EUVIMEDEUVIMED entdecken
Crossref

DocuMind: An Offline Multilingual Retrieval-Augmented Generation System for Document Question Answering Using Local Large Language Models

Swetha M S, Dr. Sripalreddy

International Scientific Journal of Engineering and Management · 06.08.2026 · 05 (08) · 1-9

DOI: 10.55041/isjem08461 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Scientific Journal of Engineering and Management, online erschienen am 06.08.2026. Verfasst von Swetha M S und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

DocuMind is a fully offline, privacy-preserving, multilingual Document Question Answering system built on the Retrieval-Augmented Generation (RAG) architecture. The system enables users to upload documents in any language and ask questions in their native language — including Kannada, Hindi, Tamil, Telugu, and English — receiving accurate, contextually grounded answers from a locally running Large Language Model (LLM) with zero cloud dependency and zero recurring cost. The system employs Language-Agnostic BERT Sentence Embeddings (LaBSE), a multilingual model supporting 109 languages, to map all text into a shared 768-dimensional semantic vector space, enabling true cross-lingual retrieval without any translation step. Document embeddings are persisted in a local ChromaDB vector database and answer generation is performed by LLaMA 3.2 (3B parameters) running locally via the Ollama runtime. Evaluation using RAGAS-style metrics across five languages demonstrates Faithfulness scores of 0.77 to 0.87 and average query latency under 8 seconds on a standard consumer laptop with 8 GB RAM. KEYWORDS Retrieval-Augmented Generation, Large Language Models, Multilingual NLP, LaBSE, ChromaDB, Ollama, LLaMA, Document Question Answering, Indic Languages, Offline AI, Natural Language Processing, Cross-lingual Retrieval.

Zitieren

APA

S, S. M., & Sripalreddy, D. (2026). DocuMind: An Offline Multilingual Retrieval-Augmented Generation System for Document Question Answering Using Local Large Language Models. International Scientific Journal of Engineering and Management, 05(08), 1-9. https://doi.org/10.55041/isjem08461

Vancouver

S SM, Sripalreddy D. DocuMind: An Offline Multilingual Retrieval-Augmented Generation System for Document Question Answering Using Local Large Language Models. International Scientific Journal of Engineering and Management. 2026;05(08):1-9. doi:10.55041/isjem08461

BibTeX
@article{S2026,
  author = {S, Swetha M and Sripalreddy, Dr.},
  title = {DocuMind: An Offline Multilingual Retrieval-Augmented Generation System for Document Question Answering Using Local Large Language Models},
  journal = {International Scientific Journal of Engineering and Management},
  year = {2026},
  volume = {05},
  number = {08},
  pages = {1--9},
  doi = {10.55041/isjem08461}
}
Kostenlos starten →