mlrun
mlrun copied to clipboard
[Serving] Add support for input as a Batch (without model monitoring)
๐ Description
Add support for input as a batch in ModelRunnerErrorRaiser and add format_batch client function.
Update body parameter type.
Important note: Batch support in model monitoring will be added in a follow-up PR and is not supported yet.
๐ ๏ธ Changes Made
โ Checklist
- [x] I updated the documentation (if applicable)
- [x] I have tested the changes in this PR
- [x] I confirmed whether my changes are covered by system tests
- [x] If yes, I ran all relevant system tests and ensured they passed before submitting this PR
- [x] I updated existing system tests and/or added new ones if needed to cover my changes
- [x] If I introduced a deprecation:
- [x] I followed the Deprecation Guidelines
- [ ] I updated the relevant Jira ticket for documentation
๐งช Testing
Add unit tests + system tests.
๐ References
- Ticket link: ML-11680
- Design docs links:
- External links:
๐จ Breaking Changes?
- [ ] Yes (explain below)
- [ ] No