PipelineModel deploy method cannot find update_endpoint argument

[markpurser]

Please fill out the form below.

System Information

• Framework (e.g. TensorFlow) / Algorithm (e.g. KMeans):
  SKLearn with kNN
• Framework Version:
• Python Version:
  Python 3
• CPU or GPU:
  CPU
• Python SDK Version:
• Are you using a custom image:
  No

Describe the problem

I want to update an endpoint that already exists when deploying from a PipelineModel. The update_endpoint flag is supported on Estimators.deploy but not on PipelineModel.deploy

Minimal repro / logs

---

TypeError Traceback (most recent call last)
in ()
22 instance_type='ml.t2.medium',
23 endpoint_name=endpoint_name,
---> 24 update_endpoint=True)

TypeError: deploy() got an unexpected keyword argument 'update_endpoint'

• Exact command to reproduce:
  model_name = 'inference-pipeline-' + timestamp_prefix
  endpoint_name = 'sagemaker-ep'
  sm_model = PipelineModel(
  name=model_name,
  role=role,
  models=[
  sklearn_preprocessor_model,
  sklearn_estimator_model])

sm_model.deploy(initial_instance_count=1,
instance_type='ml.t2.medium',
endpoint_name=endpoint_name,
update_endpoint=True)

[knakad]

@markpurser
Hi Mark!
There was a separate issue blocking this, which I was able to resolve earlier this week.
Ujjwal beat me to the actual update_endpoint fix, which he pushed just a minute ago.
(Thanks Ujjwal!)

This'll be automatically released to PyPi within the next day or so (1.36.5) =)

[knakad]

I'm going to go ahead and keep this issue open until the release is available for consumption.

[knakad]

I triggered a release for this earlier this morning: https://github.com/aws/sagemaker-python-sdk/releases/tag/v1.37.0

Thanks again for reaching out and pointing this out to us!