Presidio
Presidio helps to ensure sensitive data is properly managed and governed. It provides fast identification and anonymization modules for private entities in text and images such as credit card numbers, names, locations, social security numbers, bitcoin wallets, US phone numbers, financial data and more.
How it works
I was just taking a look at Chainlit, and more specifically this example and saw Presidio mentioned.
I have seen basic attempts at doing this with hand-spun regexes in the past and I’ve seen commercial products, but this feels like it strikes a nice middle ground. Despite the very Microsoft-y website that made me immediately assume it was for C# or .NET, it’s a Python library, and it’s MIT licensed. From their FAQs:
Microsoft Presidio is not an official Microsoft product. […] The authors and maintainers of Presidio come from [our] Industry Solutions Engineering team.