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{206817,
        author = {Rashmi P},
        title = {A Retrieval-Augmented Generation (RAG) Framework for Generating AN Accurate and Real Time Educational Content},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {560-565},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206817},
        abstract = {The growing demand for intelligent learning systems has brought to the fore the significance of context-aware, real-time content generation technologies. The present paper presents a comprehensive Retrieval-Augmented Generation (RAG) system with Google Gemini models for facilitating accurate question-answering from user-uploaded learning documents. The proposed system offers multimodal input — text, voice and picture-based search queries — enabling users to interact intuitively and naturally. Leaning on FAISS for optimized vector indexing and LangChain for runtime chaining of dynamic retrievals, the platform delivers high-precision matching of documents. Enriched with user authentication, session logging, inappropriate query detection and feedback logging, the system also has an admin dashboard to monitor user behavior and control content too. Offline text-to-speech synthesis and auto-generated query resolution reminders are some features that enhance the user experience quite significantly too. The solution suggested offers a flexible, secure and user-centered approach to the presentation of educational content with potentially helpful implications for customized learning environments.},
        keywords = {FAISS Vector store, Google Gemini, LLM, LangChain, Retrieval-Augmented Generation (RAG), Streamlit},
        month = {July},
        }