[Feature] New transform to do PII detection on code files

[Bytes-Explorer]

trafficstars

Search before asking

• [X] I searched the issues and found no similar issues.

Component

Other

Feature

PII detection and redaction is important step while preparation of data for LLMs. The request is to build a new transform that can perform PII detection on code entities.

Are you willing to submit a PR?

• [ ] Yes I am willing to submit a PR!

[SowmyaLR]

I am willing to work on this card. Is there any deadline to work on for this card? @Bytes-Explorer

[Bytes-Explorer]

Thanks @SowmyaLR for your interest. Couple of weeks should be a good time frame.

[Bytes-Explorer]

@SowmyaLR We are doing a demo in two weeks where this module can be showcased, if ready. Do you think you can raise a PR in the next couple of days? Please feel free to ask for help.

[SowmyaLR]

@Bytes-Explorer I can raise PR by next week. Yeah had some issues and figured it out. I hope this can also go along for the demo 🤞

[Bytes-Explorer]

Awesome @SowmyaLR ! cc @shivdeep-singh-ibm As and when this PR is raised, lets fast track the review process on it.

[SowmyaLR]

@Bytes-Explorer @shivdeep-singh-ibm Raised PR for this. I have added few comments in PR description. Need suggestions from people to know how to resolve that.