AWS Machine Learning Blog

Category: Storage

Multilingual content processing using HAQM Bedrock and HAQM A2I

This post outlines a custom multilingual document extraction and content assessment framework using a combination of Anthropic’s Claude 3 on HAQM Bedrock and HAQM A2I to incorporate human-in-the-loop capabilities.

Build a reverse image search engine with HAQM Titan Multimodal Embeddings in HAQM Bedrock and AWS managed services

In this post, you will learn how to extract key objects from image queries using HAQM Rekognition and build a reverse image search engine using HAQM Titan Multimodal Embeddings from HAQM Bedrock in combination with HAQM OpenSearch Serverless Service.

http://issues.haqm.com/issues/ML-15995

Implement HAQM SageMaker domain cross-Region disaster recovery using custom HAQM EFS instances

In this post, we guide you through a step-by-step process to seamlessly migrate and safeguard your SageMaker domain from one active Region to another passive or active Region, including all associated user profiles and files.

Use HAQM SageMaker Studio with a custom file system in HAQM EFS

In this post, we explore three scenarios demonstrating the versatility of integrating HAQM EFS with SageMaker Studio. These scenarios highlight how HAQM EFS can provide a scalable, secure, and collaborative data storage solution for data science teams.

Build RAG-based generative AI applications in AWS using HAQM FSx for NetApp ONTAP with HAQM Bedrock

Build RAG-based generative AI applications in AWS using HAQM FSx for NetApp ONTAP with HAQM Bedrock

In this post, we demonstrate a solution using HAQM FSx for NetApp ONTAP with HAQM Bedrock to provide a RAG experience for your generative AI applications on AWS by bringing company-specific, unstructured user file data to HAQM Bedrock in a straightforward, fast, and secure way.

Elevate customer experience through an intelligent email automation solution using HAQM Bedrock

Elevate customer experience through an intelligent email automation solution using HAQM Bedrock

In this post, we show you how to use HAQM Bedrock to automate email responses to customer queries. With our solution, you can identify the intent of customer emails and send an automated response if the intent matches your existing knowledge base or data sources. If the intent doesn’t have a match, the email goes to the support team for a manual response.

Implement web crawling in HAQM Bedrock Knowledge Bases

HAQM Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading artificial intelligence (AI) companies like AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and HAQM through a single API, along with a broad set of capabilities to build generative AI applications with security, privacy, and responsible AI. With […]

The Weather Company enhances MLOps with HAQM SageMaker, AWS CloudFormation, and HAQM CloudWatch

In this post, we share the story of how The Weather Company (TWCo) enhanced its MLOps platform using services such as HAQM SageMaker, AWS CloudFormation, and HAQM CloudWatch. TWCo data scientists and ML engineers took advantage of automation, detailed experiment tracking, integrated training, and deployment pipelines to help scale MLOps effectively. TWCo reduced infrastructure management time by 90% while also reducing model deployment time by 20%.