EUVIMEDEUVIMED entdecken
Crossref

A Survey on Retrieval-Augmented Generation for Multi-PDF Question Answering Systems

P. S. Togrikar, Tejas Pawar, Akshay Malgunde, Mayureshwar Raychure

International Journal of Innovative Science and Research Technology · 31.10.2026 · 11 (10) · 2336

DOI: 10.38124/ijisrt/26oct1167 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 31.10.2026. Verfasst von P. S. Togrikar und 3 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Togrikar, P. S., Pawar, T., Malgunde, A., & Raychure, M. (2026). A Survey on Retrieval-Augmented Generation for Multi-PDF Question Answering Systems. International Journal of Innovative Science and Research Technology, 11(10), 2336. https://doi.org/10.38124/ijisrt/26oct1167

Vancouver

Togrikar PS, Pawar T, Malgunde A, Raychure M. A Survey on Retrieval-Augmented Generation for Multi-PDF Question Answering Systems. International Journal of Innovative Science and Research Technology. 2026;11(10):2336. doi:10.38124/ijisrt/26oct1167

BibTeX
@article{Togrikar2026,
  author = {Togrikar, P. S. and Pawar, Tejas and Malgunde, Akshay and Raychure, Mayureshwar},
  title = {A Survey on Retrieval-Augmented Generation for Multi-PDF Question Answering Systems},
  journal = {International Journal of Innovative Science and Research Technology},
  year = {2026},
  volume = {11},
  number = {10},
  pages = {2336},
  doi = {10.38124/ijisrt/26oct1167}
}
Kostenlos starten →