version: "3.9"
services:
  api:
    image: localai/localai:latest-cpu
    # For a specific version:
   # image: localai/localai:v2.12.4-cpu
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
      interval: 1m
      timeout: 20m
      retries: 5
    ports:
      - 31245:8080
    environment:
      - DEBUG=true
      - REBUILD=true
      - GALLERIES=[{"name":"model-gallery", "url":"github:go-skynet/model-gallery/index.yaml"}, {"name":"huggingface", "url":"github:go-skynet/model-gallery/huggingface.yaml"}]
     # - PRELOAD_MODELS='[{"url": "https://raw.githubusercontent.com/go-skynet/model-gallery/main/gpt4all-j.yaml","name": "gpt4all-j"}]' local-ai
      # ...
    volumes:
      - ./models:/build/models:cached
    # decomment the following piece if running with Nvidia GPUs
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: 1
    #           capabilities: [gpu]