[Serving] Support model monitoring with list + tests #9117
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Conflicts: # tests/serving/test_async_flow.py
tomerm-iguazio
force-pushed
the
mm_support_list
branch
from
4b697ef to
12f466d
Compare
tomerm-iguazio
changed the title
# Conflicts: # tests/serving/test_async_flow.py
tomerm-iguazio
commented
Dec 30, 2025
tomerm-iguazio
changed the title
royischoss
reviewed
Dec 30, 2025
Contributor
royischoss
left a comment
royischoss
left a comment
There was a problem hiding this comment.
Hey looks good overall added some comments
| serving_fn: mlrun.runtimes.nuclio.serving.ServingRuntime, | ||
| *, | ||
| with_training_set: bool = True, | ||
| model_runner_mode: typing.Optional[str] = None, |
Contributor
There was a problem hiding this comment.
I think it not clear here the usage of V2ModelServer is hidden with None, better adding a flag or adding a V2ModelServer option and adding a ModelRunner prefix for the batch and single
| @pytest.mark.parametrize("with_training_set", [True, False]) | ||
| @pytest.mark.parametrize("with_model_runner", [True, False]) | ||
| def test_app_flow(self, with_training_set: bool, with_model_runner: bool) -> None: | ||
| @pytest.mark.parametrize( |
Contributor
There was a problem hiding this comment.
Thought this will be in a separate test, can be add to test_monitoring_with_model_runner_dict_infer in class TestBasicModelMonitoring
mlrun/serving/system_steps.py
Outdated
| mm_schemas.StreamProcessingEvent.WHEN | ||
| ) | ||
| # if the body is not a dict, we set it to empty dict to fields extraction | ||
| body_by_model = ( |
Contributor
There was a problem hiding this comment.
I think it better to create a method to extract fields of labels or error from body. this way we just we may cause someone else to use this body as the event data while we initialized an empty dict
mlrun/serving/system_steps.py
Outdated
| when = event._original_timestamp | ||
| else: | ||
| when = event._metadata.get(mm_schemas.StreamProcessingEvent.WHEN) | ||
| event_body = event.body if isinstance(event.body, dict) else {} |
update test to use v2modelserver as model_mode and not as None
add simpler test: test_monitoring_with_model_runner_batch_infer
10 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
📝 Description
🛠️ Changes Made
✅ Checklist
🧪 Testing
Unit test for model monitoring + helpers functions.
System test for main functionality.
🔗 References
🚨 Breaking Changes?
🔍️ Additional Notes