Conversational-Agent for Patient Information Leaflet

Conversational agents offer a natural way to interact with users, providing a wide range of services in different fields. In the healthcare sector, conversational agents can be used to provide information about medications, diseases and treatments. In this paper, we present a conversational agent designed to provide information about Patient Information Leaflets (PIL), originated from the SeSaMo web service. The conversational agent is powered by a Large Language Model and uses a Retrieval-Augmented Generation (RAG) framework to generate the text. We present the preliminary results of the system, showing that the RAG framework can be used to generate high-quality text. The next steps will be to expand the architecture to handle questions about multiple medications and to provide information about the interactions between them, evaluating the system with a larger dataset of questions and answers.