Open-source repo with demo of Generative AI RAG solution using Amazon Bedrock and OpenSearch Serverless - Using the Well-Architected Machine Learning Lens PDF to prepare for the AWS Machine Learning Engineer Associate (MLA-C01) Certification Exam
This is a CDK project written in TypeScript to demo how to implement a RAG solution using Amazon Bedrock and Amazon OpenSearch Serverless
For more details on how to deploy the infrastructure and the solution details, please refer to the Blog Posts:
- Part 1: Build the Amazon OpenSearch Serverless Vector Db using AWS-CDK.
- Part 2: Build the MCQ orchestrator using Bedrock Converse API.
Architecture Diagram: RAG App using Amazon Bedrock and AOSS (Amazon OpenSearch Serverless) running on ECS Fargate
Architecture Diagram: RAG App with Cognito Authenitcation using Amazon Bedrock and AOSS (Amazon OpenSearch Serverless) running on ECS Fargate
- Part 4: Integrating Cognito Authentication with ECS Fargate, Bedrock, and OpenSearch Serverless.
- Part 5: Enhancing Security Posture of the GenAI Application.
Architecture Diagram: Event-Driven Document Indexing RAG App with Cognito Authenitcation using Amazon Bedrock and AOSS (Amazon OpenSearch Serverless) running on ECS Fargate
Architecture Diagram: Event-Driven Document Indexing RAG App with Cognito Authenitcation using Amazon Bedrock and AOSS (Amazon OpenSearch Serverless) running on EKS Cluster
-
Part 9: Optimizing ECS and EKS Infrastructure with AWS Graviton.
-
Part 10: Develop Cost Sensitive Self-Terminating Resources Using CDK Aspects and Advanced CDK Tips.
The cdk.json
file tells the CDK Toolkit how to execute your app.
npm run build
compile typescript to jsnpm run watch
watch for changes and compilenpm run test
perform the jest unit testsnpx cdk deploy
deploy this stack to your default AWS account/regionnpx cdk diff
compare deployed stack with current statenpx cdk synth
emits the synthesized CloudFormation template