Set Up Open WebUI with Ollama: Your Own ChatGPT

Open WebUI is a self-hosted ChatGPT alternative. Pair it with Ollama for a fully local, private AI chat.

Prerequisites

• Ollama installed and running (ollama run llama3.2 at least once)
• Docker (or use the pip install)

Docker install (recommended)

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

Open http://localhost:3000. Create an admin account.

Connect Ollama

In Open WebUI settings, add Ollama as a connection. URL: http://host.docker.internal:11434 (or http://localhost:11434 if not using Docker). Save. You'll see your local models in the model selector.

Start chatting

Select a model (e.g., Llama 3.2), type your prompt. Everything runs locally. No data leaves your machine.

Optional: Add OpenAI for hybrid use

You can add your OpenAI API key too. Use local models for sensitive tasks, cloud for heavy lifting. Open WebUI lets you switch per conversation.