Hia (Health Insights Agent) - AI Agent to analyze blood reports and provide detailed health insights.

AI-powered legal chatbot that leverages Retrieval-Augmented Generation (RAG) with DeepSeek R1 for advanced legal reasoning and document analysis. It provides a sophisticated legal assistant that can process and analyze complex legal documents, retrieve relevant information using advanced vector search, and generate nuanced legal analysis.

Extracting details from Resume(CVs) and matching with Job Description(JDs) using pretrained model like DistilBERT and ranking them using cosine similarity.

Convert PDF into an audiobook.

Ready to use Python application/file for parsing a specific format of pdf form, and storing relevant user data in a tabular format in excel sheet

Medical AI Report Summarizer is a smart web application that allows users to upload medical reports (PDF, JPG, PNG), automatically extract text, highlight medical terms, and generate an AI-based summary. Users can also export the final summary as a clean PDF.

This project facilitates the extraction of text from PDF files using various Python libraries. It is designed to be flexible, allowing the choice among different text extraction libraries and supporting both single PDF file and directory containing multiple PDF files.

BIA (Blood Report Insights Agent) - AI Agent to analyze blood reports and provide detailed health insights.

A modern web application that integrates a conversational AI chatbot with real-time user interactions smooth animations. Built using React, Framer Motion, Lucide Icons, and ShadCN Components on frontend and fastapi on backend. [Below is website deployed Frontend]

NLP model for extracting chinese datas from the documents

This is my exploration of a variety of Python 🐍 libraries. I have built geospatial data analytics systems from CSV files, Image and video processing tools like face detection and motion detection. I also built a website with flask (and three.js), I built apps connecting to several types of databases. Created a simple budgeting app that reads, wr…

A Python application that converts PDF invoices to Excel format, with support for both text-based and scanned PDFs. The application includes OCR capabilities for processing scanned documents and features a modern GUI interface with real-time processing logs.

學生學程查詢系統

GUI app for parsing specific PDF files (data from standardized Vehicle Registration smart card - Republic of Serbia) and generating data file for specific use case.

Business objective- The document classification solution should significantly reduce the manual human effort in the HRM. It should achieve a higher level of accuracy and automation with minimal human intervention

A sample script to extract text data from a pdf file, converts it to a pandas data frame, and saves it into a CSV file.

This project provides a Python-based solution for extracting structured data from PDF documents, with a focus on accurately parsing tables and handling complex cell layouts. It leverages pdfplumber for PDF parsing and incorporates custom logic to restructure tables, especially those with multi-line content or merged cells.

collecting data from the Barcelona City Hall Open Data Service's on socioeconomic indicators of the territorial division of the city of Barcelona

NLP-based resume parsing tool for extracting relevant info and rank candidates for job applications

Interface developed to extract information from web through scraping and summarize given data.