OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Infrastructure & Serving

Generative AI Sagemaker Cdk Demo

A Python AWS CDK sample that provisions infrastructure for deploying generative AI models from Amazon SageMaker JumpStart and connecting clients to hosted model endpoints.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Generative AI Sagemaker Cdk Demo — OpenViST project profile in AI Infrastructure & Serving.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a code-defined AWS deployment pattern for JumpStart model serving and can work with Python, CDK, and AWS account and Region setup.

Who it is for

  • Developers building AWS infrastructure for SageMaker JumpStart model serving.
  • Teams exploring an API-backed web application architecture for hosted generative models.

Documented uses

  • Define repeatable cloud infrastructure for JumpStart generative-model endpoints.
  • Expose hosted models to a web application or other clients through API Gateway and Lambda.
  • Study a sample architecture combining model endpoints, application hosting, and a client interface.
Before you choose

Requirements & limits

The repository is public and lists an MIT-0 license.

  • The sample deploys models from SageMaker JumpStart rather than supplying a model.
  • The README’s example uses Stable Diffusion and FLAN-T5-XL.
  • The described application stack includes ECS with Fargate and an Application Load Balancer; model requests pass through API Gateway and Lambda.
  • The README describes the API Gateway endpoints in this example as publicly accessible.
  • The project is written in Python and requires AWS CDK bootstrapping for the deployment account and Region.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare the CDK project environment

Set up the documented Python environment and bootstrap AWS CDK for the account and Region where you plan to work.

Before you start

  • Python 3 and pip
  • The repository and its requirements.txt file
  • An AWS account and a target Region for CDK bootstrapping

Steps

  1. Create a virtual environment with the command below and activate it; on Windows, use .venv\Scripts\activate.bat.

    Documented command
    python3 -m venv .venv

  2. Upgrade pip with the command below.

    Documented command
    python3 -m pip install --upgrade pip

  3. Install project dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  4. Run cdk bootstrap for the default Region, or cdk bootstrap aws://ACCOUNT-NUMBER/REGION for a specified account and Region.

Expected outcome

The Python dependencies are installed and the selected AWS account and Region are bootstrapped for CDK applications.

Guide limitations

  • This covers preparation only; it does not deploy the application.
  • AWS account and Region details must be supplied for a non-default target.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
aws-samples/generative-ai-sagemaker-cdk-demo · Official homepage title · retained in its source language
How we review sourcesSuggest a correction