Anonymizing text files by identifying and extracting different types of PII from text data and replacing sensitive information with generic placeholders or pseudonyms using Microsoft Presidio
Helper functions for converting pdf file to txt using pdfplumber and reading from txt files
Running unit tests on anonymize.py using pytest
pip install -r requirements.txt
In order to make the full App works on the user's local machine, It's required to launch the api first then running the frontend by executing the scripts below:
uvicorn app.api.main:app --reload
curl http://localhost:8000/anonymize -F "file=@tests/example.pdf"
curl -X POST -H "Content-Type: application/json" -d '{ "question": "Your question goes here", "text": "Text goes here" }' http://localhost:8000/ask
cd frontend
npm install
npm start