services:
  app:
    build: .
    ports:
      - "5000:5000"
    depends_on:
      db:
        condition: service_healthy
      ollama:
        condition: service_started
    volumes:
      - app_data:/data
      # To use a bind mount instead (gives direct host access to all app data):
      # - ./data:/data
    environment:
      DATABASE_URL: "postgresql+asyncpg://${POSTGRES_USER:-fabled}:${POSTGRES_PASSWORD:-fabled}@db:5432/${POSTGRES_DB:-fabledassistant}"
      OLLAMA_URL: "http://ollama:11434"
      OLLAMA_MODEL: "${OLLAMA_MODEL:-qwen3:14b}"
      SECRET_KEY: "${SECRET_KEY:-dev-secret-change-me}"
      # Uncomment and set to enable web research and image search via SearXNG:
      # SEARXNG_URL: "http://searxng:8080"
      # IMAGE_CACHE_DIR: /data/images  # default, change if using a different mount path
      # IMAGE_MAX_BYTES: "5242880"     # 5 MB per image, adjust if needed
      # Push notifications (VAPID keys - generate with: python -c "from py_vapid import Vapid01; v=Vapid01(); v.generate_keys(); print(v.private_key, v.public_key)")
      VAPID_PRIVATE_KEY: "${VAPID_PRIVATE_KEY:-}"
      VAPID_PUBLIC_KEY: "${VAPID_PUBLIC_KEY:-}"
      VAPID_CLAIMS_SUB: "${VAPID_CLAIMS_SUB:-mailto:admin@fabledassistant.local}"
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:5000/api/health')"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s

  db:
    image: postgres:16-alpine
    volumes:
      - pgdata:/var/lib/postgresql/data
    environment:
      POSTGRES_USER: ${POSTGRES_USER:-fabled}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-fabled}
      POSTGRES_DB: ${POSTGRES_DB:-fabledassistant}
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-fabled}"]
      interval: 5s
      timeout: 5s
      retries: 5

  ollama:
    image: ollama/ollama
    volumes:
      - ollama_models:/root/.ollama
    environment:
      OLLAMA_MAX_LOADED_MODELS: "2"
      OLLAMA_NUM_PARALLEL: "2"
      OLLAMA_KEEP_ALIVE: "30m"
      OLLAMA_FLASH_ATTENTION: "1"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

volumes:
  pgdata:
  ollama_models:
  app_data: