AI-Based Smart Document Management System With Dynamic Field Extraction

Kata Raju Reddy 1, Korada Ramya 2

1Assistant Professor, 2 MCA Final Semester,

Master of Computer Applications, Sanketika Vidya Parishad Engineering College, Vishakhapatnam,

Andhra Pradesh, India

koradaramya369@gmail.com

ABSTRACT:

Traditional document management systems suffer from inefficiencies in organization, retrieval, and data extraction, often relying on manual entry and rigid field structures that fail to accommodate diverse document types. This project proposes an AI Smart Document Management System with Dynamic Field Extraction that leverages Deep Learning and modern web technologies to address these limitations. The system supports a broad range of document categories including invoices, contracts, medical records, and academic transcripts enabling intelligent, automated extraction of key fields without requiring predefined templates. Optical Character Recognition (OCR) powered by

Tesseract processes uploaded documents, while a Large Language Model (LLM) running through the Groq API performs context-aware, dynamic field extraction and document summarization. All documents are indexed and stored in MongoDB, with vector embeddings enabling semantic search across the repository. Users can perform natural language queries to retrieve relevant documents efficiently, bypassing traditional keyword-based search limitations. The backend is developed using FastAPI for scalable and asynchronous API handling, while the frontend is built with React.js for a modern, responsive user experience. Authentication and session management are secured using JWT tokens. The system further incorporates AI-assisted summarization and an intelligent assistant for document-level querying. By combining OCR, LLM-driven extraction, and semantic retrieval, this solution significantly reduces manual processing overhead and modernizes organizational document workflows.

Keywords:

Smart Document Management, Dynamic Field Extraction, Optical Character Recognition, Large Language Models, Semantic Search, Vector Embeddings