docker-compose-localai.yml

# This file comes from https://localai.io/basics/container/
# Visit that URL for more infos

services:
  api:
    image: localai/localai:latest-aio-cpu
    # For a specific version:
    # image: localai/localai:v2.21.1-aio-cpu
    # For Nvidia GPUs decomment one of the following (cuda11 or cuda12):
    # image: localai/localai:v2.21.1-aio-gpu-nvidia-cuda-11
    # image: localai/localai:v2.21.1-aio-gpu-nvidia-cuda-12
    # image: localai/localai:latest-aio-gpu-nvidia-cuda-11
    # image: localai/localai:latest-aio-gpu-nvidia-cuda-12
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
      interval: 1m
      timeout: 20m
      retries: 5
    ports:
      - 8080:8080
    environment:
      - DEBUG=true
      # ...
    volumes:
      - localai-models:/build/models:cached
    # decomment the following piece if running with Nvidia GPUs
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: 1
    #           capabilities: [gpu]

volumes:
  localai-models: { }