A multilingual, context-aware PII redaction tool that removes sensitive information from PDF documents (not just masking β the data is truly deleted) ensuring thorough privacy protection.
β¨ Features
Comprehensive PII Detection: Identifies a wide range of personal information including names, email addresses, phone numbers, addresses, IDs, and more
Hybrid Detection Approach: Combines regex pattern matching with LLM-based detection for improved accuracy
PDF Processing: Works with standard PDFs containing selectable text
Multi-language Support: Detects PII in multiple languages
Progress Tracking: Real-time progress and logging information