A docker-compose for running ollama with webui

README.md

Running Ollama on Docker Compose

Assuming you start with a vanilla Ubuntu, you need to install Nvidia stuff

Add Nvidia apt registries:

curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
  && curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
    sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
    sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
    

Install and configure docker to use Nvidia:

sudo apt-get update
sudo apt-get install -y nvidia-container-toolkit
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

Create a directory to store ollama's model files. Make sure you have at least a few 100 Gb free on a fast drive:

mkdir -p ollama/ollama-data

Copy the docker-compose.yml file into the ollama/ directory you create.

cd ollama
docker compose up -d

docker-compose.yml

version: '3.8'

services:
  ollama:
    # Uncomment below for GPU support
    deploy:
      resources:
         reservations:
           devices:
             - driver: nvidia
               count: 1
               capabilities: [gpu]
    volumes:
      - ${OLLAMA_DATA_DIR-./ollama-data}:/root/.ollama
    # Uncomment below to expose Ollama API outside the container stack
    # ports:
    #   - 11434:11434
    container_name: ollama
    pull_policy: always
    tty: true
    restart: unless-stopped
    image: ollama/ollama:latest

  ollama-webui:
    image: ghcr.io/ollama-webui/ollama-webui:main
    container_name: ollama-webui
    depends_on:
      - ollama
    ports:
      - 8080:8080
    environment:
      - "OLLAMA_API_BASE_URL=http://ollama:11434/api"
    extra_hosts:
      - host.docker.internal:host-gateway
    restart: unless-stopped

#volumes:
#  ollama: {}