when you update the model endpoint, you need to create a new
EndpointConfig where you specify a new
s3 uri where data capture will be stored and thats how you can see different data captures from different versions of the model.
When you update the model endpoint (using boto3), you must to create a new EndpointConfig where you specify a new Amazon S3 URI. The new Amazon S3 URI is where the data capture will be stored so that you can see different data captures from different versions of the model.
For more information, see the following: https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_UpdateEndpoint.html https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpointConfig.html
SageMaker Multi Model endpoint creation fails while creating for model built on container sagemaker-scikit-learn:0.23-1-cpu-py3asked 4 months ago
Sagemaker endpoint does not use latest approved model versionasked 6 months ago
SageMaker Multi Model EndPoint and Inference Data Capture featureAccepted Answerasked 6 months ago
Relevancy of SageMaker Model Monitor for NLP?Accepted Answer
Redshift ML / SageMaker - Deploy an existing model artifact to a Redshift ClusterAccepted Answerasked 2 years ago
Cloudformation Deployment for Serverless Sagemaker Model Endpointasked 4 months ago
Tracking the lineage between Amazon SageMaker endpoint model and Model Monitor captured dataAccepted Answer
Auto rollback with Guardrails if model accuracy is not goodasked 8 months ago
Does SageMaker Multi-Model Endpoint support SageMaker Model Monitor?Accepted Answer
Failing to create multi-model endpointasked 2 years ago