On the Subject of TBC Chatbot
• Implemented a chatbot leveraging the LLaMA3 language model, tailored specifically for TBC College data.
• Created an admin panel for managing the knowledge base, allowing for the addition and processing of PDF documents, which are then converted into embeddings and stored in a vector database for efficient retrieval.
• Integrated the LLM model chain with a Prompt Template using the Retrieval-Augmented Generation (RAG) technique with GPU (CUDA), enhancing the accuracy and relevance of chatbot responses.
• Built and deployed an API using Flask, successfully integrating it with a user-friendly chatbot interface to enhance user interaction and accessibility.
Project Genre
Technologies Used