Olares

English

简体中文

English

简体中文

Appearance

Set up Open WebUI for local AI chat ​

Open WebUI is a self-hosted chat interface that lets you interact with local models on your Olares device.

This guide walks you through installing Open WebUI, connecting it to a local model, and starting your first conversation.

Learning objectives ​

In this guide, you will learn how to:

  • Install Open WebUI on Olares.
  • Create an admin account.
  • Connect Open WebUI to a local model.
  • Start a chat session with your configured model.

Prerequisites ​

Before you begin, you need:

  • An Olares device running Olares 1.12.7 or later, with sufficient disk space and memory.
  • Access to Router for local model connections.
  • The following model:
    Model typeModelHow to get it
    ChatQwen3.8-27B (llama.cpp)Install from Market
Optional: Use a different model

Install another chat model from Market, or create a model instance with Engine Base apps. Then select it as the default chat model on Router's Default models page. Clients configured with default-chat use the new default without changing their model settings.

To keep a client on one specific model, use the full model name from Router's How to call this model window instead.

Install Open WebUI ​

  1. Open Market and search for "Open WebUI".

    Open WebUI

  2. Click Get, and then click Install. Wait for the installation to finish.

Create an admin account ​

The first time you launch Open WebUI, you need to create a local administrator account to manage your models and settings.

  1. Open Open WebUI from the Launchpad.

  2. On the welcome page, click Get started.

  3. Enter your name, email, and password to create the admin account.

    Create account

Get model connection details ​

To connect Open WebUI to a model, you first need to collect the model's connection information from Router.

  1. Open Router from Launchpad. On Default models, set Qwen3.8-27B (llama.cpp) as the default chat model.

  2. Go to LLM, find Qwen3.8-27B (llama.cpp), and click View connection example on its row.

  3. In How to call this model, select Apps in Olares and copy the Base URL, including /v1.

  4. Use default-chat as the model name in the client. Apps in Olares do not need a Router API key. Leave the key empty where possible, or use olares if the client requires a value.

    default-chat is a routing name and is not returned by the model-list API. Add it manually if the client fetches a model list. If the client only supports selecting a listed model, use the full model name from Router instead.

Configure the connection in Open WebUI ​

With the connection details ready, add the model as an OpenAI-compatible provider in Open WebUI.

  1. In Open WebUI, click your profile icon and select Admin Panel.

  2. Select the Settings tab, and then choose Connections from the left sidebar.

  3. To the right of Manage OpenAI API Connections, click add to add a new connection.

  4. In the API Base URL field, enter the Base URL you copied from Router. For example, https://router.<your-olares-domain>/v1.

  5. Expand Advanced, use Add a Model ID to add default-chat, and set Auth to None for this Olares app.

  6. Click Save. Open WebUI verifies the connection automatically.

    When you see the "OpenAI API settings updated" message, the connection is established.

Start chatting ​

Once you connect a model, you are ready to use the chat interface.

  1. In the chat area, select your configured model.

    Select model

  2. Enter your prompt in the text box, and then press Enter to start your conversation.

    Chat with LLM

Learn more ​