Authors : P. S. Togrikar; Tejas Pawar; Akshay Malgunde; Mayureshwar Raychure

Volume/Issue : Volume 11 - 2026, Issue 10 - October

Google Scholar : https://tinyurl.com/3c72ff9r

DOI : https://doi.org/10.38124/ijisrt/26Oct1167

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Retrieval-Augmented Generation (RAG) effectively separates knowledge retrieval from generation for private document question answering. This study explores the design space of document-grounded QA and details a multi-PDF RAG system. The pipeline uses PyMuPDF for text extraction with OCR fallback, BAAI/bge-small-en-v1.5 for dense embeddings, and ChromaDB for storage. Semantically similar chunks are retrieved via cosine distance to generate answers using a local Llama 3.2:3B model via Ollama. Built with React/Vite and FastAPI, the system supports document management and query APIs. The paper reviews RAG methodologies—including hybrid retrieval, reranking, and GraphRAG—while maintaining a local, modular architecture optimized for consumer-grade hardware. Finally, it evaluates the system's strengths and limitations to identify future research directions.

Keywords : Retrieval-Augmented Generation; Multi-PDF Question Answering; Document-Grounded QA; Dense Retrieval; Vector Databases; OCR; Local LLMs.

References :

1. P. Lewis et al., “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” arXiv:2005.11401, 2020.
2. Y. Gao et al., “Retrieval-Augmented Generation for Large Language Models: A Survey,” arXiv:2312.10997, 2023, revised 2024.
3. Y. Huang and J. Huang, “A Survey on Retrieval-Augmented Text Generation for Large Language Models,” arXiv:2404.10981, 2024.
4. V. Karpukhin et al., “Dense Passage Retrieval for Open-Domain Question Answering,” Proc. EMNLP, pp. 6769–6781, 2020.
5. N. Reimers and I. Gurevych, “Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks,” Proc. EMNLP-IJCNLP, pp. 3982–3992, 2019.
6. Chroma, “Chroma Core Concepts and APIs: Collections, Embeddings, Metadata and Filters,” Chroma Cookbook, accessed 2026.
7. PyMuPDF, “The Basics: PDF Text Extraction and OCR,” PyMuPDF Documentation, accessed 2026.
8. PyMuPDF, “Text Extraction Recipes and Structured Page Extraction,” PyMuPDF Documentation, accessed 2026.
9. C. Auer et al., “Docling Technical Report,” arXiv, 2024.
10. N. F. Liu et al., “Lost in the Middle: How Language Models Use Long Contexts,” arXiv:2307.03172, 2023.
11. S. Es, J. James, L. Espinosa-Anke, and S. Schockaert, “RAGAS: Automated Evaluation of Retrieval Augmented Generation,” arXiv:2309.15217, 2023.
12. D. Edge et al., “From Local to Global: A Graph RAG Approach to Query-Focused Summarization,” arXiv:2404.16130, 2024.
13. BAAI, “BGE Embedding Models,” BAAI FlagEmbedding project and model documentation, accessed 2026.
14. Ollama, “Llama 3.2 Model and Local Inference Documentation,” Ollama Documentation, accessed 2026.
15. LangChain, “Retrieval and RAG Concepts,” LangChain Documentation, accessed 2026.
16. F. M. Reimers and I. Gurevych, “Making Monolingual Sentence Embeddings Multilingual Using Knowledge Distillation,” EMNLP, 2020.