Skip to content

divesh9892/HindiTableExtractor

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

📄 Enterprise Hindi Document Extractor

A secure, cloud-connected VLM (Vision Language Model) tool designed to convert unstructured Hindi government forms, exam sheets, and WhatsApp images into perfectly formatted Excel reports.

✨ Features

  • Smart Layout Analysis: Automatically detects tables, titles, and footers, calculating optimal Excel column widths and row heights.
  • Auto-Healing JSON Engine: Surgically extracts and repairs AI-flattened JSON responses to prevent application crashes.
  • Zero-Trust Security (BYOK): Users can bring their own Gemini API key. Keys are held entirely in temporary memory and destroyed upon session end.
  • Format Agnostic: Supports .jpg, .png, and .pdf extraction natively through the Gemini GenAI SDK.

🚀 Quick Start

1. Clone the repository

git clone [https://github.com/YOUR_USERNAME/HindiTableExtractor.git](https://github.com/YOUR_USERNAME/HindiTableExtractor.git)
cd HindiTableExtractor

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages