Enhancing Healthcare Accessibility: A RAG- Based Medical Chatbot Using Transformer Models
Agrim Kulshreshtha, Aditya Choudhary, Tejas Taneja, Seema Verma
Abstract
Significant improvements in patient involvement and medical diagnosis have resulted from the use of AI in healthcare. This paper introduces a transformer-based medical chatbot that uses LangChain and Retrieval-Augmented Generation (RAG) to provide accurate, context-aware healthcare support. The chatbot solves issues with healthcare accessibility, especially in underprivileged areas, and improves user happiness and diagnostic accuracy by utilizing large medical datasets. The aim of the work is to produce dependable and contextually relevant responses by refining refined LLaMa models using RAG approaches. It also looks at how AI-powered chatbots might help with data privacy, timely medical advice, and healthcare disparity reduction. The results highlight how AI-powered virtual health assistants might improve clinical judgment, lessen the workload for medical staff, and offer affordable patient care options.