AWS Machine Learning Blog

AUGUST 9, 2024

Question and answering (Q&A) using documents is a commonly used application in various use cases like customer support chatbots, legal research assistants, and healthcare advisors. In this collaboration, the AWS GenAIIC team created a RAG-based solution for Deltek to enable Q&A on single and multiple government solicitation documents.

AWS 129

AWS AI AI Database 129

Flipboard

JUNE 20, 2023

For reference, GPT-3, an earlier generation LLM has 175 billion parameters and requires months of non-stop training on a cluster of thousands of accelerated processors. The Carbontracker study estimates that training GPT-3 from scratch may emit up to 85 metric tons of CO2 equivalent, using clusters of specialized hardware accelerators.

AWS 123

AWS Machine Learning Machine Learning ML 123

AWS Machine Learning Blog

SEPTEMBER 4, 2024

A challenge for DevOps engineers is the additional complexity that comes from using Kubernetes to manage the deployment stage while resorting to other tools (such as the AWS SDK or AWS CloudFormation ) to manage the model building pipeline. kubectl for working with Kubernetes clusters. eksctl for working with EKS clusters.

AWS 107

AWS Clustering ML ML 107

AWS Machine Learning Blog

MAY 1, 2024

Llama2 by Meta is an example of an LLM offered by AWS. To learn more about Llama 2 on AWS, refer to Llama 2 foundation models from Meta are now available in Amazon SageMaker JumpStart. Virginia) and US West (Oregon) AWS Regions, and most recently announced general availability in the US East (Ohio) Region.

AWS 122

AWS ML ML Clustering 122

AWS Machine Learning Blog

JANUARY 24, 2024

We demonstrate how to build an end-to-end RAG application using Cohere’s language models through Amazon Bedrock and a Weaviate vector database on AWS Marketplace. Additionally, you can securely integrate and easily deploy your generative AI applications using the AWS tools you are already familiar with.

AWS 144

AWS Database AI AI 144

AWS Machine Learning Blog

MARCH 15, 2024

Therefore, ML creates challenges for AWS customers who need to ensure privacy and security across distributed entities without compromising patient outcomes. Solution overview We deploy FedML into multiple EKS clusters integrated with SageMaker for experiment tracking. As always, AWS welcomes your feedback.

AWS 139

AWS ML ML Machine Learning 139

Flipboard

NOVEMBER 17, 2023

The Retrieval-Augmented Generation (RAG) framework augments prompts with external data from multiple sources, such as document repositories, databases, or APIs, to make foundation models effective for domain-specific tasks. Set up a MongoDB cluster To create a free tier MongoDB Atlas cluster, follow the instructions in Create a Cluster.

K-nearest Neighbors 170

K-nearest Neighbors AWS Clustering Database 170

AWS Machine Learning Blog

MAY 30, 2024

Because Amazon Bedrock is serverless, you don’t have to manage infrastructure, and you can securely integrate and deploy generative AI capabilities into your applications using the AWS services you are already familiar with. AWS Prototyping developed an AWS Cloud Development Kit (AWS CDK) stack for deployment following AWS best practices.

AWS 127

AWS SQL Database AI 127

AWS Machine Learning Blog

NOVEMBER 1, 2023

Organizations can search for PII using methods such as keyword searches, pattern matching, data loss prevention tools, machine learning (ML), metadata analysis, data classification software, optical character recognition (OCR), document fingerprinting, and encryption. This speeds up the PII detection process and also reduces the overall cost.

AWS 119

AWS Machine Learning Machine Learning ML 119

AWS Machine Learning Blog

FEBRUARY 2, 2024

In this post, you’ll see an example of performing drift detection on embedding vectors using a clustering technique with large language models (LLMS) deployed from Amazon SageMaker JumpStart. Then we use K-Means to identify a set of cluster centers. A visual representation of the silhouette score can be seen in the following figure.

AWS 124

AWS Clustering ETL Database 124

Flipboard

NOVEMBER 27, 2024

dbt helps manage data transformation by enabling teams to deploy analytics code following software engineering best practices such as modularity, continuous integration and continuous deployment (CI/CD), and embedded documentation. Choose the us-east-1 AWS Region in which to create the stack. Create dbt models in dbt Cloud.

ETL 139

ETL Data Warehouse Analytics Analytics 139

AWS Machine Learning Blog

JULY 3, 2023

Companies across various industries create, scan, and store large volumes of PDF documents. There’s a need to find a scalable, reliable, and cost-effective solution to translate documents while retaining the original document formatting. It also uses the open-source Java library Apache PDFBox to create PDF documents.

AWS 99

AWS ML ML Clustering 99

AWS Machine Learning Blog

MAY 23, 2023

Original content production, code generation, customer service enhancement, and document summarization are typical use cases of generative AI. In April 2023, AWS unveiled Amazon Bedrock , which provides a way to build generative AI-powered apps via pre-trained models from startups including AI21 Labs , Anthropic , and Stability AI.

AWS 107

AWS AI AI ML 107

AWS Machine Learning Blog

MAY 30, 2024

In this post, we introduce the Media Analysis and Policy Evaluation solution, which uses AWS AI and generative AI services to provide a framework to streamline video extraction and evaluation processes. This solution, powered by AWS AI and generative AI services, meets these needs. This sample includes a basic inline policy.

AWS 127

AWS AI AI ML 127

Flipboard

FEBRUARY 16, 2023

Modern model pre-training often calls for larger cluster deployment to reduce time and cost. In October 2022, we launched Amazon EC2 Trn1 Instances , powered by AWS Trainium , which is the second generation machine learning accelerator designed by AWS. The following diagram shows an example.

Clustering 132

Clustering AWS Deep Learning Deep Learning 132

AWS Machine Learning Blog

NOVEMBER 13, 2024

Prerequisites To implement the proposed solution, make sure that you have the following: An AWS account and a working knowledge of FMs, Amazon Bedrock , Amazon SageMaker , Amazon OpenSearch Service , Amazon S3 , and AWS Identity and Access Management (IAM). Amazon Titan Multimodal Embeddings model access in Amazon Bedrock.

AWS 114

AWS Database K-nearest Neighbors AI 114

AWS Machine Learning Blog

MAY 31, 2024

In this blog post and open source project , we show you how you can pre-train a genomics language model, HyenaDNA , using your genomic data in the AWS Cloud. Amazon SageMaker Amazon SageMaker is a fully managed ML service offered by AWS, designed to reduce the time and cost associated with training and tuning ML models at scale.

AWS 115

AWS ML ML Machine Learning 115

AWS Machine Learning Blog

NOVEMBER 30, 2023

Building foundation models (FMs) requires building, maintaining, and optimizing large clusters to train models with tens to hundreds of billions of parameters on vast amounts of data. SageMaker HyperPod integrates the Slurm Workload Manager for cluster and training job orchestration.

Clustering 120

Clustering AWS Machine Learning Machine Learning 120

AWS Machine Learning Blog

JANUARY 15, 2025

Powered by generative AI services on AWS and large language models (LLMs) multi-modal capabilities, HCLTechs AutoWise Companion provides a seamless and impactful experience. This personalized document helps the customer gain a deeper understanding of the vehicle and supports their decision-making process.

AWS 103

AWS SQL AI AI 103

IBM Journey to AI blog

AUGUST 30, 2023

To ease this transition for customers unfamiliar with running containers in production, Amazon Web Services (AWS) has partnered with IBM and Red Hat to develop an IBM MAS on Red Hat OpenShift Service for AWS (ROSA) reference architecture. Why ROSA for Maximo in AWS? There are several advantages of IBM MAS SaaS on AWS.

AWS 84

AWS Clustering Internet of Things Artificial Intelligence 84

AWS Machine Learning Blog

JULY 17, 2023

As described in the AWS Well-Architected Framework , separating workloads across accounts enables your organization to set common guardrails while isolating environments. Organizations with a multi-account architecture typically have Amazon Redshift and SageMaker Studio in two separate AWS accounts. Select VPC Only , then choose Next.

Clustering 96

Clustering AWS ML ML 96

Flipboard

NOVEMBER 27, 2024

Customers want to search through all of the data and applications across their organization, and they want to see the provenance information for all of the documents retrieved. A state machine in AWS Step Functions defines the workflow of the ingestion process by invoking AWS Lambda functions, as illustrated in the following figure.

AWS 150

AWS Database ML ML 150

AWS Machine Learning Blog

DECEMBER 22, 2023

As a result, machine learning practitioners must spend weeks of preparation to scale their LLM workloads to large clusters of GPUs. To learn more about the SageMaker model parallel library, refer to SageMaker model parallelism library v2 documentation. You can also refer to our example notebooks to get started.

Clustering 119

Clustering Deep Learning Deep Learning AWS 119

AWS Machine Learning Blog

APRIL 19, 2024

The architecture deploys a simple service in a Kubernetes pod within an EKS cluster. Karpenter monitors for any pending pods that can’t run due to lack of sufficient resources in the cluster. If such pods are detected, Karpenter adds more nodes to the cluster to provide the necessary resources.

Clustering 123

Clustering AI AI AWS 123

AWS Machine Learning Blog

MAY 24, 2023

Intelligent document processing (IDP) is a technology that automates the processing of high volumes of unstructured data, including text, images, and videos. The system is capable of processing images, large PDF, and documents in other format and answering questions derived from the content via interactive text or voice inputs.

AI 98

AI AI AWS ML 98

AWS Machine Learning Blog

SEPTEMBER 26, 2024

This domain knowledge is traditionally captured in reference manuals, service bulletins, quality ticketing systems, engineering drawings, and more, but the quantity and complexity of documents is growing and takes time to learn. How can I trace the reasoning of my model back to source documents to build user trust?” “How

AWS 116

AWS AI AI Machine Learning 116

AWS Machine Learning Blog

AUGUST 15, 2024

QnABot on AWS (an AWS Solution) now provides access to Amazon Bedrock foundational models (FMs) and Knowledge Bases for Amazon Bedrock , a fully managed end-to-end Retrieval Augmented Generation (RAG) workflow. Deploying the QnABot solution builds the following environment in the AWS Cloud.

AWS 125

AWS AI AI Machine Learning 125

AWS Machine Learning Blog

NOVEMBER 20, 2024

Whether it’s structured data in databases or unstructured content in document repositories, enterprises often struggle to efficiently query and use this wealth of information. Complete the following steps: Choose an AWS Region Amazon Q supports (for this post, we use the us-east-1 Region). Choose Create database.

Database 110

Database AWS SQL ETL 110

AWS Machine Learning Blog

AUGUST 14, 2024

You can use the Amazon Q Business ServiceNow Online data source connector to connect to the ServiceNow Online platform and index ServiceNow entities such as knowledge articles, Service Catalogs, and incident entries, along with the metadata and document access control lists (ACLs).

AWS 118

AWS AI AI Clustering 118

AWS Machine Learning Blog

AUGUST 8, 2023

You can run Spark applications interactively from Amazon SageMaker Studio by connecting SageMaker Studio notebooks and AWS Glue Interactive Sessions to run Spark jobs with a serverless cluster. With interactive sessions, you can choose Apache Spark or Ray to easily process large datasets, without worrying about cluster management.

AWS 97

AWS Clustering Machine Learning Machine Learning 97

AWS Machine Learning Blog

DECEMBER 4, 2024

Orchestrate with Tecton-managed EMR clusters – After features are deployed, Tecton automatically creates the scheduling, provisioning, and orchestration needed for pipelines that can run on Amazon EMR compute engines. You can view and create EMR clusters directly through the SageMaker notebook.

ML 100

ML ML AWS AI 100

AWS Machine Learning Blog

MARCH 10, 2023

This blog post will go through how data professionals may use SageMaker Data Wrangler’s visual interface to locate and connect to existing Amazon EMR clusters with Hive endpoints. Solution overview With SageMaker Studio setups, data professionals can quickly identify and connect to existing EMR clusters. This is TLS enabled.

Clustering 100

Clustering AWS ML ML 100

AWS Machine Learning Blog

MARCH 6, 2023

These factors require training an LLM over large clusters of accelerated machine learning (ML) instances. In the past few years, numerous customers have been using the AWS Cloud for LLM training. We recommend working with your AWS account team or contacting AWS Sales to determine the appropriate Region for your LLM workload.

AWS 105

AWS Clustering ML ML 105

AWS Machine Learning Blog

NOVEMBER 22, 2024

Although QLoRA helps optimize memory during fine-tuning, we will use Amazon SageMaker Training to spin up a resilient training cluster, manage orchestration, and monitor the cluster for failures. To take complete advantage of this multi-GPU cluster, we use the recent support of QLoRA and PyTorch FSDP. 24xlarge compute instance.

Clustering 98

Clustering AWS ML ML 98

AWS Machine Learning Blog

DECEMBER 18, 2023

It is a document based storage that provides a fully managed database, with built-in full-text and vector Search , support for Geospatial queries, Charts and native support for efficient time series storage and querying capabilities. In his role Igor is working with strategic partners helping them build complex, AWS-optimized architectures.

Clustering 120

Clustering AWS Database ML 120

AWS Machine Learning Blog

OCTOBER 9, 2024

The service, which was launched in March 2021, predates several popular AWS offerings that have anomaly detection, such as Amazon OpenSearch , Amazon CloudWatch , AWS Glue Data Quality , Amazon Redshift ML , and Amazon QuickSight. To learn more, see the documentation. To learn more, see the documentation.

AWS 93

AWS ML ML Data Quality 93

Smart Data Collective

AUGUST 17, 2022

You can safely use an Apache Kafka cluster for seamless data movement from the on-premise hardware solution to the data lake using various cloud services like Amazon’s S3 and others. Amazon’s AWS Glue is one such tool that allows you to consume data from Apache Kafka and Amazon-managed streaming for Apache Kafka (MSK).

Apache Kafka 117

Apache Kafka ETL Data Lakes AWS 117