Ollama

docker-compose.yml

version: '3.8'
services:
  app:
    build: .
    ports:
      - 8000:8000
      - 5678:5678
    volumes:
      - .:/code
    command: uvicorn src.main:app --host 0.0.0.0 --port 8000 --reload
    restart: always
    depends_on:
      - ollama
      - ollama-webui
    networks:
      - ollama-docker

  ollama:
    image: ollama/ollama:latest
    ports:
      - 11434:11434
    volumes:
      - .:/code
      - ./ollama/ollama:/root/.ollama
    container_name: ollama
    pull_policy: always
    tty: true
    restart: always
    environment:
      - OLLAMA_KEEP_ALIVE=24h
      - OLLAMA_HOST=0.0.0.0
    networks:
      - ollama-docker

  ollama-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: ollama-webui
    volumes:
      - ./ollama/ollama-webui:/app/backend/data
    depends_on:
      - ollama
    ports:
      - 8080:8080
    environment: # <https://docs.openwebui.com/getting-started/env-configuration#default_models>
      - OLLAMA_BASE_URLS=http://host.docker.internal:11434 #comma separated ollama hosts
      - ENV=dev
      - WEBUI_AUTH=True
      - WEBUI_NAME=valiantlynx AI
      - WEBUI_URL=http://localhost:8080
      - WEBUI_SECRET_KEY=t0p-s3cr3t
    extra_hosts:
      - host.docker.internal:host-gateway
    restart: unless-stopped
    networks:
      - ollama-docker

networks:
  ollama-docker:
    external: false
  

This will spin up an Ollama server, with an open-webui frontend

If you have a GPU and wish to use it you can add this under the ollama section

You will need the  Nvidia container toolkit

 deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]

ollama-docker/docker-compose-ollama-gpu.yaml at main · valiantlynx/ollama-docker