docker-compose.yml

services:
  llama-server:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: llama-server
    restart: always
    ports:
      - 8080:8080
    volumes:
      - ./unsloth:/models/
      - ./config.yaml:/project/config.yaml
    deploy:
      resources:
        reservations:
          devices:
          - capabilities: ["gpu"]
            driver: nvidia
            count: all
  webui:
    image: ghcr.io/open-webui/open-webui
    container_name: webui
    volumes:
      - webui:/app/backend/data
    depends_on:
      - llama-server 
    ports:
      - 3000:3000 
    environment:
      - WEBUI_AUTH=False
      - PORT=3000
      - ENABLE_OPENAI_API=True
      - OPENAI_API_BASE_URL=http://llama-server:8080/v1
      - ENABLE_OLLAMA_API=False
    extra_hosts:
      - host.docker.internal:host-gateway
    restart: unless-stopped
volumes:
  webui: {}
  llama-server: {}