Using Generative AI from Amazon Aurora

Amazon Bedrock is an offering from AWS that allows you to make use of large language models without having to worry about the technical complexity of training, deploying, or hosting them. You can access the models through the Amazon Bedrock API, and you only pay for the prompts and responses you use.

Learning how to integrate Amazon Bedrock with Amazon RDS Aurora MySQL will benefit anyone who regularly works with databases or anyone looking to learn more about how to use AI models in their applications.

In this hands-on lab, you will configure an Amazon Aurora MySQL RDS cluster to access Amazon Bedrock, use SQL to call a model to generate synthetic data, and you will use a model to enrich data in a table.

Please note: This lab creates an Amazon Aurora MySQL cluster, which takes approximately ten minutes to complete. Please ensure you have enough time available before starting the lab.

Learning objectives

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

• Attach a Bedrock IAM policy to an IAM role
• Configure an Amazon Aurora RDS MySQL cluster to use Amazon Bedrock
• Use SQL to call an Amazon Bedrock model to generate synthetic data
• Use an Amazon Bedrock model to enrich data in a table

Intended audience

• Candidates for the AWS Certified Machine Learning Specialty
• Cloud Architects
• Data Engineers
• DevOps Engineers
• Machine Learning Engineers
• Software Engineers

Prerequisites

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

• Amazon Aurora MySQL
• Amazon Bedrock
• Structured Query Language (SQL)

The following content can be used to fulfill the prerequisites:

• Introduction to Amazon RDS & DynamoDB
• Interacting with Amazon Bedrock Foundation Models using APIs
• Introduction to SQL

Updates

July 11th, 2025 - Updated lab instructions to use Amazon Nova Micro model