pii-safe 0.1.0

A Python library for redacting PII from text using privacy-filter model

pii-safe — Redact PII from text

Install

pip install pii-safe

Usage

from pii_safe import redact_text

text = "mi nombre es Dario Clavijo"
redacted = redact_text(text)
print(redacted)  # mi nombre es[REDACTED_10eda051]

Using the Redacter class

from pii_safe import Redacter

redacter = Redacter()
result1 = redacter.redact("mi nombre es Dario Clavijo")
result2 = redacter.redact("el es Dario Clavijo")

# Same PII gets consistent hash
hash_map = redacter.get_hash_map()
print(hash_map)  # {'Dario Clavijo': '10eda051'}

CLI

pii-safe input.txt
pii-safe input.txt -o output.txt

Development

git clone https://github.com/daedalus/pii-safe.git
cd pii-safe
pip install -e ".[test]"

# run tests
pytest

# format
ruff format src/ tests/

# lint
ruff check src/ tests/

# type check
mypy src/

API

redact_text(text: str) -> str

Redacts PII from text using the openai/privacy-filter model.

class Redacter

Context manager for consistent PII-to-hash mapping across calls.

• redact(text: str) -> str: Redact PII from text
• get_hash_map() -> dict[str, str]: Get PII-to-hash mapping