UniGPT Revisited: From a Simple Chatbot to an API-First AI Platform — Two Years of On-Premises LLM Operations
Radas, Jonathan; Risse, Benjamin; Vogl, Raimund
Research article in edited proceedings (conference) | Peer reviewedAbstract
In 2024, we introduced uniGPT, an on-premises Kubernetes-based LLM platform at a major German university designed for GDPR compliance, digital sovereignty, and avoiding vendor lock-in. This paper evaluates nearly two years of operation (May 2024 - February 2026), tracing its evolution from a simple chatbot into a multi-modal, API-first AI infrastructure. Using the TOE framework, we analyze this progression as an iterative design cycle triggered by technological, organisational, or environmental factors. We detail 8 key iterations - including frontend and inference engine swaps, adding an OpenAI-compatible API layer, multi-modal services, and RAG pipelines. Notably, we find that >99% of usage now occurs via API rather than the chat frontend. Finally, we offer generalizable lessons for institutions building sustainable on-premises AI infrastructure in higher education.
Details about the publication
Authors from the University of Münster
| Radas, Jonathan | |
| Risse, Benjamin | |
| Vogl, Raimund |
Distinctions received for the publication
| EUNIS Elite Award 2026 in the category: Honourable mention Awarded by: European University Information Systems organisation Award given to: Radas, Jonathan; Risse, Benjamin; Vogl, Raimund Announced at: 03/06/2026 | Date of awarding: 03/06/2026 Type of distinction: Research award or other distinction |