Smart Doc AI: Intelligent Document Processing and Semantic Analysis System
Abstract
Smart Doc AI is an end-to-end Retrieval-Augmented Generation (RAG) platform designed to transform multi-format academic course materials into an interactive AI study companion. The system supports PDF, DOCX, PPTX, TXT, Markdown, and image documents, using specialized parsers and OCR for document ingestion. Extracted content is processed using sentence-boundary-aware chunking and Google Gemini embeddings. The system combines dense cosine similarity with BM25 lexical retrieval for hybrid semantic search. Retrieved passages are provided to a Gemini language model for grounded answer generation with document and page-level citations. The platform provides authenticated conversational Q&A, examination preparation, automated quiz evaluation, study planning, and analytics through a Flask REST API and React web application.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.