In this blog, we will use the AWS Generative AI Constructs Library to deploy a complete RAG application composed of the following components:
- Knowledge Bases for Amazon Bedrock: This is the foundation for the RAG solution.
- OpenSearch Serverless collection: It supports the vector search collection type that provides similarity search capability.
- An S3 bucket: This will act as the data source for the Knowledge Base.
- AWS Lambda function (written in Python) along with an API Gateway that uses the RetrieveAndGenerate API to query the knowledge base and generate responses from the information it retrieves.