Create ChatGPT like Interface with your favorite model in 3 steps

In this blog, you will learn how to set up a ChatGPT like interface with your favorite model in just 3 simple steps. Don’t worry if you are not sure which model to choose, you can follow the steps in the video.

STEP 1:

• Download and Install Ollama using this link.
• Verify Ollama is installed by running ollama command on your terminal.

STEP 2:

• Choose a model, for example llama3.2
• Run the model using the command — ollama run llama3.2
• Verify the model is running successfully.

STEP 3:

It’s time to expose the model through a ChatGPT like Interface using Open WebUI.

docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

Note:

You can also run Ollama bundled with Open WebUI in one single step using the below command.

Does not work MAC as Docker does not provide the GPU support yet.

With GPU Support: Utilize GPU resources by running the following command:

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

For CPU Only: If you’re not using a GPU, use this command instead:

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