LEVERAGING LARGE LANGUAGE MODELS FOR THE CREATION OF AN AI LECTURE CHATBOT AVATAR: A COMPREHENSIVE EXPLORATION AND IMPLEMENTATION

This project aimed to design and implement an AI lecture chatbot by leveraging large language models (LLMs) and learning management systems (LMS). LLMs, such as ChatGPT, are trained on vast amounts of data, enabling advanced natural language processing and understanding capabilities. The integration of LLMs and LMS was assessed by surveying 36 students from Edo State University Uzairue. The findings revealed that 80.6% of students were from the Faculty of Engineering, 40% were familiar with AI chatbots, and 85% endorsed the adoption of AI in education. The novelty of this project lies in its unique approach to combining LLMs with LMS features to create an AI lecture chatbot tailored explicitly for the educational context of Edo State University Uzairue. The system is based on a Retrieval-Augmented Generation (RAG) pipeline. Users upload files, which are processed using NLP algorithms to split the text into chunks. These chunks are converted into vector embeddings and stored in a vector database. The chatbot processes user queries by matching them with the relevant text chunks, generating accurate and contextually relevant responses. Despite a small sample size and a focus on computer engineering students, the study provides valuable insights into the positive reception and potential impact of AI in education. Future research should expand the sample size and include a more diverse range of students to validate and extend the findings. This project demonstrates the potential of AI lecture chatbots to enhance educational experiences and suggests avenues for further research to explore AI's transformative potential in education.