IDFY_Hackathon_2024

Project

This projects offers accurate identification and classification of Personally Identifiable Information (PII) within diverse data repositories.

High Level Diagram
Text Model: Finetuned Gliner model
Vision Model: Finetuned Yolo v8 nano

Currently We offer data ingestion from following data sources
├── AWS S3 Bucket  
├── SQL server
├── Local Folder
└── Copy and Paste Text data

We offer two interfaces
├── Web Application  
└── Command line application

Web Application

Landing Page	Select Your Data

Local Folder Search	SQL Server Integration

Text Analysis	Results

Command Line Application

Running Command line application

cd backend

python3 Test.py

For local folder search input the path as "Test".

Risk Score Calculation