Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{191656,
        author = {Patil Surya Narayana Reddy and Chapala Narasimhulu and Syed Md Sameer and Kanchi Gokul Raj and M Sivamma and Dr. C V Madhusudhan Reddy},
        title = {Intelligent RAG-Based Conversational Assistant for Medical and Healthcare Awareness},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {7488-7492},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191656},
        abstract = {The increasing reliance on digital platforms for medical information has highlighted the need for accurate, reliable, and context-aware healthcare advisory systems. General AI chatbots and unverified online sources often provide misleading or incomplete information that can negatively impact healthcare awareness and education. The objective of this project is to develop an Intelligent Retrieval-Augmented Generation (RAG) based medical conversational assistant that delivers trustworthy and educational medical information while avoiding diagnostic or prescriptive outputs. The proposed system integrates document retrieval techniques with large language models to ensure that the generated responses are grounded in verified medical documents. Medical knowledge sources are pre-processed, embedded using sentence-transformer models, and stored in a FAISS vector database for efficient similarity-based retrieval. User queries are matched with relevant medical contexts, which are then supplied to the language model through a controlled RAG pipeline orchestrated using Lang Chain. 
Experimental evaluation shows that the RAG-based approach significantly improves response accuracy, contextual relevance, and reliability compared with standalone language models, while reducing hallucinations and misinformation. The system is well suited for medical students, healthcare awareness platforms, and hospital information desks. Overall, this project demonstrates the effective application of AI and RAG techniques in building safe, scalable, and reliable medical information systems.},
        keywords = {Health Information System, Artificial Intelligence, Natural Language Processing, Retrieval-Augmented Generation, Machine Learning for Health Care, Intelligent Information Retrieval, Semantic Search.},
        month = {January},
        }