Category: Artificial Intelligence

In this post, we discuss how Amazon Bedrock Knowledge Bases provides a powerful solution for numerical analysis on documents. You can deploy this solution in an AWS account and use it to analyze different types of documents.

In this post, we show how you can discover and deploy the Llama 3.2 11B Vision model using SageMaker JumpStart. We also share the supported instance types and context for all the Llama 3.2 models available in SageMaker JumpStart.

This is the first time that the Llama models from Meta have been released with vision capabilities. These new capabilities expand the usability of Llama models from their traditional text-only applications. In this post, we demonstrate how you can use Llama 3.2 11B and 90B models for a variety of vision-based use cases.

In this post, we show you how DoorDash built a generative AI agent using Amazon Connect, Amazon Lex, and Amazon Bedrock Knowledge Bases to provide a low-latency, self-service experience for their delivery workers.

In this post, we share how Karini AI’s migration of vector embedding models from Kubernetes to Amazon SageMaker endpoints improved concurrency by 30% and saved over 23% in infrastructure costs.

The International Research Centre on Artificial Intelligence (IRCAI), Zindi, and Amazon Web Services (AWS) are proud to announce the launch of the “AI for Equity Challenge: Climate Action, Gender, and Health”—a global virtual competition aimed at empowering organizations to use advanced AI and cloud technologies to drive real-world impact with a focus on benefitting vulnerable populations around the world.

In this post, we explain how to use Anthropic Claude on Amazon Bedrock to generate synthetic data for evaluating your RAG system.

In this blog post, we show you how Amazon Rekognition can mitigate congestion at traffic intersections and reduce operations and maintenance costs.

In this post, we present a real-world use case analyzing the Diabetes 130-US hospitals dataset to develop an ML model that predicts the likelihood of readmission after discharge.

In this post, we analyze strategies for governing access to Amazon Bedrock and SageMaker JumpStart models from within SageMaker Canvas using AWS Identity and Access Management (IAM) policies. You’ll learn how to create granular permissions to control the invocation of ready-to-use Amazon Bedrock models and prevent the provisioning of SageMaker endpoints with specified SageMaker JumpStart models.