volumes:
  open-webui-data:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: /opt/ai-server/data
  
  portainer-data:
    driver: local
  
  grafana-data:
    driver: local
  
  prometheus-data:
    driver: local

# Конфигурация для production
x-production-settings: &production-settings
  restart: unless-stopped
  logging:
    driver: "json-file"
    options:
      max-size: "10m"
      max-file: "3"