Q: How does the solution handle real-time and batch inference options?

A: Users have two options for provisioning the solution's pipeline: API calls to an Amazon API Gateway, or Git commits to a Git repository. In both options, the user specifies a configuration parameter for real-time or batch inference.

For real-time inferences, the pipeline creates an Amazon Sagemaker model and endpoint, then connects it to an Amazon API Gateway endpoint. The user then can call that API to run real-time inference jobs against the deployed model.

For batch inferences, the user provides an extra pipeline parameter that indicates the location of the batch inference data. When the pipeline is finished provisioning, it creates an Amazon SageMaker model, then runs the batch inference data against the created model.

Q: How does the solution support integration with third-party CI/CD deployment tools?

A: Users can provision a pipeline using API calls to Amazon API Gateway which allows them to integrate their CI/CD tools with the solution's framework. Users can operate the pipeline from the third-party CI/CD tool as long as the stages in the CI/CD tool are able to make HTTP API calls to the solution.

For example, if a user's CI/CD source code contains build, test, and deploy stages, they can make an HTTP API call to the solution to provision a pipeline and deploy their machine learning model.

Q: What are the feedback mechanisms for a model in production?

A: After the model is deployed, it supports a range of features such as model monitoring, drift detection, and custom integration tests through Amazon Sagemaker Endpoint.

Q: Can I deploy this solution in any AWS Region?

A: No. This solution uses the AWS CodePipeline and Amazon SageMaker services,
which are not currently available in all AWS Regions. Therefore, you must launch this solution in an AWS Region where these services are available. For the most current availability by Region, refer to the AWS Regional Services List.

Training and Certification

AWS Training and Certification builds your competence, confidence, and credibility through practical cloud skills that help you innovate and build your future.  Learn more »

ML Building Blocks: Services and Terminology

These two courses clarify both the machine learning stack and the terms and processes that will help you build a good foundation in machine learning.

Enroll now »

Demystifying AI/ML/DL

After taking this set of courses, you’ll understand how artificial intelligence (AI) led to machine learning (ML), which then led to deep learning (DL).

Enroll now »

AWS Certified Solutions Architect – Associate

This exam validates your ability to effectively demonstrate knowledge of how to architect and deploy secure and robust applications on AWS technologies.

Schedule your exam »

Partner resources

The AWS Partner Network (APN) is focused on helping partners build successful AWS-based businesses to drive superb solutions and customer experiences. APN Partners are focused on customer success, helping you take full advantage of all the business benefits that AWS has to offer. With their deep expertise on AWS, APN Partners are uniquely positioned to help your company at any stage of your Cloud Adoption Journey and to help you solve some of your most complex problems.

Need more resources to get started with AWS?

Visit the Getting Started Resource Center to find tutorials, projects and videos to get started with AWS.

Learn more »