-
Notifications
You must be signed in to change notification settings - Fork 2
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.
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
chore: adding runbook documentation #280
base: dev
Are you sure you want to change the base?
Conversation
Please review the existing CDK-Nag Violations for 30cefc6518acaed7f890eb94f336bac33d193eae There are 92 AwsSolutions Violation(s)
There are 64 NIST.800.53.R5 Violation(s)
|
Could you update the Notes section as well? |
Done |
71bc578
to
27855ca
Compare
27855ca
to
30cefc6
Compare
|
||
This guide provides step-by-step instructions to: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
suggestion: Consider moving this content to some other README. As written it seems like you need to deploy the Notebooks before you deploy OSML. that really isn't the case. Can we reorganize this to separate the OSML deployment from the example notebooks deployment?
My main concern is that this might confuse customers who are already struggling to deploy OSML. It seems better if we break OSML into smaller / simpler pieces each that have their own deployment instructions.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
question: Does all this need to be duplicated in the guidance repo? We're already vending osml-model-runner-test to PyPi. Maybe we should update that repository to be a more polished library and then install the test utilities into the conda environment you setup for these notebooks.
nitpick: Also this commit isn't really a chore: documentation update. You have new example notebooks, utility functions, etc. all being delivered as part of this. Looks a lot more like a new feature to me. |
Issue #, if available: n/a
Summary
This PR introduces a Jupyter Notebook runbook and supporting utilities to streamline the deployment and execution of inference workflows using AWS SageMaker.
Key Additions
Runbook:
inference-runbook.ipynb
: A step-by-step guide to deploying and running inference pipelines with SageMaker. The notebook covers:Supporting Utility:
inference_utils.py
:Documentation:
README.md
: Provides detailed instructions for using the inference runbook, including prerequisites, setup steps, and example workflows.Benefits
inference_utils.py
to manage inference workflows programmatically.Testing
inference-runbook.ipynb
for functionality in SageMaker-compatible environments.inference_utils.py
functions for endpoint management and inference configuration handling.Next Steps
Before you submit a pull request, please make sure you have to following:
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.