Abstract :

In The Era Of Exponential Data Growth, Efficient And Intelligent Document Retrieval Has Become A Critical Requirement Across Various Domains Such As Education, Healthcare, Legal Systems, And Enterprise Knowledge Management. Traditional Keyword-based Search Systems Often Fail To Capture Semantic Meaning And Context, Resulting In Less Accurate And Relevant Outputs. To Address These Limitations, This Project Proposes A Document Retrieval System Using Retrieval-Augmented Generation (RAG), Which Combines The Strengths Of Information Retrieval And Generative Artificial Intelligence. The Proposed System Leverages A Hybrid Architecture Where A Retrieval Module First Identifies Relevant Documents From A Large Corpus Using Vector Embeddings And Similarity Search Techniques. These Embeddings Are Generated Using Pre-trained Language Models, Enabling Semantic Understanding Beyond Simple Keyword Matching. The Retrieved Documents Are Then Passed To A Generative Model, Which Synthesizes Precise, Contextaware Responses Tailored To User Queries. This Approach Enhances Both Accuracy And Explainability, As The Generated Answers Are Grounded In Actual Source Documents. The System Is Designed To Support Multiple Document Formats, Including PDFs, Text Files, And Structured Datasets. It Incorporates Efficient Indexing Mechanisms Using Vector Databases To Ensure Fast And Scalable Retrieval. Additionally, The Architecture Supports Real-time Querying And Can Be Integrated Into Web-based Applications For User-friendly Interaction. Performance Evaluation Demonstrates Improved Relevance, Reduced Response Time, And Enhanced User Satisfaction Compared To Traditional Search Systems.

Published:

08-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1964-1971

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite