Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fixing sagemaker urls to take the settings into consideration #3195

Merged
merged 1 commit into from
Nov 14, 2024
Merged

Fixing sagemaker urls to take the settings into consideration #3195

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 19 additions & 4 deletions src/zenml/integrations/aws/orchestrators/sagemaker_orchestrator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -478,7 +478,9 @@ def prepare_or_run_pipeline(
)

# Yield metadata based on the generated execution object
yield from self.compute_metadata(execution=execution)
yield from self.compute_metadata(
execution=execution, settings=settings
)

# mainly for testing purposes, we wait for the pipeline to finish
if settings.synchronous:
Expand Down Expand Up @@ -577,12 +579,15 @@ def fetch_status(self, run: "PipelineRunResponse") -> ExecutionStatus:
raise ValueError("Unknown status for the pipeline execution.")

def compute_metadata(
self, execution: Any
self,
execution: Any,
settings: SagemakerOrchestratorSettings,
) -> Iterator[Dict[str, MetadataType]]:
"""Generate run metadata based on the generated Sagemaker Execution.

Args:
execution: The corresponding _PipelineExecution object.
settings: The Sagemaker orchestrator settings.

Yields:
A dictionary of metadata related to the pipeline run.
Expand All @@ -599,7 +604,9 @@ def compute_metadata(
metadata[METADATA_ORCHESTRATOR_URL] = Uri(orchestrator_url)

# URL to the corresponding CloudWatch page
if logs_url := self._compute_orchestrator_logs_url(execution):
if logs_url := self._compute_orchestrator_logs_url(
execution, settings
):
metadata[METADATA_ORCHESTRATOR_LOGS_URL] = Uri(logs_url)

yield metadata
Expand Down Expand Up @@ -643,11 +650,13 @@ def _compute_orchestrator_url(
@staticmethod
def _compute_orchestrator_logs_url(
pipeline_execution: Any,
settings: SagemakerOrchestratorSettings,
) -> Optional[str]:
"""Generate the CloudWatch URL upon pipeline execution.

Args:
pipeline_execution: The corresponding _PipelineExecution object.
settings: The Sagemaker orchestrator settings.

Returns:
the URL querying the pipeline logs in CloudWatch on AWS.
Expand All @@ -657,10 +666,16 @@ def _compute_orchestrator_logs_url(
pipeline_execution.arn
)

use_training_jobs = True
if settings.use_training_step is not None:
use_training_jobs = settings.use_training_step

job_type = "Training" if use_training_jobs else "Processing"

return (
f"https://{region_name}.console.aws.amazon.com/"
f"cloudwatch/home?region={region_name}#logsV2:log-groups/log-group"
f"/$252Faws$252Fsagemaker$252FTrainingJobs$3FlogStreamNameFilter"
f"/$252Faws$252Fsagemaker$252F{job_type}Jobs$3FlogStreamNameFilter"
f"$3Dpipelines-{execution_id}-"
)
except Exception as e:
Expand Down
Loading