Developing LLM-RAG Based Course Assistants to Enhance Students' Team-based Learning

Artificial intelligence encompasses numerous domains, including natural language processing, machine learning, and human-computer interaction. A rapidly evolving area within this field is the use of Retrieval-Augmented Generation (RAG) in large language models (LLMs), which integrates information retrieval with generative capabilities to enhance conversational agents. This project aims to leverage RAG LLMs to develop an intelligent course assistant for the CS2313 computer programming course, addressing the challenges students face in grasping complex programming concepts. By providing instant access to relevant course materials, answering questions, and facilitating interactive learning experiences, the course assistant will not only improve comprehension but also foster engagement and collaboration among students. Instructors will benefit as well, as the assistant streamlines support for common queries, allowing them to focus on personalized feedback and adapt teaching strategies based on insights gathered. The integration of this assistant will enhance engagement and retention by facilitating interactive learning experiences and promoting collaboration among students in team-based projects. Ultimately, this innovative tool aims to create a more effective and engaging educational environment.