This repo provides samples to demonstrate how to build your own Generative AI solutions using AWS Generative AI CDK Constructs.
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 Inferentia 2 | 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 Inferentia 2 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 |
Bedrock Agents | This sample provides a sample application which deploys a Bedrock Agent and Knowledge Base backed by an OpenSearch Serverless Collection and documents in S3. It demonstrates how to use the Bedrock CDK construct. | TypeScript |
Please refer to the CONTRIBUTING document for further details on contributing to this repository.