Open Access Open Access  Restricted Access Subscription Access

ResearchMind AI An AI-Powered Multi-Domain Research Paper Analysis and Report Generation System

Mr Sanjay Krishna B, Anandhi A, Karthikha shree S M, Lekha P, Maajida A

Abstract


ResearchMind AI is an AI-powered system designed to simplify research paper analysis across multiple domains. It enables users to upload and analyze multiple research papers in PDF format. PyMuPDF is used to extract text, while Sentence Transformers generate semantic embeddings. ChromaDB stores and retrieves relevant information through semantic search. Retrieval-Augmented Generation (RAG) is integrated with an open-source Large Language Model (LLM) to provide context-based answers. The system supports automated literature survey generation, research gap identification, paper comparison, and intelligent question answering. It also generates structured research reports summarizing key findings and future research directions. The application uses React.js for the frontend and Flask with Python for the backend. ResearchMind AI aims to reduce manual effort, improve research organization, and make literature analysis more efficient.


Full Text:

PDF

References


Lewis P. et al. “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.” Advances in Neural Information Processing Systems, 2020, 33, 9459–9474.

Reimers N., Gurevych I. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. EMNLP, 2019.

Wang L. et al. “Text Embeddings by Weakly-Supervised Contrastive Pre-training.” arXiv preprint arXiv:2212.03533, 2022.

Chalkidis I. et al. “LEGAL-BERT: The Muppets Straight Out of Law School.” Findings of ACL: EMNLP, 2020, 2898–2904.

Johnson J., Douze M., Jégou H. Billion-scale Similarity Search with GPUs. IEEE Transactions on Big Data, 2019, 7(3), 535–547.

Robertson S., Zaragoza H. The Probabilistic Relevance Framework: BM25 and Beyond. Foundations and Trends in Information Retrieval, 2009, 3(4), 333–389.

Asai A. et al. “Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection.” ICLR, 2024.

Chroma. Chroma Documentation: Vector Database for AI Applications. Available at: https://docs.trychroma.com/

Hugging Face. intfloat/e5-base-v2: Text Embeddings Model. Available at: https://huggingface.co/intfloat/e5-base-v2

Apache Software Foundation. Apache PDFBox Documentation. Available at: https://pdfbox.apache.org/


Refbacks

  • There are currently no refbacks.