LocalAI

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
    # 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: quay.io/go-skynet/local-ai:master
    build:
      context: .
      dockerfile: Dockerfile
      args:
      - IMAGE_TYPE=core
      - BASE_IMAGE=ubuntu:24.04
    ports:
      - 8080:8080
    env_file:
      - .env
    environment:
      - MODELS_PATH=/models
      # Avoid probing remote gallery GGUF metadata during container startup.
      # Remove this line or set a positive limit to opt back into cache warming.
      - LOCALAI_VRAM_WARM_LIMIT=0
    #  - DEBUG=true
    ## Agents (LocalAGI) - https://localai.io/features/agents/
    #  - LOCALAI_DISABLE_AGENTS=false
    #  - LOCALAI_AGENT_POOL_DEFAULT_MODEL=hermes-3-llama3.1-8b
    #  - LOCALAI_AGENT_POOL_ENABLE_SKILLS=true
    #  - LOCALAI_AGENT_POOL_ENABLE_LOGS=true
    #  - LOCALAI_AGENT_HUB_URL=https://agenthub.localai.io
    ## Uncomment to use PostgreSQL for the knowledge base (requires the postgres service below)
    #  - LOCALAI_AGENT_POOL_VECTOR_ENGINE=postgres
    #  - LOCALAI_AGENT_POOL_DATABASE_URL=postgresql://localrecall:localrecall@postgres:5432/localrecall?sslmode=disable
    volumes:
      - models:/models
      - images:/tmp/generated/images/
      - data:/data
      - backends:/backends
      - configuration:/configuration
    command:
    # Here we can specify a list of models to run (see quickstart https://localai.io/basics/getting_started/#running-models )
    # or an URL pointing to a YAML configuration file, for example:
    # - https://gist.githubusercontent.com/mudler/ad601a0488b497b69ec549150d9edd18/raw/a8a8869ef1bb7e3830bf5c0bae29a0cce991ff8d/phi-2.yaml
    - phi-2-chat
    # For NVIDIA GPU support with CDI (recommended for NVIDIA Container Toolkit 1.14+):
    # Uncomment the following deploy section and use driver: nvidia.com/gpu.
    # Include `utility` in capabilities so nvidia-smi / NVML are available —
    # without it, free-VRAM reporting on discrete GPUs is unavailable and the
    # Nodes UI will misreport memory usage.
    # environment:
    #   NVIDIA_DRIVER_CAPABILITIES: "compute,utility"
    # init: true   # avoids zombie-reap races that can make nvidia-smi flaky
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia.com/gpu
    #           count: all
    #           capabilities: [gpu, utility]
    #
    # For legacy NVIDIA driver (for older NVIDIA Container Toolkit):
    # Request compute for CUDA libraries (libcuda.so.1) and utility for NVML.
    # environment:
    #   NVIDIA_DRIVER_CAPABILITIES: "compute,utility"
    # init: true
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: 1
    #           capabilities: [gpu, compute, utility]

  ## Uncomment for PostgreSQL-backed knowledge base (see Agents docs)
  # postgres:
  #   image: quay.io/mudler/localrecall:v0.5.2-postgresql
  #   environment:
  #     - POSTGRES_DB=localrecall
  #     - POSTGRES_USER=localrecall
  #     - POSTGRES_PASSWORD=localrecall
  #   volumes:
  #     - postgres_data:/var/lib/postgresql
  #   healthcheck:
  #     test: ["CMD-SHELL", "pg_isready -U localrecall"]
  #     interval: 10s
  #     timeout: 5s
  #     retries: 5

volumes:
  models:
  images:
  data:
  configuration:
  backends:
  # postgres_data: