INTELLIGENT DOCUMENT QUESTION ANSWERING SYSTEM USING VECTOR EMBEDDINGS AND LARGE LANGUAGE MODEL

Read full text Summarise with VIRAT
Authors: Mrs S.T. Ramya, V Harshitha, R VyomRaj, G Sushma
Cited by: 0
References: 3

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The Intelligent Document Question Answering System presents an implementation-focused Retrieval-Augmented Generation (RAG) framework that transforms static document repositories into an interactive conversational interface.The system processes uploaded documents through text extraction, cleaning, and segmentation before generating high-dimensional vector embeddings.These embeddings are stored in ChromaDB to enable semantic similarity search that surpasses traditional keyword-based retrieval.During query processing, user questions are converted into embeddings, the most relevant segments are retrieved, and a grounded prompt is constructed for a selectable Large Language Model backend (OpenAI or Ollama).The integration of semantic retrieval, modular architecture, and context-aware generation ensures improved factual accuracy, reduced hallucination, and domain adaptability.

Fields of Study & Subjects

Topic Modeling Information Retrieval and Search Behavior Natural Language Processing Techniques

Publication details

Journal / source
International journal of engineering science and advanced technology.
Volume
26
Issue
3
Pages
1119–1125
Publication date
1 March 2026
Language
EN