Production-grade RAG system for NASA SE Handbook — multi-hop retrieval, table extraction, acronym resolution, confidence scoring

AI-powered resume screening system using NLP and Streamlit

An AI agent that summarizes academic papers into .docx files and emails them to students, automating literature reviews.

A production-inspired, multi-stage agentic pipeline for converting heterogeneous enterprise documents into structured, queryable, spatially-indexed knowledge.

🚢 Intelligent maritime document automation tool that merges Charter Party templates with fixture recaps, featuring smart field extraction, change tracking, and multi-format document generation (PDF/DOCX). Built with Python, Flask, and advanced document processing libraries for the shipping industry.

The backend of CareerLens is built using Flask and Python, providing REST APIs for resume parsing, skill gap analysis, and personalized roadmap generation. It processes uploaded resumes using PDF extraction tools and applies role-based logic to deliver actionable insights.

A web application to compare two PDF files side by side, highlight differences, and view previous comparison history.

Production-grade LangGraph "Digital Courtroom" for autonomous auditing of a GitHub repository and its architectural PDF report.

A Python project for document summarization using various NLP techniques. The project includes a basic setup with a .gitignore file, necessary dependencies listed in requirements.txt, and a script (text.py) for processing documents. It is designed to help automate and streamline document summarization tasks.

Script for conversion of menu pdf to usable data