Date
Publisher
arXiv
This project addresses a critical pedagogical need: offering students
continuous, on-demand academic assistance beyond conventional reception hours.
I 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. GPU
acceleration significantly improves inference latency, enabling practical
deployment on consumer hardware. This approach demonstrates how consumer GPUs
can enable affordable, private, and effective AI tutoring for HPC education.
Study at a glance
- Question: Can an AI messaging bot run on consumer hardware to provide students with continuous, course-specific tutoring?
- Setting and data: Course materials from an "Introduction to Parallel Processing" course.
- Method: System development and technical demonstration.
Why it matters
Students have a critical pedagogical need for continuous, on-demand academic assistance beyond conventional reception hours.
Key findings
- In an introduction to parallel processing course, a messaging assistant provided continuous, personalized answers aligned with class materials to support student learning.
- Graphics processing hardware significantly improved response speeds, making it practical to run the AI assistant on standard consumer equipment.
- Standard consumer hardware can support affordable, private, and effective AI tutoring for high-performance computing education.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
