version: '3.8'

services:
  ollama:
    image: ollama/ollama
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
    ports:
      - "11434:11434"
    volumes:
      - ./data/ollama:/root/.ollama
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

  webui:
    image: ${WEBUI_IMAGE:-ghcr.io/open-webui/open-webui:cuda}
    runtime: nvidia  # Use NVIDIA runtime for GPU support
    deploy:
      resources:
        reservations:
          devices:
            - capabilities: [gpu]
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
    volumes:
      - "${VOL_PATH:-./data}/webui:/root/.cache"
      - "${VOL_PATH:-./data}/open-webui:/app/backend/data"
    extra_hosts:
      - "host.docker.internal:host-gateway"
    ports:
      - "3000:8080"  # Open WebUI access

  ollama-cpu:
    image: ollama/ollama
    ports:
      - "11434:11434"
    volumes:
      - "${VOL_PATH:-./data}/ollama:/root/.ollama"

  webui-cpu:
    image: ${WEBUI_IMAGE:-ghcr.io/open-webui/open-webui:cuda}
    volumes:
      - "${VOL_PATH:-./data}/webui:/root/.cache"
      - "${VOL_PATH:-./data}/open-webui:/app/backend/data"
    extra_hosts:
      - "host.docker.internal:host-gateway"
    ports:
      - "3000:8080"  # Open WebUI access