services:
  api:
    # See https://localai.io/basics/getting_started/#container-images for
    # a list of available container images (or build your own with the provided Dockerfile)
    # Available images with CUDA, ROCm, SYCL, Vulkan
    # Image list (quay.io): https://quay.io/repository/go-skynet/local-ai?tab=tags
    # Image list (dockerhub): https://hub.docker.com/r/localai/localai
    image: localai/localai:latest-cpu
    command: 
    - marco-o1
    - bert-embeddings
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
      interval: 10s
      timeout: 20m
      retries: 20
    ports:
    - 8081:8080
    environment:
      - DEBUG=true
    volumes:
      - ./models:/build/models:cached
    # decomment the following piece if running with Nvidia GPUs
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: 1
    #           capabilities: [gpu]
  localagent:
    depends_on:
      api:
        condition: service_healthy
    build:
      context: .
      dockerfile: Dockerfile.webui
    ports:
      - 8080:3000
    environment:
      - LOCALAGENT_MODEL=marco-o1
      - EMBEDDING_MODEL=bert-embeddings
      - LOCALAGENT_LLM_API_URL=http://api:8080
    volumes:
      - ./data/:/pool