SageMaker delete Models and Endpoint configurations with python API

Question

I've tried deleting/recreating endpoints with the same name, and wasted a lot of time before I realized that changes do not get applied unless you also delete the corresponding Model and Endpoint configuration so that new ones can be created with that name.

Is there a way with the sagemaker python api to delete all three instead of just the endpoint?

Answer 1

I believe you are looking for something like this? :

https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker.html#SageMaker.Client.delete_endpoint_config

Examples:

import boto3

deployment_name = 'my_deployment_name'
client = boto3.client('sagemaker')
response = client.describe_endpoint_config(EndpointConfigName=deployment_name)
model_name = response['ProductionVariants'][0]['ModelName']
client.delete_model(ModelName=model_name)    
client.delete_endpoint(EndpointName=deployment_name)
client.delete_endpoint_config(EndpointConfigName=deployment_name)

Answer 2

It looks like AWS is currently in the process of supporting model deletion via API with this pull request.

For the time being Amazon's only recommendation is to delete everything via the console.

If this is critical to your system you can probably manage everything via Cloud Formation and create/delete services containing your Sagemaker models and endpoints.