MUMBAI, India, Aug. 24 -- Intellectual Property India has published a patent application (202621080934 A) filed by Symbiosis International Deemed University on June 30, 2026, for Rag-Based Medical Chatbot System With Vector-Indexed Document Retrieval.
Inventors include Sagar Joshi; Dr. Aniket K. Shahade; Dr. Priyanka V. Deshmukh; Dr. Shruti Patil; and Dr. Ketan Kotecha.
The application for the patent was published on August 21, 2026, under issue no. 34/2026.
Abstract: ABSTRACT RAG-BASED MEDICAL CHATBOT SYSTEM WITH VECTOR-INDEXED DOCUMENT RETRIEVAL The present invention discloses a medical chatbot system (100) using retrieval-augmented generation for providing contextually grounded medical information. The system comprises a data ingestion module (110) that parses medical documents, splits them into overlapping text chunks using a text chunking unit (114), and generates vector embeddings using a sentence transformer based embedding generator (116). The embeddings are stored in a FAISS-based vector database (120). A retrieval module (130) transforms user queries into embeddings, performs similarity search to retrieve relevant chunks, and assembles a context block. A response generation module (140) constructs a structured prompt incorporating retrieved context and hallucination prevention instructions, and feeds it to an instruction-tuned large language model (144) that generates evidence-grounded responses. A user interface module (150) displays the response with source document references and page numbers through a source traceability display (156), ensuring transparency and verifiability of medical information. [
Disclaimer: Curated by HT Syndication.
