UGC Approved Journal no 63975(19)
New UGC Peer-Reviewed Rules

ISSN: 2349-5162 | ESTD Year : 2014
Volume 13 | Issue 3 | March 2026

JETIREXPLORE- Search Thousands of research papers



WhatsApp Contact
Click Here

Published in:

Volume 13 Issue 3
March-2026
eISSN: 2349-5162

UGC and ISSN approved 7.95 impact factor UGC Approved Journal no 63975

7.95 impact factor calculated by Google scholar

Unique Identifier

Published Paper ID:
JETIR2603083


Registration ID:
576923

Page Number

a597-a602

Share This Article


Jetir RMS

Title

PRISM: AI-POWERED LEARNING AND PREPARATION PLATFORM

Abstract

A personalized learning platform that employs Retrieval-Augmented Generation (RAG) to enable students to interact with their study materials through an AI-powered assistant. The system comprises a web-based interface built with React that allows users to upload educational documents in various formats including PDF, DOCX, TXT, and YouTube video transcripts, which are then processed through a text extraction and chunking pipeline. Document chunks are encoded into 768-dimensional vector embeddings using the all-mpnet-base-v2 sentence transformer and stored in a Pinecone vector database for efficient semantic retrieval. When users pose questions, the system retrieves relevant passages from their uploaded documents and conditions a language model's response generation on this retrieved context, ensuring factually grounded and document-specific answers. The platform includes eight integrated learning modes: interactive chat-based question answering, automated quiz generation, AI-scored mock tests, virtual interview sessions, a swipeable flashcard feed (Doomscroll), per-page PDF analysis with graded questions, in-browser PDF annotation with AI-powered Q&A on highlighted text, and rich note-taking. The backend implements a FastAPI server with asynchronous HTTP endpoints, JWT-based authentication, and hybrid data persistence using MongoDB and Pinecone. The system is designed to improve learning outcomes through retrieval augmentation, reduce hallucination compared to ungrounded language models, and support concurrent users with low-latency responses, thereby democratizing personalized tutoring for students regardless of geographical or economic constraints.

Key Words

Retrieval-Augmented Generation, Educational Technology, Large Language Models, Personalized Learning, Vector Database, Sentence Transformers, FastAPI, React, MongoDB, Pinecone

Cite This Article

"PRISM: AI-POWERED LEARNING AND PREPARATION PLATFORM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 3, page no.a597-a602, March-2026, Available :http://www.jetir.org/papers/JETIR2603083.pdf

ISSN


2349-5162 | Impact Factor 7.95 Calculate by Google Scholar

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 7.95 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Cite This Article

"PRISM: AI-POWERED LEARNING AND PREPARATION PLATFORM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 3, page no. ppa597-a602, March-2026, Available at : http://www.jetir.org/papers/JETIR2603083.pdf

Publication Details

Published Paper ID: JETIR2603083
Registration ID: 576923
Published In: Volume 13 | Issue 3 | Year March-2026
DOI (Digital Object Identifier):
Page No: a597-a602
Country: Hyderabad, Telangana, India .
Area: Science & Technology
ISSN Number: 2349-5162
Publisher: IJ Publication


Preview This Article


Downlaod

Click here for Article Preview

Download PDF

Downloads

0005

Print This Page

Current Call For Paper

Jetir RMS