Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62585
Volume:
10 |
5 |
May 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department Of Electronics and Telecommunication Engineering
G. H. Raisoni College of Engineering and Management Nagpur, India
Department Of Electronics and Telecommunication Engineering
G. H. Raisoni College of Engineering and Management Nagpur, India
Department Of Electronics and Telecommunication Engineering
G. H. Raisoni College of Engineering and Management Nagpur, India
Retrieval - Augmented Generation (RAG) is a framework that optimizes the output of a Large Language Model (LLM) by referencing an authoritative knowledge base outside of its initial training data before generating a response. This approach is particularly effective for creating chatbots that can "read" specific documents and provide grounded, factual answers without the high costs of retraining the model. The exponential growth of scientific literature necessitates advanced tools for rapid information synthesis. This paper presents a specialized Retrieval-Augmented Generation (RAG) framework capable of processing and querying multiple research papers simultaneously. By integrating FAISS for vector similarity search, HuggingFace sentence transformers for semantic embeddings, and Groq-accelerated Inference, the system achieves low-latency, contextually accurate responses. Our implementation focuses on a "Privacy-First" approach, utilizing local embedding models and high-performance, open-source LLMs like Llama-3.3
KEYWORDS
This study successfully developed and deployed a Retrieval-Augmented Generation (RAG) application tailored for academic synthesis. By combining the document-parsing capabilities of pdfplumber, the semantic understanding of HuggingFace Embeddings, and the high-speed inference of the Groq API, the system provides a robust solution for researchers to interact with multiple complex documents simultaneously.
1. Gupta, Shailja & Ranjan, Rajesh & Singh, Surya. (2024). A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions. 10.48550/arXiv.2410.12837. 2. Lewis, Patrick & Perez, Ethan & Piktus, Aleksandara & Petroni, Fabio & Karpukhin, Vladimir & Goyal, Naman & Küttler, Heinrich & Lewis, Mike & Yih, Wen-tau & Rocktäschel, Tim & Riedel, Sebastian & Kiela, Douwe. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. 10.48550/arXiv.2005.11401. 3. Agarwal, Shubham & Sundaresan, Sai & Mitra, Subrata & Mahapatra, Debabrata & Gupta, Archit & Sharma, Rounak & Kapu, Nirmal & Yu, Tong & Saini, Shiv. (2025). Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation. Proceedings of the ACM on Management of Data. 3. 1-28. 10.1145/3725273. 4. Es, Shahul & James, Jithin & Espinosa-Anke, Luis & Schockaert, Steven. (2024). RAGAs: Automated Evaluation of Retrieval Augmented Generation. 150-158. 10.18653/v1/2024.eacl-demo.16. 5. Jiang, Ziyan & Ma, Xueguang & Chen, Wenhu. (2024). LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs. 10.48550/arXiv.2406.15319. 6. Wang, Xiaohua & Wang, Zhenghua & Gao, Xuan & Zhang, Feiran & Wu, Yixin & Xu, Zhibo & Shi, Tianyuan & Wang, Zhengyuan & Li, Shizheng & Qian, Qi & Yin, Ruicheng & Lv, Changze & Zheng, Xiaoqing & Huang, Xuanjing. (2024). Searching for Best Practices in Retrieval-Augmented Generation. 17716-17736. 10.18653/v1/2024.emnlp-main.981. 7. https://doi.org/10.48550/arXiv.2112.01488
Publication Date
5/6/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
7
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...