Configuring Open WebUI
- WHAT?
Open WebUI is a Web-based application that allows you to interact with AI models.
- WHY?
To configure Open WebUI according to both user and administrator requirements and preferences.
- EFFORT
To understand how to configure selected parts of Open WebUI takes less than 1 hour.
- REQUIREMENTS
The procedures in this article assume that the following points are already fulfilled:
You have successfully deployed the SUSE AI.
You can access the Open WebUI interface in your Web browser.
Your Open WebUI user account has been created and you have received the login credentials.
You have navigated your Web browser to the URL of your instance of Open WebUI and logged in with your credentials.
Selected tasks require the Open WebUI administrator privileges.
1 Introduction #
This topic explains what Open WebUI is and describes basics of its user interface.
1.1 What is Open WebUI? #
Open WebUI is a Web-based interface that allows you to interact with AI models, such as large language models (LLMs). It simplifies working with AI by providing a graphical user interface (GUI) instead of relying on command-line tools. The goal of Open WebUI is to make AI accessible to a broader audience, including those without technical expertise in AI development.
1.2 What are key benefits of using Open WebUI? #
- Interaction with AI models.
You can load a preferred AI model and interact with it using prompts in your natural language.
- Custom data handling for RAG workflows.
Open WebUI allows you to upload documents or specify URLs of pages that the AI can parse and reference during interaction, often used in RAG workflows.
- User-friendly interface.
By providing a graphical user interface, Open WebUI makes AI tools more accessible to non-technical users. It helps them utilize the power of advanced AI models without needing technical knowledge.
- Data privacy
You can deploy Open WebUI locally or in a private environment. Such deployment is required for users concerned about privacy and data security.
1.3 Open WebUI user interface #
The Open WebUI interface consists of three parts:
- Top panel
Contains controls to manage tasks related to the current chat, such as:
Maximizing the chat window.
Selecting an AI model for the current chat.
Viewing and managing advanced settings for the current chat.
Changing settings related to the current user.
Viewing archived chats of the current user.
Accessing the .
- Left side bar
Contains links to perform the following tasks:
Start a new chat.
Access the administrator's .
Search the content of the current chat.
Browse through the history of your chats.
- Main chat window
Displays your recent queries and corresponding answers provided by the AI. By using the prompt field at the bottom, you can accomplish the following tasks related to the current chat:
Enter a query that you want the AI to answer.
Upload custom documents that you want the AI process and use as a source of information when answering.
Select a document, collection of documents or URL to extend the AI model's knowledge base.
Select a preconfigured AI model for the current chat.
Interrupt the chatbot from answering if you are already satisfied with the provided information.
1.4 Workspace #
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
The area of the Open WebUI is a place where you can manage important parts of the AI stack. To access it, click in the top of the left panel. consists of the following parts:
- Models
Manage existing AI modules or add your custom AI module based on an existing one. Refer to https://docserv.suse.de:8085/suse-ai/1.0/html/openwebui-configuring/index.html#openwebui-managing-models for more details and related procedures.
- Knowledge
Manage information sources—such as custom documents—that the users can use to enhance the current AI model's knowledge base. This helps to make the model's responses more contextual. Refer to for more details and related procedures.
- Prompts
Define system prompts that guide the AI model to respond accurately in the style and format that you prefer. Refer to for more details and related procedures.
- Tools
include a collection of Python snippets that enhance interaction and expand functionality for working with AI models. Tools can, for example, integrate additional data sources to the model knowledge base, such as databases.
- Functions
include a collection of Python snippets that can perform mostly internal data processing to automate workflows or manage text processing.
1.5 Admin Panel #
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
The is a centralized control interface for administrators to manage system settings, user accounts and overall application functionality.
To access the , click your avatar button in the top right of the Open WebUI screen and select .
1.6 For more information #
The upstream Open WebUI documentation is hosted at https://docs.openwebui.com/.
2 Setting the default system prompt #
In Open WebUI, you can set system prompts in several contexts—for the current chat, for the current user, or for a specific AI model. While the prompt set for the current chat overrides the user and model prompts, the user-specific prompt overrides the model prompt only.
2.1 System prompt for the current chat #
In the top right of the Open WebUI window, click the icon.
Unfold the tab and paste your system prompt into the empty input text field.
Figure 3: Chat-specific system prompt #Close the window to apply the change. The responses from the AI model during the current chat session will be affected by the system prompt that you entered.
2.2 System prompt for the current user #
In the top right of the Open WebUI window, click your avatar icon to open the user menu.
Select to open your preferences and click the tab.
Paste your system prompt in the text field.
Figure 4: User-specific system prompt #Confirm with and close the window. The responses from the AI model for the current user will be affected by the system prompt that you entered.
2.3 System prompt for an AI model #
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
In the Open WebUI interface, click in the upper part of the left panel.
Select in the top menu and scroll to the AI model whose system prompt you want to set. Use the pager at the bottom if the model is not listed on the current screen.
Click the corresponding pen icon at its right to open the dialog for editing the model.
In the section, specify the system prompt in the field.
Figure 5: Model system prompt #Confirm with .
2.3.1 For more information #
Find more details about system prompts in https://docserv.suse.de:8085/suse-ai/1.0/html/AI-system-prompts/index.html.
3 Setting the default AI model #
In Open WebUI, you can specify an AI model in several contexts—for the current chat, for the current user or for the system default model. While the AI model set for the current chat overrides the user and system model, the user-specific model overrides the system model only.
3.1 AI model for the current chat #
This topic explains how to specify an AI model for the current chat session.
In the top left of the Open WebUI chat window, click either the currently selected model name or the message saying that no model is specified.
From the drop-down list, select your preferred AI model for the current chat session.
Figure 6: Chat-specific AI model #
Tip: Your default modelTo make the selected model your default one, click next to the AI model name.
Tip: Multiple AI modulesYou can select multiple AI modules by clicking the plus sign next to the name of the already selected module.
Your prompts will now be precesses by the selected AI model.
3.2 AI model for the current user #
This topic explains how to specify the default AI model for the current user.
In the top right of the Open WebUI window, click your avatar icon to open the user menu.
Select to open your preferences and click the tab.
From the drop-down list, select your default AI model.
Figure 7: Default user AI model #Confirm with and close the window. Your prompts will now be precesses by the selected AI model unless overridden by selecting a different AI model for the current chat.
3.3 Default system AI model #
This topic explains how to set the default AI model for all users. The model is then used for new chats if not overridden by specifying a model for a user or a chat.
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
In the top right of the Open WebUI window, click your avatar icon to open the user menu and select .
Click in the top left of the and select from the left menu.
Figure 8: Default system AI model #In the section, select the default system AI model. Confirm with .
4 Managing custom AI models #
In Open WebUI, you can create custom AI models based on existing models. Later on, you can modify its settings, or share, clone or delete it.
4.1 Creating custom models #
This procedure shows how to create custom AI models using Open WebUI.
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
In the Open WebUI interface, click in the upper part of the left panel.
Select in the top menu and click the link under the search bar.
Figure 9: Managing AI models #By clicking the big + sign at the top of the form, you can upload an avatar image for your model.
Enter of your new model and modify the if you are not happy with the provided one.
Specify the base AI model on which your model will be based on.
(Optional) Enter a short description of your AI model.
Figure 10: Avatar, name and description of a new AI model #(Optional) To direct the AI model's responses, specify a . Find more details about system prompts in https://docserv.suse.de:8085/suse-ai/1.0/html/AI-system-prompts/index.html.
TipBy clicking the small link below the system prompt field, you can fine tune the model's behavior by modifying its advanced settings.
(Optional) Specify one or more . They will be shown on the model's chat welcome screen.
Figure 11: System prompt and prompt suggestions #(Optional) To extend the model's knowledge base, select one or more documents or collections of documents from the preconfigured list.
Figure 12: Extending the model's knowledge base #(Optional) In the , , and sections, activate the items that you want your model to use.
Describe the model with custom tags so that other users can identify it easily.
Figure 13: Capabilities and tags #TipTo view the JSON representation of your model, click the small link right of the label.
Save your changes with the button.
4.2 Modifying existing models #
This procedure shows how to modify an existing custom AI model using Open WebUI.
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
In the Open WebUI interface, click at the top of the left panel and select .
In the list of AI models, hover the mouse over the model that you want to delete and click the pen icon on its right.
On the model editing screen, you can modify the settings that are described in Section 4.1, “Creating custom models”.
Save your changes with the button.
4.3 Cloning existing models #
This procedure shows how to clone an existing custom AI model using Open WebUI.
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
In the Open WebUI interface, click at the top of the left panel and select .
In the list of AI models, hover the mouse over the model that you want to delete and click the three dots on its right.
From the contextual menu, select to open the same form as described in Section 4.1, “Creating custom models” with all settings copied from the original model. The field has
(Clone)appended.Review the settings and create the cloned AI model with .
4.4 Importing exported models #
This procedure shows how to import AI models using Open WebUI.
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
In the Open WebUI interface, click at the top of the left panel and select .
Click the button at the bottom of the screen.
In the file selector, specify the path to the JSON file with the exported models' definitions. Confirm with .
Important: Models with identical IDsAI models with IDs identical to existing models will not be imported.
4.5 Exporting existing models #
This procedure shows how to export an existing custom AI model using Open WebUI.
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
In the Open WebUI interface, click at the top of the left panel and select .
In the list of AI models, hover the mouse over the model that you want to delete and click the three dots on its right.
From the contextual menu, select .
In the file selector, specify the path where you want to save the exported JSON file. Confirm with .
4.6 Exporting all existing models #
This procedure shows how to export all existing AI models using Open WebUI.
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
In the Open WebUI interface, click at the top of the left panel and select .
Click the button at the bottom of the screen.
In the file selector, specify the path where you want to save the exported JSON file. Confirm with .
4.7 Deleting existing models #
This procedure shows how to delete an existing custom AI model using Open WebUI.
Using the Open WebUI interface, you can delete previously created AI models.
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
In the Open WebUI interface, click at the top of the left panel and select .
In the list of AI models, hover the mouse over the model that you want to delete and click the three dots on its right.
From the contextual menu, select and then apply with .
5 Managing user accounts #
Open WebUI provides role-based access control (RBAC). Each user is assigned one of the available roles. The role defines whether the user has privileges to perform administration tasks.
5.1 User roles in Open WebUI #
Open WebUI offers three user roles: “pending”, “user” and “admin”. Each role is in detail described in the following sections.
5.1.1 The “pending” role #
Pending users can log in but can only view the screen with the administrator name and e-mail. This is the default role for a newly created user account before the administrator accepts it and assigns it the “user” role.
5.1.2 The “user” role #
Users with this role can perform the following tasks:
- Chat permissions
Create new chats with the preconfigured models.
View own chats, including archived chats.
Pin, rename, clone, archive or unarchive, share, delete, add tags to, and remove tags from existing chats.
Generate an overview of a chat, view artifacts, copy content and download chats.
Copy, edit and delete their own messages in a chat.
Edit, copy and read aloud the responses. View response generation information. Generate images. Mark answers as good or bad. Continue responding and regenerate model messages in a chat.
- Current chat controls
Modify valves from the tools and functions available on the system.
Define the system prompt to be used by the current chat.
Modify advanced chat-specific generation parameters.
- Current user settings
Select theme and language. Activate or deactivate notifications. Define default system prompt and modify advanced generation parameters.
Set the default model. Set the user interface, chat and audio related preferences.
Personalize the interaction with the AI model by adding “memory”—personal details about yourself—to make responses tailored to you.
Set audio preferences.
Import and export chats. Archive and delete all user chats.
Change your personal details such as name, password and profile image. View JWT token and create new API key.
View the installed Open WebUI and Ollama version.
5.1.3 The “admin” role #
Administrators have full access to Open WebUI resources and can control user management and systems settings. The first Open WebUI account has the “admin” role. Subsequent administrators get their role from existing administrators.
Administrator's task and settings are included either on the or in the .
Administrators have the permissions that the “user” role has with the following additional privileges.
- ›
Add new users.
View all users and their role, name, e-mail, OAuth 2.0 ID, last active date and the user creation date.
Edit name, email and password, and delete all users, except for other administrators.
View and delete chats of all users, except for other administrators.
Change the role of all users, except their own and the first administrator.
- ›
Enable or disable new sign-ups. Set the default user role. Enable or disable viewing the administrator details on the screen. Enable or disable chat sharing, and message rating. Set the JWT expiration and webhook URL.
Enable or disable chat deletion, chat editing and temporary chat. Set the default model and specify allowed models.
View, change and add OpenAI API URL and Ollama API URL.
Update all models, pull models from ollama.com, delete, create and upload models.
Change documents settings, set the RAG template, and reset document storage.
Enable or disable Web search, change the Web search engine, and set Web loader settings.
Set the default model used for the title generation. Change the default prompt suggestions for the screen.
Change audio settings.
Enable or disable image generation and change image generation settings.
Change pipelines settings.
Import or export configuration files, download database, and export all chats from all users.
- ›
Manage models. Add models by pulling from ollama.com or by creating custom models from base models. Change order of models or hide models from model list.
- ›
Manage collections of documents. Add documents to collections.
- ›
Manage system prompts. Share prompts, import and export all prompts.
- ›
Manage tools. Import and export tools.
- ›
Manage functions functions. Enable or disable functions. Globally enable or disable functions. Import and export functions. Change valves settings.
5.1.4 Creating user accounts #
This topic explains how to create a new user account with an assigned role in Open WebUI. It also describes how to create multiple user accounts from a CSV list.
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
Click your avatar button at the top right of the chat screen and select .
On the screen, click the “+” sign at the top right.
Figure 15: Creating new users #On the screen, select the user role and enter the user name, e-mail and password.
Confirm with .
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
Click your avatar button at the top right of the chat screen and select .
On the screen, click the “+” sign at the top right.
On the screen, specify the path to you CSV file with the list of user accounts to be created.
Figure 16: Creating multiple users #TipThe CSV list needs to have the four fields
Name,Email,Password,Roleper line separated by commas, for example:Example User,tux@example.com,SECRET_PASSWD,user
Confirm with .
5.1.5 Assigning roles to existing users #
This topic explains how to assign one of the available roles to an existing user account. To assign the role when creating a new user account, refer to Section 5.1.4, “Creating user accounts”.
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
Click your avatar button at the top right of the chat screen and select .
On the screen, scroll to the user whose role you want to modify. Use the pager at the bottom if the user is not listed on the current screen.
Figure 17: Assigning user role #Click the role button left to the user name to cycle through “pending” → “user” → “admin” role.
5.1.6 Modifying existing user accounts #
This topic explains how to modify existing user accounts in Open WebUI.
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
Click your avatar button at the top right of the chat screen and select .
On the screen, scroll to the user whose account you want to modify. Use the pager at the bottom if the user is not listed on the current screen.
Click the corresponding pen icon at their right to open the dialog.
Figure 18: Modifying user accounts #Modify the user's e-mail, name or password and confirm with .
5.1.7 Revoking access to Open WebUI #
This topic explains how to revoke access to Open WebUI for an existing user account.
You need to have Open WebUI administrator privileges to access configuration screens or settings mentioned in this section.
Click your avatar button at the top right of the chat screen and select .
On the screen, scroll to the user whose access to Open WebUI you want to revoke. Use the pager at the bottom if the user is not listed on the current screen.
To revoke the access while maintaining the user account, click the user's role button left to their name until it becomes “pending”.
To delete the user account from the system, click the trash icon at the right and confirm the deletion.
6 Legal Notice #
Copyright© 2006–2024 SUSE LLC and contributors. All rights reserved.
Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or (at your option) version 1.3; with the Invariant Section being this copyright notice and license. A copy of the license version 1.2 is included in the section entitled “GNU Free Documentation License”.
For SUSE trademarks, see https://www.suse.com/company/legal/. All other third-party trademarks are the property of their respective owners. Trademark symbols (®, ™ etc.) denote trademarks of SUSE and its affiliates. Asterisks (*) denote third-party trademarks.
All information found in this book has been compiled with utmost attention to detail. However, this does not guarantee complete accuracy. Neither SUSE LLC, its affiliates, the authors, nor the translators shall be held liable for possible errors or the consequences thereof.