<aside> đź’ˇ
Open WebUI is an extensible, self-hosted AI interface that adapts to your workflow, all while operating entirely offline, when using local models.
</aside>
<aside> 🚨
If you get an error that states “Docker Desktop - WSL update failed” - don’t panic! Simply follow these few steps:
Ubuntu 22.04.5 LTS - Free download and install on Windows | Microsoft Store
Start the Ubuntu 22.04.5 LTS application you just installed to complete the installation </aside>
Open Terminal (Windows: Press Win+R then type “cmd” and press enter)
Copy this command into the terminal (Press enter to run it):
If you have a GPU:
docker run -d -p 3000:8080 --gpus=all -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:ollama
CPU only:
docker run -d -p 3000:8080 -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:ollama
Launch Open Web UI in the browser: http://localhost:3000/
Follow the instructions on screen for the login
<aside> 👉
You need to run these commands every time you restart your computer, as they start the docker container. Once you have started the container, you can always access the Open Web UI application on your localhost on port 3000 (or you can change it to any port you want by replacing 3000 with e.g. 5000 in the command shown above)
</aside>
Admin PanelYou may need to open the sidebar by clicking the 3 lines in the top left.

Settings and then to Connections
Configure under Manage OpenAI API Connections
Add the base url (https://litellm.sph-prod.ethz.ch/v1) and your API key
It should look something like this:
