The International Conference for High Performance Computing, Networking, Storage, and Analysis

Workshops Archive

A GPU-Accelerated RAG-Based Telegram Assistant for Supporting Parallel Processing Students


Workshop: EduHPC-25: Workshop on Education for High Performance Computing

Authors: Guy Tel-Zur (Ben-Gurion University of the Negev)


Abstract: This project addresses a critical pedagogical need: offering students continuous, on-demand academic assistance beyond conventional reception hours. We present a domain-specific Retrieval-Augmented Generation (RAG) system powered by a quantized Mistral-7B Instruct model and deployed as a Telegram bot. The assistant enhances learning by delivering real-time, personalized responses aligned with the "Introduction to Parallel Processing" course materials [1]. GPU acceleration significantly improves inference latency, enabling practical deployment on consumer hardware.




Back to EduHPC-25: Workshop on Education for High Performance Computing Archive Listing



Back to Full Workshop Archive Listing