AWS, Blog and System Architecture - Data Science Current

Create a multimodal chatbot tailored to your unique dataset with Amazon Bedrock FMs

AWS Machine Learning Blog

OCTOBER 14, 2024

In this post, we show how to create a multimodal chat assistant on Amazon Web Services (AWS) using Amazon Bedrock models, where users can submit images and questions, and text responses will be sourced from a closed set of proprietary documents. For this post, we recommend activating these models in the us-east-1 or us-west-2 AWS Region.

AWS

AWS AI AI System Architecture

Transforming financial analysis with CreditAI on Amazon Bedrock: Octus’s journey with AWS

AWS Machine Learning Blog

MARCH 10, 2025

We walk through the journey Octus took from managing multiple cloud providers and costly GPU instances to implementing a streamlined, cost-effective solution using AWS services including Amazon Bedrock, AWS Fargate , and Amazon OpenSearch Service. Along the way, it also simplified operations as Octus is an AWS shop more generally.

AWS

AWS Database AI AI

Real value, real time: Production AI with Amazon SageMaker and Tecton

AWS Machine Learning Blog

DECEMBER 4, 2024

Expand to generative AI use cases with your existing AWS and Tecton architecture After you’ve developed ML features using the Tecton and AWS architecture, you can extend your ML work to generative AI use cases. You can also find Tecton at AWS re:Invent. This process is shown in the following diagram.

ML

ML ML AWS AI

Webinars

How to Achieve High-Accuracy Results When Using LLMs

MORE WEBINARS

Build a dynamic, role-based AI agent using Amazon Bedrock inline agents

AWS Machine Learning Blog

FEBRUARY 13, 2025

AWS Lambda functions for executing specific actions (such as submitting vacation requests or expense reports). To understand how this dynamic role-based functionality works under the hood, lets examine the following system architecture diagram. Maira Ladeira Tanke is a Senior Generative AI Data Scientist at AWS.

AI

AI AI AWS ML

Rad AI reduces real-time inference latency by 50% using Amazon SageMaker

AWS Machine Learning Blog

NOVEMBER 26, 2024

Let’s transition to exploring solutions and architectural strategies. Approaches to researcher productivity To translate our strategic planning into action, we developed approaches focused on refining our processes and system architectures. He has a passion for continuous innovation and using data to drive business outcomes.

ML

ML ML AI AI

How Vidmob is using generative AI to transform its creative data landscape

AWS Machine Learning Blog

SEPTEMBER 6, 2024

In this post, we illustrate how Vidmob , a creative data company, worked with the AWS Generative AI Innovation Center (GenAIIC) team to uncover meaningful insights at scale within creative data using Amazon Bedrock. The chatbot built by AWS GenAIIC would take in this tag data and retrieve insights.

AWS

AWS AI AI Data Scientist

Build an Amazon SageMaker Model Registry approval and promotion workflow with human intervention

AWS Machine Learning Blog

JANUARY 10, 2024

In this post, we discuss how the AWS AI/ML team collaborated with the Merck Human Health IT MLOps team to build a solution that uses an automated workflow for ML model approval and promotion with human intervention in the middle. A model developer typically starts to work in an individual ML development environment within Amazon SageMaker.

ML

ML ML AWS Machine Learning

Automating product description generation with Amazon Bedrock

AWS Machine Learning Blog

NOVEMBER 24, 2023

This solution is available in the AWS Solutions Library. The system architecture comprises several core components: UI portal – This is the user interface (UI) designed for vendors to upload product images. AWS Lambda – AWS Lambda provides serverless compute for processing.

AWS

AWS Database AI AI

Accelerate pre-training of Mistral’s Mathstral model with highly resilient clusters on Amazon SageMaker HyperPod

AWS Machine Learning Blog

SEPTEMBER 18, 2024

The compute clusters used in these scenarios are composed of more than thousands of AI accelerators such as GPUs or AWS Trainium and AWS Inferentia , custom machine learning (ML) chips designed by Amazon Web Services (AWS) to accelerate deep learning workloads in the cloud. at a minimum).

Clustering

Clustering AWS ML ML

Moderate your Amazon IVS live stream using Amazon Rekognition

AWS Machine Learning Blog

NOVEMBER 17, 2023

You can deploy this solution to your AWS account using the AWS Cloud Development Kit (AWS CDK) package available in our GitHub repo. Using the AWS Management Console , you can create a recording configuration and link it to an Amazon IVS channel. In this section, we briefly introduce the system architecture.

AWS

AWS ML ML Algorithm

Reduce call hold time and improve customer experience with self-service virtual agents using Amazon Connect and Amazon Lex

AWS Machine Learning Blog

MARCH 31, 2023

Solution overview To tackle these challenges, the KYTC team reviewed several contact center solutions and collaborated with the AWS ProServe team to implement a cloud-based contact center and a virtual agent named Max. Amazon Lex and the AWS QnABot Amazon Lex is an AWS service for creating conversational interfaces.

AWS

AWS Natural Language Processing System Architecture Machine Learning

Accelerate disaster response with computer vision for satellite imagery using Amazon SageMaker and Amazon Augmented AI

AWS Machine Learning Blog

FEBRUARY 24, 2023

AWS recently released Amazon SageMaker geospatial capabilities to provide you with satellite imagery and geospatial state-of-the-art machine learning (ML) models, reducing barriers for these types of use cases. In this blog post we discussed using computer vision on satellite imagery.

ML

ML ML AWS Data Pipeline

Build a water consumption forecasting solution for a water utility agency using Amazon Forecast

AWS Machine Learning Blog

JANUARY 30, 2023

Create a new AWS Identity and Access Management (IAM) role. Conclusion In this post, we showed you how easy to use how to use Forecast and its underlying system architecture to predict water demand using water consumption data. The steps in this post demonstrated how to build the solution on the AWS Management Console.

ML

ML ML AWS System Architecture

LLMOps: What It Is, Why It Matters, and How to Implement It

The MLOps Blog

MARCH 12, 2024

Combine this with the serverless BentoCloud or an auto-scaling group on a cloud platform like AWS to ensure your resources match the demand. Caption : RAG system architecture. to ingest data from health forums, medical journals, and wellness blogs.

Database

Database Machine Learning Machine Learning AI

How Amazon Shopping uses Amazon Rekognition Content Moderation to review harmful images in product reviews

AWS Machine Learning Blog

AUGUST 15, 2023

The team successfully migrated a subset of self-managed ML models in the image moderation system for nudity and not safe for work (NSFW) content detection to the Amazon Rekognition Detect Moderation API, taking advantage of the highly accurate and comprehensive pre-trained moderation models.

ML

ML ML AWS System Architecture

Accelerate machine learning time to value with Amazon SageMaker JumpStart and PwC’s MLOps accelerator

AWS Machine Learning Blog

MAY 23, 2023

This is a guest blog post co-written with Vik Pant and Kyle Bassett from PwC. In this post, we start with an overview of MLOps and its benefits, describe a solution to simplify its implementations, and provide details on the architecture. The source code for these IaC templates is managed in AWS CodeCommit.

Machine Learning

Machine Learning Machine Learning AWS ML

Innovating at speed: BMW’s generative AI solution for cloud incident analysis

AWS Machine Learning Blog

MARCH 5, 2025

In this post, we explain how BMW uses generative AI technology on AWS to help run these digital services with high availability. Moreover, these teams might be geographically dispersed and run their workloads in different locations and regions; many hosted on AWS, some elsewhere.

AWS

AWS AI AI Machine Learning

Generative AI for agriculture: How Agmatix is improving agriculture with Amazon Bedrock

AWS Machine Learning Blog

NOVEMBER 12, 2024

This post describes how Agmatix uses Amazon Bedrock and AWS fully featured services to enhance the research process and development of higher-yielding seeds and sustainable molecules for global agriculture. AWS generative AI services provide a solution In addition to other AWS services, Agmatix uses Amazon Bedrock to solve these challenges.

AWS

AWS AI AI Data Lakes

Optimizing AI responsiveness: A practical guide to Amazon Bedrock latency-optimized inference

AWS Machine Learning Blog

JANUARY 28, 2025

This optimization is available in the US East (Ohio) AWS Region for select FMs, including Anthropics Claude 3.5 In this section, we explore how different system components and architectural decisions impact overall application responsiveness. Rupinder Grewal is a Senior AI/ML Specialist Solutions Architect with AWS.

AI

AI AI AWS ML

Build verifiable explainability into financial services workflows with Automated Reasoning checks for Amazon Bedrock Guardrails

AWS Machine Learning Blog

FEBRUARY 19, 2025

AWS FSI customers, including NASDAQ, State Bank of India, and Bridgewater, have used FMs to reimagine their business operations and deliver improved outcomes. The new Automated Reasoning checks safeguard is available today in preview in Amazon Bedrock Guardrails in the US West (Oregon) AWS Region. Happy building!

AWS

AWS Natural Language Processing Machine Learning Machine Learning

Data Science Current

Create a multimodal chatbot tailored to your unique dataset with Amazon Bedrock FMs

Transforming financial analysis with CreditAI on Amazon Bedrock: Octus’s journey with AWS

Webinars

Trending Sources

Real value, real time: Production AI with Amazon SageMaker and Tecton

Webinars

Build a dynamic, role-based AI agent using Amazon Bedrock inline agents

Rad AI reduces real-time inference latency by 50% using Amazon SageMaker

How Vidmob is using generative AI to transform its creative data landscape

Build an Amazon SageMaker Model Registry approval and promotion workflow with human intervention

Automating product description generation with Amazon Bedrock

Accelerate pre-training of Mistral’s Mathstral model with highly resilient clusters on Amazon SageMaker HyperPod

Moderate your Amazon IVS live stream using Amazon Rekognition

Reduce call hold time and improve customer experience with self-service virtual agents using Amazon Connect and Amazon Lex

Accelerate disaster response with computer vision for satellite imagery using Amazon SageMaker and Amazon Augmented AI

Build a water consumption forecasting solution for a water utility agency using Amazon Forecast

LLMOps: What It Is, Why It Matters, and How to Implement It

How Amazon Shopping uses Amazon Rekognition Content Moderation to review harmful images in product reviews

Accelerate machine learning time to value with Amazon SageMaker JumpStart and PwC’s MLOps accelerator

Innovating at speed: BMW’s generative AI solution for cloud incident analysis

Generative AI for agriculture: How Agmatix is improving agriculture with Amazon Bedrock

Optimizing AI responsiveness: A practical guide to Amazon Bedrock latency-optimized inference

Build verifiable explainability into financial services workflows with Automated Reasoning checks for Amazon Bedrock Guardrails

Stay Connected