-
Notifications
You must be signed in to change notification settings - Fork 167
Created a template to deploy API Gateway + Serverless endpoint #37
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
Conversation
|
Missing permissions to update a running project for the LaunchRole created in the template. Suggest reverting to default product launch role (however note PR#39) or add to your custom one. Approved for merge once fixed. |
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.
|
Please take a look at the template for GitLab. The expectation for contributions is to automate the creation of the Service Catalog Product. The main readme in this repo provides a CFN template to create a Portfolio and each project template should have a CFN template to create a Product within that folder. Please update this PR so a user can leverage this template with a single CFN template. |
|
@kirit93 isn't it already like this? This PR follows the example of the serverless endpoint template, providing a single CFN file. The README file explains this also. |
This comment was marked as resolved.
This comment was marked as resolved.
|
@kirit93 I think I know why, the file https://github.com/aws-samples/sagemaker-custom-project-templates/pull/37/files#diff-13890f9e344706cad5a42295d1638cf9e82e1f17f65787ae8851fed6d9878f89 is too long so is hidden by default by GitHub. That's why it's not obvious to see at first glance. |



Issue #, if available: N/A
Description of changes:
This adds a new template to automate the deployment of models in the Amazon SageMaker model registry to SageMaker Serverlss Endpoints with a API Gateway for real-time inference. This project is derived from the built-in MLOps template for model deployment but uses serverless inference endpoints + API Gateway to provide a REST API.
@dgallitelli kindly agreed to review this PR. This will serve as an example used in a upcoming workshop material.
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.