services:
  localai:
    image: ${LOCALAI_IMAGE:-localai/localai:v4.4.3-gpu-nvidia-cuda-13}
    container_name: localai
    profiles:
      - localai
    restart: unless-stopped
    init: true
    ports:
      - "${LOCALAI_PORT:-8080}:8080"
    environment:
      - LOCALAI_API_KEY=${LOCALAI_API_KEY:-}
      - CUDA_VISIBLE_DEVICES=${CUDA_VISIBLE_DEVICES:-0}
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
      - MODELS_PATH=/models
      - DEBUG=${DEBUG:-false}
      - SINGLE_ACTIVE_BACKEND=true
      - PARALLEL_REQUESTS=false
    volumes:
      - ${DATA_ROOT:-/data}/apps/localai/models:/models
      - ${DATA_ROOT:-/data}/apps/localai/backends:/backends
      - ${DATA_ROOT:-/data}/apps/localai/configuration:/configuration
      - ${DATA_ROOT:-/data}/apps/localai/images:/tmp/generated/images
      - ${DATA_ROOT:-/data}/apps/localai/data:/data
    gpus: all
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
      interval: 1m
      timeout: 20m
      retries: 5
      start_period: 2m