Connect Open WebUI to OpenLLM Buddy

Connect Open WebUI to OpenLLM Buddy. Add an OpenAI-compatible connection in Admin Settings or with environment variables, then chat with your model.

Chat UI · Integration guide

What is Open WebUI?

Open WebUI is a self-hosted chat interface with multi-user accounts, chat history, document upload, and prompt presets. It talks to any OpenAI-compatible API. Visit Open WebUI.

Why connect OpenLLM Buddy?

OpenLLM Buddy gives Open WebUI a private, unrestricted model behind a standard /v1/chat/completions endpoint, so you get a polished chat front end without running a model locally.

Before you start, create an API key in the console and deploy a model. If anything fails, run the curl test in Step 4 first: no tool can fix a broken endpoint.

1

Run Open WebUI

If you do not have Open WebUI yet, the quickest path is Docker. Passing the base URL and key as environment variables pre-fills the connection for every user.

Terminal
bash
docker run -d -p 3000:8080 \
  -e OPENAI_API_BASE_URL=https://openllmbuddy-proxy.botbuddytech.workers.dev/v1 \
  -e OPENAI_API_KEY=YOUR_API_KEY \
  -v open-webui:/app/backend/data \
  --name open-webui --restart always \
  ghcr.io/open-webui/open-webui:main

Open http://localhost:3000, create the first account (it becomes the admin), and skip to Step 3. If Open WebUI is already running, use Step 2 instead.

2

Add the connection in Admin Settings

Sign in as an admin, then add OpenLLM Buddy as an OpenAI connection.

  • Open Admin Panel → Settings → Connections.
  • Under OpenAI API, click + to add a connection.
  • URL: https://openllmbuddy-proxy.botbuddytech.workers.dev/v1
  • API Key: your OpenLLM Buddy key.
  • Click the verify button next to the URL, then Save.
3

Pick the model and chat

Start a new chat and open the model selector. Your model gemma4:26b should be listed. If the list is empty, add the id manually under the connection's Model IDs (Filter) field.

Tip: set a default system prompt per model in Workspace → Models to carry your own instructions into every chat.

4

Test the endpoint with curl

Confirm the key, URL, and model id work before debugging Open WebUI. A short JSON reply means the endpoint is healthy.

Terminal
bash
curl -sS https://openllmbuddy-proxy.botbuddytech.workers.dev/v1/chat/completions   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{"model": "gemma4:26b", "messages": [{"role": "user", "content": "Reply with OK"}], "max_tokens": 16}'

Troubleshooting

  • Empty model list — Open WebUI reads /v1/models. Add the model id by hand in the connection's Model IDs field.
  • Verify fails but curl works — the container cannot reach the internet or the URL has a trailing slash. Remove the slash and restart the container.
  • 401 or 403 — the API key is wrong, revoked, or missing the Bearer prefix. Create a fresh key in the console.
  • 404 on /chat/completions — the base URL must end in /v1, with no trailing /chat/completions and no extra path.
  • Model not found — the model id must match your deployment exactly. Run the curl test and copy the id you used.
  • Timeouts on the first request — a GPU that was idle may still be loading the model. Retry after a minute.
  • Connection refused from Docker or a remote host — use the public HTTPS base URL, never localhost.

Connection details

Use these values wherever Open WebUI asks for an OpenAI-compatible provider.

Reference
text
Base URL:  https://openllmbuddy-proxy.botbuddytech.workers.dev/v1
Chat URL:  https://openllmbuddy-proxy.botbuddytech.workers.dev/v1/chat/completions
API key:   your key from the console
Model id:  gemma4:26b