useful_scripts/ollama-stack.yaml

version: '3.9'

services:
  ollama:
    image: ollama/ollama:latest
    restart: always
    deploy:
      replicas: 1
      resources:
        reservations:
          devices:
          - driver: nvidia
            capabilities: ["compute", "gpu", "utility", "graphics"]
            count: all  # Adjust count for the number of GPUs you want to use        
    ports:
      - 11434:11434
    volumes:
      - ollama:/root/.ollama

  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    restart: always
    ports:
      - 3000:8080
    volumes:
      - open-webui:/app/backend/data
    environment:
      - 'OLLAMA_BASE_URL=http://ollama:11434'

volumes:
  ollama: {}
  open-webui: {}