A Multi-Purpose Text Generation Framework Using LLM: OWN-GPT

Read full text Summarise with VIRAT
Authors: Kinal Patel
Cited by: 0
References: 9

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

OWN-GPT is a 2.3-billion-parameter transformer-based Large Language Model (LLM) developed as a full-stack AI system featuring a React.js frontend and a Python FastAPI backend. The system provides conversational text generation, imagebased question answering using OCR and visual feature extraction, and PDF document question answering through RetrievalAugmented Generation (RAG). The backend incorporates PyTorch, HuggingFace Transformers, PyMuPDF, LangChain, FAISS, sentence-transformers, OpenCV, Tesseract, and ViT-Base/16 for multimodal processing. Trained on an 81 GB multidomain corpus (~40 billion tokens), OWN-GPT achieves a perplexity of 7.8, BLEU score of 0.68, image module CER of 6.8%, and RAG module faithfulness and relevancy scores of 0.81 and 0.79. Designed for local deployment in Indian academic institutions, the system ensures data privacy and zero per-query operational cost. A user study reports a System Usability Scale (SUS) score of 77.1, confirming strong usability and user satisfaction.

Fields of Study & Subjects

Topic Modeling Multimodal Machine Learning Applications Natural Language Processing Techniques

Publication details

Journal / source
International Journal for Research in Applied Science and Engineering Technology
Volume
14
Issue
3
Pages
3813–3818
Publication date
28 March 2026
Language
EN