NVIDIA-Merlin / NVIDIA-Merlin/Merlin
[QST] What is the best way of handling string UUIDs in Merlin?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 907
- Forks
- 129
- PR merge metrics
- No merged PRs in 30d
Description
❓ Questions & Help
Details
What would be the best way of going about this?
My original idea was to either Hash or Categorify the UUID values for training, then have the user_id_raw and item_id_raw string values be returned from the Feast store during inference so that my application can get the raw UUIDs. However, Merlin does not support this paradigm as I get type errors during inference.
Another option would be to map the UUIDs to Int separately but I'm not sure how and where this should be implemented with Merlin.
Thank you in advance.
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, tests, or entry points are named. Start by reviewing how Feast store values are handled during inference and where Merlin enforces types, then determine whether raw UUIDs can be returned while training uses transformed identifiers; a decision on the supported approach would be needed before implementation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100