Tracking Generative AI Usage With Amazon Bedrock Inference Profiles

Amazon Bedrock provides generative AI and machine-learning models as a service enabling you to use them in your infrastructure without worrying about the technical complexity of model deployment, hosting, and scaling. Inference profiles in Amazon Bedrock allow you to access models across regions and to track model usage and cost.

Learning how to use Amazon Bedrock inference profiles will benefit anyone looking to use and keep track of models in the public AWS cloud.

In this hands-on lab, you will create inference profiles, and use them to track model usage.

Learning objectives

Upon completion of this beginner-level lab, you will be able to:

• Create Amazon Bedrock inference profiles
• Implement model usage tracking in Python
• Test accessing a model using Amazon API Gateway
• Observe model usage using Amazon CloudWatch

Intended audience

• Anyone looking to make use of generative AI in AWS
• Cloud Architects
• Data Engineers
• DevOps Engineers
• Machine Learning Engineers
• Software Engineers

Prerequisites

Familiarity with the following will be beneficial but is not required:

• Amazon Bedrock
• AWS Lambda
• API Gateway
• Amazon CloudWatch
• The Python scripting language

The following content can be used to fulfill the prerequisites:

• Interacting with Amazon Bedrock Foundation Models using APIs
• Understanding AWS Lambda to Run and Scale Your Code
• Introduction to Amazon API Gateway
• Python for Beginners
• An Overview of Amazon CloudWatch