NVIDIA-NeMo / NVIDIA-NeMo/Anonymizer
feat: Allow for deterministic substituting of PII detected entities
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 122
- Forks
- 17
- Avg merge
- 4d 2h
- Merged PRs (30d)
- 11
Description
Priority Level
Medium (Nice to have)
Is your feature request related to a problem?
When running Anonymizer against documents, we need context preserving and deterministic replacement for detected PII across multiple runs. This is required for various downstream use cases
Describe the solution you'd like
When running Anonymizer against documents, would like the library to replace the detected PII deterministically across runs so:
Run 1:
"Sandy went to New York and there Sandy ate pizza" -> "Alice went to Los Angeles and there Alice ate pizza"
Run 2:
"Sandy went to New York and there Sandy ate pizza" -> "Alice went to Los Angeles and there Alice ate pizza"
Describe alternatives you've considered
No response
Additional context
No response
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
No files or tests are named. Start by locating the Anonymizer entry point and its entity-replacement flow, then determine how deterministic replacement state should work across runs; done means repeated inputs produce the consistent entity mappings shown in the examples.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- security
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100