IT Center Changes

Features:

• Users can now create and manage their own API keys
• [ADMIN] API access can now be enabled or disabled per user group
• [ADMIN] Reporting has been expanded to include API usage analytics
• [ADMIN] New setting for maximum parallel requests per user

Bugfixes and Improvements: 

• Fixed issues with title generation for chats with long completions

Features:

• Support for new models:
  • gpt-oss-120b and gpt-oss-20b
• Chat export function added
• [ADMIN] Admins can now see and use all user groups

Bugfixes and Improvements:

• Improved display of formulas
• Document content is now sent to LLMs as a user message (previously system)
• Strict role sequence in prompts (no two consecutive messages with the same role)
• Improvements to timeouts and retries
• Various design optimizations
• [ADMIN] Added soft delete function for deployments
• [ADMIN] Added translatable labels for user groups
• The correct time period is now displayed when message limits are reached
• Title generation with Mistral Small now works correctly
• The sidebar can now be expanded and collapsed again

Features:

• Newly supported models:
  • gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-chat
  • Beta support for various models from the Llama, Mistral, Gemma, Qwen, Teuken, and InternVL families
• Users with access to multiple user groups can now switch between groups in the frontend
• Added notifications for automatically deleted chats, along with a new modal for manually deleting or extending these chats
  • [ADMIN] Configurable retention period for automatic chat deletion per tenant
• [ADMIN] New report: “Hourly Activity Heatmap”
• [ADMIN] Tenants can now publish info banners visible to all users within the tenant
• [ADMIN] Automatic email notifications at 80%, 90%, and 100% of a user group’s hard limit consumption
• [ADMIN] For each deployment, an optional data processing region (Germany, EU, Worldwide) can be selected; this information is also displayed in the frontend

Bugfixes and Improvements:

• Content pages are now displayed correctly across all tenants
• Optimized print layout for chat history
• [ADMIN] Help menu entries and deployments are now sortable via drag & drop
• [ADMIN] In the deployment modal, model-type-specific parameters are only displayed after a model has been selected
• [ADMIN] “Reasoning Effort Level” is now a mandatory field; the maximum token limit can no longer be set to 0
• [ADMIN] Model selection in the deployment modal is now sorted alphabetically
• [ADMIN] For supported models, a price can now be defined for cached input tokens
• [ADMIN] Deployments can now be duplicated
• [ADMIN] Deployments are automatically set to inactive if their endpoint is deleted
• [ADMIN] Improved axis labeling in reports

Features:

• [ADMIN] New theming options: different backgrounds, more colors adjustable, own logos possible
• [ADMIN] User groups can now be deactivated
• [ADMIN] For each user group, you can now set whether no, one or an unlimited number of documents can be uploaded per chat

Bugfixes and Improvements:

• Summer theme revised
• Improvement in cost tracking: Prompt caching and various error cases are now taken into account
• The chat deletion dialog now always shows the correct chat title
• File upload button is reactivated after a file that has already been uploaded is removed
• [ADMIN] Deployments can now be sorted using buttons in the deployment overview
• [ADMIN] Input fields in the deployment dialog now have a short Explanation

Based on RWTHgpt, RWTH has launched the state-wide project KI:connect.nrw on July 1, 2024, which is funded by the NRW Ministry of Culture and Science. As part of this project, RWTH is making our central web application available to the state’s universities. The nationwide rollout began in July 2025.

Further information can be found here:

Latest News