Tooling · Configuration
Open WebUI
How do I use Open WebUI with Onrup?
Add your deployment as an OpenAI-compatible connection in the admin settings. It gives non-technical colleagues a chat interface against your fine-tuned model without anyone writing a front end.
A self-hosted chat interface that can connect to any OpenAI-compatible backend.
Minimal working example
Settings -> Connections -> OpenAI API
API Base URL https://serve.onrup.com/<tenant>/<deployment>/v1
API Key onrup_sk_...The thing that catches people out
It periodically calls the models listing endpoint to populate its menu. On a scale-to-zero deployment that can trigger a cold start on a schedule, quietly keeping the endpoint warm and billing for it.
Worth knowing
- The fastest way to let subject-matter experts judge a fine-tune before it goes near production.
- Their reactions make good gate cases — the ones they disliked are the ones worth measuring.
- Self-host it inside your own network if the conversations contain anything sensitive.
Other tooling
LiteLLM
A proxy and library that presents many model providers behind one OpenAI-compatible interface.
n8n
A workflow automation tool with a visual editor, self-hostable, with language-model nodes built in.
Continue
An open-source coding assistant extension for VS Code and JetBrains that can use any compatible model.
Start with the free tier
A magic link creates your account, your tenant and your first API key. No card until you ask for compute.