Skip to main content

Open WebUI

Open WebUI integration

Build a private chatbot using Loc.ai and Open WebUI — privacy, no subscription fees, full control.

What is Open WebUI?​

Open WebUI is a self-hosted chat UI for LLMs with a ChatGPT-like experience in the browser, talking to any OpenAI-compatible API.

How it works​

  1. Loc.ai — Deploys and serves the model on your hardware (PC or VM).
  2. Open WebUI — The browser UI on your main computer.

They talk over your network.

Step 1: Connect your device​

  1. Log into the Loc.ai dashboard → Devices
  2. Click Add Device and copy the curl command
  3. Run it on the machine that will run the model:
curl -sSL https://raw.githubusercontent.com/locai-co-uk/locai-link/main/install.sh | bash -s -- \
  --device-name "YOUR_DEVICE" \
  --username "YOUR_USERNAME" \
  --registration-key "YOUR_KEY" \
  --start-running

When registered, the device shows Online.

Step 2: Upload and deploy​

  1. Go to ML MODELS
  2. Upload a GGUF model (e.g. quantised Qwen) or pick from the library; set type Language Model
  3. Deploy to the device from step 1

Step 3: Start serving​

  1. Open the deployed model in the dashboard
  2. Click Start Serving and pick a port (e.g. 8123)
info

Save the device IP and port for step 5.

Step 4: Launch Open WebUI​

pip install open-webui
open-webui serve

Open http://localhost:8080 in your browser.

Step 5: Connect to Loc.ai​

  1. In Open WebUI: profile → Settings → Admin Settings → Connections
  2. Under OpenAI API, add a connection
  3. Set API Base URL to http://<YOUR_DEVICE_IP>:<PORT>/v1

Connections

Step 6: Start chatting​

Choose your Loc.ai model from the model dropdown and chat.

Chat

tip

Add multiple connections for multiple served models on different ports.