| 1 | # Open WebUI |
| 2 | |
| 3 | [Open WebUI](https://github.com/open-webui/open-webui) is an extensible, feature-rich, |
| 4 | and user-friendly self-hosted AI platform designed to operate entirely offline. |
| 5 | It supports various LLM runners like Ollama and OpenAI-compatible APIs, |
| 6 | with built-in RAG capabilities, making it a powerful AI deployment solution. |
| 7 | |
| 8 | To get started with Open WebUI using vLLM, follow these steps: |
| 9 | |
| 10 | 1. Install the [Docker](https://docs.docker.com/engine/install/). |
| 11 | |
| 12 | 2. Start the vLLM server with a supported chat completion model: |
| 13 | |
| 14 | ```console |
| 15 | vllm serve Qwen/Qwen3-0.6B-Chat |
| 16 | ``` |
| 17 | |
| 18 | !!! note |
| 19 | When starting the vLLM server, be sure to specify the host and port using the `--host` and `--port` flags. |
| 20 | For example: |
| 21 | |
| 22 | ```console |
| 23 | vllm serve <model> --host 0.0.0.0 --port 8000 |
| 24 | ``` |
| 25 | |
| 26 | 3. Start the Open WebUI Docker container: |
| 27 | |
| 28 | ```console |
| 29 | docker run -d \ |
| 30 | --name open-webui \ |
| 31 | -p 3000:8080 \ |
| 32 | -v open-webui:/app/backend/data \ |
| 33 | -e OPENAI_API_BASE_URL=http://0.0.0.0:8000/v1 \ |
| 34 | --restart always \ |
| 35 | ghcr.io/open-webui/open-webui:main |
| 36 | ``` |
| 37 | |
| 38 | 4. Open it in the browser: <http://open-webui-host:3000/> |
| 39 | |
| 40 | At the top of the page, you should see the model `Qwen/Qwen3-0.6B-Chat`. |
| 41 | |
| 42 |  |