IT Center Help
FAQ - KI:connect / RWTHgpt
FAQ - KI:connect / RWTHgpt
- RWTHgpt users should contact the IT-ServiceDesk (servicedesk@itc.rwth-aachen.de) for any issues.
- KI:connect users should direct inquiries to the administrators of the respective participating universities. Since the system may behave differently depending on its configuration, the administrators are the first point of contact for questions or issues.
last changed on 03/11/2026
Share this FAQ
- GPT (Generative pre-trained transformers) describe AI models that are able to create human-like texts and content (images, music and more) with the help of previously trained large language models.
last changed on 07/11/2024
Share this FAQ
- Tokens are the unit with which the AI models used measure the length of texts (both for user-generated questions and system-side answers).
These are frequent character strings that occur in a text. The division into tokens is complicated and is not uniformly based on words or characters. - Detailed information on calculating the number of tokens and the background can be found here:
- OpenAI itself offers a calculator that makes it possible to determine the number of tokens and calculation in sentences or texts:
- Tokenizer
Please note that this page is subject to the general data protection guidelines of OpenAI. Please do not insert any personal data (from third parties) here.
- Tokenizer
last changed on 03/10/2026
Share this FAQ
- There is a general token limit for chats with RWTHgpt / KI:connect, which can vary depending on the selected language model or AI tool.
- The maximum number of available tokens, as well as the number of tokens already used, is displayed below the text input field. When the model selection is collapsed, the current usage is also displayed below the selected model. A colored bar provides a visual indication of how much of the respective limits has already been used.
- Once the token limit has been reached, either start a new chat or edit your prompts. If the limit is reached while a response is being generated, the text generation is not interrupted immediately. Instead, the AI model completes its current response, and only then will no further prompts be possible with the selected model for the corresponding time period.
- The limits of the individual AI models are independent of one another. If the limit for one model has been reached, you can simply switch to another model and continue working with it.
- Individual inputs (text and images) are not subject to an additional token limit.
- Depending on the selected language model or AI tool, there are also limits on the number of prompts per hour. These are shown in the model selection.
last changed on 07/07/2026
Share this FAQ
At present, it is not possible to adjust usage limits for individual users. The quotas are standardized for all employees and cannot be increased on an individual basis.
last changed on 06/03/2026
Share this FAQ
- Prompt is a term for a text input that is passed on to the AI.
- Both user input and system-side instructions can be described as a prompt.
- Detailed descriptions and notes can be found here:
last changed on 03/10/2026
Share this FAQ
- Some of the language models available in RWTHgpt can recognize and analyze images (e.g., OpenAI GPT-4o and o1).
- Image generation is not yet possible, but will be made available in 2026.
- KI:connect supports image generation models. Access permissions are configured by administrators at the respective participating universities.
last changed on 03/10/2026
Share this FAQ
- Click on the paperclip icon to the left of the chat
- Select the image to be analyzed
- Now write a prompt that instructs RWTHgpt / KI:connect to analyze the image. You can also set restrictions here.
- For example: “Analyze the attached image (focusing on the font and ignoring colors).
last changed on 03/10/2026
Share this FAQ