Real-Time Retrieval-Augmented Generation in Healthcare Using LLMs for Audio-based Querying and Retrieval

– Healthcare information systems are critical for efficient decision-making and patient care. This paper presents a real-time audio-query-driven retrieval-augmented generation (RAG) system using a large language model (LLM) that interfaces with a healthcare database and a vector database. The system allows users to make real-time audio queries, retrieves the necessary information using LLM tools, and delivers audio responses. Comparative performance evaluations between traditional healthcare information systems and our proposed LLM-based approach show significant improvements in query throughput, cost-efficiency, and response time.