A minimal web tool to detect and redact Personally Identifiable Information (PII) such as email addresses, phone numbers , names, and addresses from PDF and TXT files.
- Accepts PDF or TXT input
- Detects and redacts PII using Regex and Gemini LLM
- Displays both original and redacted text
- Shows a table of removed items with type, value, and reason
- Export redacted output as PDF
The tool is built using React and designed to be simple and privacy-focused. It works in two ways: using regex for PII detection and also supports Gemini LLM for smarter results.
-
Built with a clean React UI
-
Detects emails, phone numbers, names, and addresses using regex
-
Shows original and redacted text side-by-side
-
Supports Gemini LLM for advanced detection
-
Allows downloading redacted files as PDF
-
OCR for scanned PDFs/images (coming soon)
-
DOC/DOCX file support (coming soon)
This project is licensed under the MIT License.