This guide is verified with Open WebUI setup through Manual Installation.
Local LLM Setup with IPEX-LLM on Intel GPU
IPEX-LLM is a PyTorch library for running LLM on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc A-Series, Flex and Max) with very low latency.
This tutorial demonstrates how to setup Open WebUI with IPEX-LLM accelerated Ollama backend hosted on Intel GPU. By following this guide, you will be able to setup Open WebUI even on a low-cost PC (i.e. only with integrated GPU) with a smooth experience.
Start Ollama Serve on Intel GPU
Refer to this guide from IPEX-LLM official documentation about how to install and run Ollama serve accelerated by IPEX-LLM on Intel GPU.
If you would like to reach the Ollama service from another machine, make sure you set or export the environment variable OLLAMA_HOST=0.0.0.0 before executing the command ollama serve.
Configure Open WebUI
Access the Ollama settings through Settings -> Connections in the menu. By default, the Ollama Base URL is preset to https://localhost:11434, as illustrated in the snapshot below. To verify the status of the Ollama service connection, click the Refresh button located next to the textbox. If the WebUI is unable to establish a connection with the Ollama server, you will see an error message stating, WebUI could not connect to Ollama.
If the connection is successful, you will see a message stating Service Connection Verified, as illustrated below.
If you want to use an Ollama server hosted at a different URL, simply update the Ollama Base URL to the new URL and press the Refresh button to re-confirm the connection to Ollama.