AWS Machine Learning Blog

NOVEMBER 13, 2024

Recognizing this need, we have developed a Chrome extension that harnesses the power of AWS AI and generative AI services, including Amazon Bedrock , an AWS managed service to build and scale generative AI applications with foundation models (FMs). The user signs in by entering a user name and a password.

AWS 136

AWS AI AI Natural Language Processing 136

AWS Machine Learning Blog

NOVEMBER 18, 2024

Between monitoring, analyzing, and documenting architectural findings, a lack of crucial information can leave your organization vulnerable to potential risks and inefficiencies. Prerequisites For this walkthrough, the following are required: An AWS account. AWS Management Console access. A Python 3.12 environment.

AWS 116

AWS AI AI Machine Learning 116

AWS Machine Learning Blog

NOVEMBER 19, 2024

The excitement is building for the fourteenth edition of AWS re:Invent, and as always, Las Vegas is set to host this spectacular event. Third, we’ll explore the robust infrastructure services from AWS powering AI innovation, featuring Amazon SageMaker , AWS Trainium , and AWS Inferentia under AI/ML, as well as Compute topics.

AWS 109

AWS ML ML AI 109

AWS Machine Learning Blog

NOVEMBER 7, 2024

It also uses a number of other AWS services such as Amazon API Gateway , AWS Lambda , and Amazon SageMaker. You can use AWS services such as Application Load Balancer to implement this approach. Some applications may need to access data with personal identifiable information (PII) while others may rely on noncritical data.

AWS 121

AWS AI AI Machine Learning 121

AWS Machine Learning Blog

NOVEMBER 15, 2024

This wealth of content provides an opportunity to streamline access to information in a compliant and responsible way. Principal wanted to use existing internal FAQs, documentation, and unstructured data and build an intelligent chatbot that could provide quick access to the right information for different roles.

AWS 121

AWS AI AI Machine Learning 121

AWS Machine Learning Blog

DECEMBER 11, 2024

Earlier this year, we published the first in a series of posts about how AWS is transforming our seller and customer journeys using generative AI. Field Advisor serves four primary use cases: AWS-specific knowledge search With Amazon Q Business, weve made internal data sources as well as public AWS content available in Field Advisors index.

AWS 113

AWS Database AI AI 113

AWS Machine Learning Blog

NOVEMBER 26, 2024

AWS Trainium and AWS Inferentia based instances, combined with Amazon Elastic Kubernetes Service (Amazon EKS), provide a performant and low cost framework to run LLMs efficiently in a containerized environment. For more information on how to view and increase your quotas, refer to Amazon EC2 service quotas.

AWS 107

AWS Clustering ML ML 107

AWS Machine Learning Blog

DECEMBER 9, 2024

It simplifies the often complex and time-consuming tasks involved in setting up and managing an MLflow environment, allowing ML administrators to quickly establish secure and scalable MLflow environments on AWS. AWS CodeArtifact , which provides a private PyPI repository so that SageMaker can use it to download necessary packages.

AWS 106

AWS ML ML Data Scientist 106

AWS Machine Learning Blog

NOVEMBER 13, 2024

A reverse image search engine enables users to upload an image to find related information instead of using text-based queries. The AWS Command Line Interface (AWS CLI) installed on your machine to upload the dataset to Amazon S3. For more information on managing credentials securely, see the AWS Boto3 documentation.

AWS 123

AWS Database K-nearest Neighbors AI 123

AWS Machine Learning Blog

DECEMBER 24, 2024

To simplify infrastructure setup and accelerate distributed training, AWS introduced Amazon SageMaker HyperPod in late 2023. In this blog post, we showcase how you can perform efficient supervised fine tuning for a Meta Llama 3 model using PEFT on AWS Trainium with SageMaker HyperPod. architectures/5.sagemaker-hyperpod/LifecycleScripts/base-config/

AWS 111

AWS Clustering Deep Learning Deep Learning 111

AWS Machine Learning Blog

APRIL 3, 2025

Every year, AWS Sales personnel draft in-depth, forward looking strategy documents for established AWS customers. These documents help the AWS Sales team to align with our customer growth strategy and to collaborate with the entire sales team on long-term growth ideas for AWS customers.

AWS 113

AWS AI AI Database 113

AWS Machine Learning Blog

JANUARY 7, 2025

To address this need, AWS generative AI best practices framework was launched within AWS Audit Manager , enabling auditing and monitoring of generative AI applications. The agent then interprets the users request and determines if actions need to be invoked or information needs to be retrieved from a knowledge base.

AWS 118

AWS AI AI Database 118

AWS Machine Learning Blog

APRIL 1, 2025

Were excited to announce the open source release of AWS MCP Servers for code assistants a suite of specialized Model Context Protocol (MCP) servers that bring Amazon Web Services (AWS) best practices directly to your development workflow. This post is the first in a series covering AWS MCP Servers.

AWS 127

AWS AI AI Python 127

AWS Machine Learning Blog

NOVEMBER 22, 2024

Because Amazon Bedrock is serverless, you don’t have to manage any infrastructure, and you can securely integrate and deploy generative AI capabilities into your applications using the AWS services you are already familiar with. client( service_name="bedrock-runtime", region_name="us-east-1" ) Define the model to invoke using its model ID.

AWS 102

AWS Python AI AI 102

AWS Machine Learning Blog

DECEMBER 26, 2024

The potential for such large business value is galvanizing tens of thousands of enterprises to build their generative AI applications in AWS. This post addresses these cost considerations so you can optimize your generative AI costs in AWS. The costs, limits, and models can change over time.

AWS 143

AWS Database AI AI 143

AWS Machine Learning Blog

NOVEMBER 22, 2024

This post discusses how to use AWS Step Functions to efficiently coordinate multi-step generative AI workflows, such as parallelizing API calls to Amazon Bedrock to quickly gather answers to lists of submitted questions.

AWS 99

AWS AI AI Database 99

Flipboard

APRIL 9, 2025

For example, a marketing content creation application might need to perform task types such as text generation, text summarization, sentiment analysis, and information extraction as part of producing high-quality, personalized content. Each distinct task type will likely require a separate LLM, which might also be fine-tuned with custom data.

AWS 169

AWS AI AI Database 169

AWS Machine Learning Blog

OCTOBER 31, 2024

Previously, setting up a custom labeling job required specifying two AWS Lambda functions: a pre-annotation function, which is run on each dataset object before it’s sent to workers, and a post-annotation function, which is run on the annotations of each dataset object and consolidates multiple worker annotations if needed.

AWS 123

AWS Natural Language Processing ML ML 123

Flipboard

MAY 28, 2025

Rufus is an AI-powered shopping assistant designed to help customers make informed purchasing decisions. This post focuses on how the QP model used draft centric speculative decoding (SD)also called parallel decodingwith AWS AI chips to meet the demands of Prime Day. Rufus extended the base LLM with multiple decoding heads.

AWS 97

AWS AI AI Machine Learning 97

Flipboard

DECEMBER 3, 2024

Syngenta and AWS collaborated to develop Cropwise AI , an innovative solution powered by Amazon Bedrock Agents , to accelerate their sales reps’ ability to place Syngenta seed products with growers across North America. For sales representatives, it empowers them with deeper insights, enabling more informed recommendations.

AWS 146

AWS AI AI Machine Learning 146

AWS Machine Learning Blog

MARCH 10, 2025

Investment professionals face the mounting challenge of processing vast amounts of data to make timely, informed decisions. This challenge is particularly acute in credit markets, where the complexity of information and the need for quick, accurate insights directly impacts investment outcomes.

AWS 114

AWS Database AI AI 114

AWS Machine Learning Blog

OCTOBER 31, 2024

AWS offers powerful generative AI services , including Amazon Bedrock , which allows organizations to create tailored use cases such as AI chat-based assistants that give answers based on knowledge contained in the customers’ documents, and much more. The following figure illustrates the high-level design of the solution.

AWS 130

AWS AI AI Python 130

AWS Machine Learning Blog

MAY 16, 2025

In this post, we share how Amazon Web Services (AWS) is helping Scuderia Ferrari HP develop more accurate pit stop analysis techniques using machine learning (ML). Since implementing the solution with AWS, track operations engineers can synchronize the data up to 80% faster than manual methods.

AWS 83

AWS Machine Learning Machine Learning ML 83

Flipboard

NOVEMBER 19, 2024

Amazon Bedrock offers a serverless experience so you can get started quickly, privately customize FMs with your own data, and integrate and deploy them into your applications using AWS tools without having to manage infrastructure. This can lead to inefficiencies, delays, and errors, diminishing customer satisfaction.

AWS 147

AWS AI AI ML 147

AWS Machine Learning Blog

NOVEMBER 26, 2024

Using vLLM on AWS Trainium and Inferentia makes it possible to host LLMs for high performance inference and scalability. Deploy vLLM on AWS Trainium and Inferentia EC2 instances In these sections, you will be guided through using vLLM on an AWS Inferentia EC2 instance to deploy Meta’s newest Llama 3.2 You will use inf2.xlarge

AWS 109

AWS AI AI Artificial Intelligence 109

AWS Machine Learning Blog

APRIL 3, 2025

Theyre constantly seeking ways to use their vast amounts of information to gain competitive advantages. This post explores how OMRON Europe is using Amazon Web Services (AWS) to build its advanced ODAP and its progress toward harnessing the power of generative AI. Data is one of the most critical assets of many organizations.

AWS 88

AWS Data Governance Data Silos SQL 88

AWS Machine Learning Blog

NOVEMBER 7, 2024

These indexes enable efficient searching and retrieval of part data and vehicle information, providing quick and accurate results. The agents also automatically call APIs to perform actions and access knowledge bases to provide additional information.

AWS 134

AWS Python AI AI 134

Flipboard

JANUARY 24, 2025

Use the AWS generative AI scoping framework to understand the specific mix of the shared responsibility for the security controls applicable to your application. The following figure of the AWS Generative AI Security Scoping Matrix summarizes the types of models for each scope.

AWS 156

AWS AI AI Data Warehouse 156

Flipboard

FEBRUARY 11, 2025

Amazon Q Business , a new generative AI-powered assistant, can answer questions, provide summaries, generate content, and securely complete tasks based on data and information in an enterprises systems. Then we introduce the solution deployment using three AWS CloudFormation templates.

AWS 138

AWS ML ML Machine Learning 138

Flipboard

NOVEMBER 22, 2024

Seamless integration of latest foundation models (FMs), Prompts, Agents, Knowledge Bases, Guardrails, and other AWS services. Complete execution path information showing input, output, execution time, and errors for each node. Set up your knowledge base with relevant customer service documentation, FAQs, and product information.

AWS 163

AWS AI AI Machine Learning 163

AWS Machine Learning Blog

FEBRUARY 26, 2025

ByteDance is a technology company that operates a range of content platforms to inform, educate, entertain, and inspire people across languages, cultures, and geographies. Cross-modal attention mechanisms facilitate information exchange between modalities, and fusion layers combine representations from different modalities.

AWS 96

AWS ML ML Clustering 96

AWS Machine Learning Blog

NOVEMBER 14, 2024

Additionally, sensitive information filters can be applied to protect personally identifiable information (PII) from being incorporated into generated images. Word filters can be set up to detect and block specific phrases or terms that may lead to undesirable image outputs.

AWS 123

AWS AI AI Machine Learning 123

AWS Machine Learning Blog

NOVEMBER 14, 2024

For a multi-account environment, you can track costs at an AWS account level to associate expenses. A combination of an AWS account and tags provides the best results. Implement a tagging strategy A tag is a label you assign to an AWS resource. The AWS reserved prefix aws: tags provide additional metadata tracked by AWS.

ML 115

ML ML AWS Machine Learning 115

Flipboard

MAY 30, 2025

Scaling and load balancing The gateway can handle load balancing across different servers, model instances, or AWS Regions so that applications remain responsive. The AWS Solutions Library offers solution guidance to set up a multi-provider generative AI gateway. Leave us a comment and we will be glad to collaborate.

AWS 117

AWS AI AI Database 117

Flipboard

JUNE 5, 2025

AWS has always provided customers with choice. In terms of hardware choice, in addition to NVIDIA GPUs and AWS custom AI chips, CPU-based instances represent (thanks to the latest innovations in CPU hardware) an additional choice for customers who want to run generative AI inference, like hosting small language models and asynchronous agents.

AWS 91

AWS AI AI ML 91

Flipboard

MAY 13, 2025

In this post, we demonstrate a solution using Amazon Elastic Kubernetes Service (EKS) with Amazon Bedrock to build scalable and containerized RAG solutions for your generative AI applications on AWS while bringing your unstructured user file data to Amazon Bedrock in a straightforward, fast, and secure way. Sonnet on Amazon Bedrock.

AWS 138

AWS AI AI Clustering 138

AWS Machine Learning Blog

APRIL 11, 2025

The AWS DeepRacer League is the worlds first autonomous racing league, open to anyone. In December 2024, AWS launched the AWS Large Language Model League (AWS LLM League) during re:Invent 2024. Response quality : Depth, accuracy, and contextual understanding.

AWS 122

AWS Machine Learning Machine Learning ML 122