Python

piiscrub

A blazing-fast, zero-dependency PII scrubbing engine for LLMs. Multi-core parallel processing, synthetic data generation, and compliance auditing out of the box.

PythonEmergingcompliancedata-privacyllm-securitynlp

GitHub

Stars

Forks

—

Contributors

Last push

4mo ago

Recent commits

Latest commits.

Merge pull request #5 from OmkarPathak/dev
df2e77aOmkar Pathak4mo ago
feat: Implement directory batch processing with `--dir` and `--recursive` options, including new CLI arguments, processing logic, unit tests, and documentation.
f7d5d22Omkar Pathak4mo ago
Merge pull request #4 from OmkarPathak/dev
d9f4ca7Omkar Pathak4mo ago
feat: Add PII scrubbing support for structured JSON and CSV data with new CLI arguments and tests.
ff88de6Omkar Pathak4mo ago
feat: Refactor PII scrubbing to a single-pass approach to prevent nested redaction, add a synthetic replacement style, and include a new test case.

Top contributors

Builders behind this project.

OmkarPathak

16 commits