microsoft / microsoft/simplechat
Inform user that PII does exist in the data returned from AI search when searching/using documents
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 152
- Forks
- 116
- Avg merge
- 7h 7m
- Merged PRs (30d)
- 122
Description
During the document tokenization process, utilize a language model to detect potential PII and notify users if any is found, so it can be handled appropriately. Consider using a similar approach for Financial Sensitive Information (FSI) and other Controlled Unclassified Information (CUI).
Just to inform, so they know its there but does not stop the usage
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue does not name an implementation file, entry point, or test. Start by locating the document tokenization flow and its existing classification or notification behavior; done means potential PII is detected and users are informed without preventing document use.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, security
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100