esc
Type to search the docs
Back to catalog

ollama-openwebui

Draft

LLM inference server with chat UI

Run locally

Terminal
$ npx launchfile up ollama-openwebui

Requires Docker Desktop. No source code needed — pulls pre-built images and starts ollama-openwebui with all dependencies.

Image: ollama/ollama:latest
Launchfile View on GitHub
# yaml-language-server: $schema=https://launchfile.dev/schema/v1
version: launch/v1
name: ollama-openwebui
description: "LLM inference server with chat UI"

components:
  ollama:
    image: ollama/ollama:latest
    platform: linux/amd64
    provides:
      - protocol: http
        port: 11434
    health:
      path: /api/tags
      interval: 30s
      timeout: 10s
      start_period: 60s
    storage:
      models:
        path: /root/.ollama
        persistent: true
    restart: always

  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    provides:
      - protocol: http
        port: 8080
        exposed: true
    depends_on:
      - component: ollama
        condition: healthy
    env:
      OLLAMA_BASE_URL:
        default: $components.ollama.url
        description: "URL of the Ollama API server"
    storage:
      data:
        path: /app/backend/data
        persistent: true
    health: /
    restart: always

Components

2 components in this Launchfile.

ollamaopen-webui

Learn More

Spec references for features used in this Launchfile.

Related Apps