Build RAG-based generative AI applications in AWS using Amazon FSx for NetApp ONTAP with Amazon Bedrock

This article discusses how to build retrieval augmented generation (RAG) based generative AI applications in AWS using Amazon FSx for NetApp ONTAP with Amazon Bedrock.

Specifically, the article covers:

• An overview of the solution that uses FSx for ONTAP with Amazon Bedrock to provide a RAG experience for generative AI applications by bringing company-specific unstructured file data to Amazon Bedrock
• How the solution uses an FSx for ONTAP file system as the source of unstructured data and continuously populates an OpenSearch Serverless vector database with files, folders, and associated metadata including security ACLs
• Architectural details and components like the RAG Retrieval Lambda function, embeddings container, chatbot application, and API Gateway interface
• Steps to deploy the solution using Terraform and test it using the chatbot UI or API Gateway with permissions-based access control
• Conclusion highlighting the benefits of using the solution to build generative AI applications that can access authorized company data from FSx for ONTAP