aws-solutions-library-samples
Change the repository type filter
All
Repositories list
275 repositories
- This Guidance demonstrates a scalable, serverless approach for automated document processing and information extraction using AWS services, such as Amazon Bedrock Data Automation and Amazon Bedrock foundational models. It combines generative AI and optical character recognition (OCR) to process documents at scale.
- The Open Source 3D Reconstruction Toolbox for Gaussian Splats provides an end-to-end, pipeline-based guidance on AWS to reconstruct 3D scenes or objects from images or video inputs.
- Comprehensive, scalable ML inference architecture using Amazon EKS, leveraging Graviton processors for cost-effective CPU-based inference and GPU instances for accelerated inference. Guidance provides a complete end-to-end platform for deploying LLMs with agentic AI capabilities, including RAG and MCP
- The EKS workload accelerator is a collection of reference implementations for Amazon EKS designed to accelerate the time it takes to provision a workload ready EKS cluster. It includes an "opinionated" set of pre-configured and integrated tools/add-ons, and best practices to support core capabilities including Autoscaling, Observability, Networking
- The AWS Game Backend Framework allows you to integrate your game clients with AWS backend services, with secure scalable identity management and authentication, and integrations to commonly used game platform identity providers and game engines.
- Guidance for Clickstream Analytics on AWS source code
- This Guidance demonstrates how to effectively orchestrate multiple specialized AI agents to solve complex customer support challenges through different coordination mechanisms on AWS. Modern customer service environments demand sophisticated handling of multi-step interactions, personalized responses, and seamless access to various data sources.
- This project demonstrates how to build a cost-effective Retrieval-Augmented Generation (RAG) solution using Amazon DynamoDB as a vector store for small use cases, enabling small businesses to implement AI personalization without the high costs typically associated with specialized vector databases.
- HPC on AWS removes the long wait times and lost productivity often associated with on-premises HPC clusters. Flexible HPC cluster configurations and virtually unlimited scalability allows you to grow and shrink your infrastructure as your workloads dictate, not the other way around
- Guidance for Media2Cloud on AWS solution (formerly known as AWS Media2Cloud Solution) is designed to demonstrate a serverless ingest framework that can quickly setup a baseline ingest workflow for placing video assets and associated metadata under management control of an AWS customer.
data-lakes-on-aws
PublicEnterprise-grade, production-hardened, serverless data lake on AWS- Infrastructure deployment automation of SageMaker HyperPod clusters based on EKS and SLURM orchestration and Protein Language ESM-2 model training job definitions including NVIDIA BioNemo
- This GenAI solution enables users to extract insights from diverse data formats (video, audio, PDFs, text) through a unified interface. Using AWS AI services, it processes and indexes content at scale, provides quick summaries, and delivers contextualized answers with direct links to source materials.
- This Guidance shows how to create a battery digital twin, a virtual representation of a physical electric vehicle battery or battery energy storage system (BESS), and overlay real-time data such as voltage, current, and temperature.
- This Guidance demonstrates how to deploy Cloud Intelligence Dashboards in your AWS environment using AWS CloudFormation templates or command line tools. These pre-built dashboards enable you to drive financial accountability, optimize costs, and track usage goals across their AWS infrastructure.
- The Game Analytics Pipeline solution helps game developers to apply a flexible, and scalable DataOps methodology to their games. Allowing them to continuously integrate, and continuously deploy a scalable serverless data pipeline for ingesting, storing, and analyzing telemetry data generated from games, and services.