Sample Apps for AWS Generative AI CDK Constructs

This repo provides samples to demonstrate how to build your own Generative AI solutions using AWS Generative AI CDK Constructs.

Getting started

Use Case	Description	Language
Document Explorer	This sample provides an end-to-end experience that allows a user to ingest documents into a knowledge base, then summarize and ask questions against those documents.	TypeScript
SageMaker JumpStart model	This sample provides a sample application which deploys a SageMaker real-time endpoint hosting a Llama 2 foundation model developed by Meta from Amazon JumpStart, and an AWS Lambda function to run inference requests against that endpoint.	TypeScript
SageMaker Hugging Face model	This sample provides a sample application which deploys a SageMaker real-time endpoint hosting a model (Mistral 7B) from Hugging Face, and an AWS Lambda function to run inference requests against that endpoint.	TypeScript
SageMaker Hugging Face model on AWS Inferentia2	This sample provides a sample application which deploys a SageMaker real-time endpoint hosting a model (Zephyr 7B) from Hugging Face, and an AWS Lambda function to run inference requests against that endpoint. This sample uses Inferentia 2 as the hardware accelerator.	TypeScript
SageMaker custom endpoint	This sample provides a sample application which deploys a SageMaker real-time endpoint hosting a model with artifacts stored in an Amazon Simple Storage Service (S3) bucket, and an AWS Lambda function to run inference requests against that endpoint. This sample uses Inferentia2 as the hardware accelerator.	TypeScript
SageMaker multimodal custom endpoint	This sample provides a sample application which deploys a SageMaker real-time endpoint hosting llava-1.5-7b, with artifacts stored in an Amazon Simple Storage Service (S3) bucket, a custom inference script, and an AWS Lambda function to run inference requests against that endpoint.	TypeScript
LLM on SageMaker in GovCloud PDT	This sample provides a sample application which deploys a SageMaker real-time endpoint hosting Falcon-40b on GovCloud PDT.	TypeScript
Amazon Bedrock Agents	This sample provides a sample application which deploys an Amazon Bedrock Agent and Knowledge Base backed by an OpenSearch Serverless Collection and documents in S3. It demonstrates how to use the Amazon Bedrock CDK construct.	TypeScript

Contributing

Please refer to the CONTRIBUTING document for further details on contributing to this repository.