AWS Machine Learning

APRIL 3, 2024

The following is a high-level overview of how it works conceptually: Separate encoders – These models have separate encoders for each modality—a text encoder for text (for example, BERT or RoBERTa), image encoder for images (for example, CNN for images), and audio encoders for audio (for example, models like Wav2Vec).

Policies 102

Policies Examples Ecommerce User Experience 102

AWS Machine Learning

OCTOBER 19, 2023

Solution overview Training a custom moderation adapter involves five steps that you can complete using the AWS Management Console or the API interface: Create a project Upload the training data Assign ground truth labels to images Train the adapter Use the adapter Let’s walk through these steps in more detail using the console.

Training 109

Training Data Social Media Ecommerce 109

AWS Machine Learning

SEPTEMBER 13, 2023

Amazon Comprehend develops insights by recognizing the entities, key phrases, sentiment, themes, and custom elements in a document. Overview of solution The following diagram illustrates the solution architecture. You can download an object from the data folder or S3 bucket using the Amazon S3 console. Enter a name for your job.

Analysis 101

Analysis Groups Data Examples 101

AWS Machine Learning

DECEMBER 12, 2023

Solution overview This post walks through a low-code workflow for deploying pre-trained and custom LLMs through SageMaker, and creating a web UI to interface with the models deployed. Refer to the following diagram for an overview of the solution architecture. We cover the following steps: Deploy SageMaker foundation models.

Interaction 101

Interaction Chatbots Training How To 101

AWS Machine Learning

JANUARY 22, 2024

Solution overview The following diagram illustrates the solution architecture. Use the Queries feature on the Amazon Textract console Before you build the vaccination verification solution, let’s explore how you can use Amazon Textract Queries to extract vaccination status via the Amazon Textract console.

Travel 100

Travel Resources Sports Hotels 100

AWS Machine Learning

OCTOBER 30, 2023

Amazon Bedrock is a fully managed service provided by AWS that offers developers access to foundation models (FMs) and the tools to customize them for specific applications. It allows developers to build and scale generative AI applications using FMs through an API, without managing infrastructure. You’re redirected to the IAM console.

Policies 125

Policies Groups Resources Connections 125

AWS Machine Learning

SEPTEMBER 12, 2023

This includes valuable information such as events, errors, and user interactions that would aid an application developer or an operations support engineer to debug and provide support. Clean up To clean up the resources created in this post, delete the CloudFormation stack via the CloudFormation console.

Groups 96

Groups Financial Examples Data 96

AWS Machine Learning

OCTOBER 11, 2023

Create a Web Crawler data source V2 via the Amazon Kendra console. For more information, see Overview of access management: Permissions and policies. Create an Amazon Kendra index To create an Amazon Kendra index, complete the following steps: On the Amazon Kendra console, choose Create an Index. Enter an optional description.

Policies 95

Policies Exercises Examples Data 95

AWS Machine Learning

APRIL 8, 2024

If you are experimenting and building with LLMs, you are likely familiar with LangChain, which offers a robust framework, simplifying the development and deployment of LLM-powered applications. Solution overview In this post, we demonstrate how to create a RAG-based application using LlamaIndex and an LLM.

Knowledge Base 100

Knowledge Base Tools Data Training 100

AWS Machine Learning

APRIL 18, 2024

Solution overview The LMA sample solution captures speaker audio and metadata from your browser-based meeting app (as of this writing, Zoom and Chime are supported), or audio only from any other browser-based meeting app, softphone, or audio source. You can copy it from the Amazon Bedrock console. Enable Developer mode.

Knowledge Base 110

Knowledge Base Meeting Resources Analytics 110

AWS Machine Learning

MAY 23, 2023

With over 600 pre-trained models available and growing every day, JumpStart enables developers to quickly and easily incorporate cutting-edge ML techniques into their production workflows. In this post, we show how to deploy image and text generative AI models from JumpStart using the AWS Cloud Development Kit (AWS CDK).

Training 92

Training Resources How To Examples 92

AWS Machine Learning

FEBRUARY 7, 2024

In the second post , we discussed an approach to develop a deep learning-based computer vision model to detect and highlight forged images in mortgage underwriting. Solution overview We use Amazon Fraud Detector, a fully managed fraud detection service, to automate the detection of fraudulent activities. Choose Create.

Training 109

Training Examples Data Financial 109

AWS Machine Learning

OCTOBER 26, 2023

For more information, see Overview of access management: Permissions and policies and IAM roles for Drupal data sources. For more information on this topic, refer to the Amazon Kendra Developer Guide. On the Amazon Kendra console, open your index and choose Data sources in the navigation pane. Then complete the following steps.

Policies 97

Policies Data Groups Software 97

AWS Machine Learning

MARCH 12, 2024

Solution overview AWS Clean Rooms can help you and your partners effortlessly and securely collaborate on and analyze your collective datasets—without copying each other’s underlying data. Collaborators can use the AWS Clean Rooms console, APIs, or AWS SDKs to set up a collaboration. Choose Create collaboration. Choose Associate table.

Analysis 100

Analysis Advertising Data Consumers 100

AWS Machine Learning

OCTOBER 5, 2023

Solution overview This solution presents an approach to building an optimized custom classification model using Amazon Comprehend. We use an Amazon SageMaker notebook and the AWS Management Console to complete some of these steps. On the SageMaker console, choose Notebook instances in the navigation pane. Choose Create job.

Effort Score 97

Effort Score Analysis Guidelines Training 97

AWS Machine Learning

SEPTEMBER 19, 2023

VirtuSwap is a startup company developing innovative technology for decentralized exchange of assets on blockchains. Solution overview VirtuSwap chose SageMaker Studio for end-to-end development, starting with iterative, interactive development in notebooks. In the navigation pane on the left, choose Policies.

Policies 118

Policies Comparison Resources Groups 118

AWS Machine Learning

APRIL 22, 2024

Create AWS Managed Microsoft AD on Directory Service Complete the following steps to set up your directory: On the Directory Service console , choose Directories in the navigation pane. On the Load Balancers console , choose Create load balancer. Choose Set up directory. For Directory type , select AWS Managed Microsoft AD.

Groups 87

Groups Software System Policies 87

AWS Machine Learning

NOVEMBER 17, 2023

Agents for Amazon Bedrock In July, AWS announced the preview of agents for Amazon Bedrock , a new capability for developers to create fully managed agents in a few clicks. Solution overview We use a shoe retailer use case to build the customer service bot. The Amazon Bedrock console provides a UI to test your agent.

Customer Service 87

Customer Service e-support Groups How To 87

AWS Machine Learning

MARCH 22, 2023

Developing a Rekognition Custom Labels model to analyze images is a significant undertaking that requires time, expertise, and resources, often taking months to complete. Solution overview The Step Functions workflow is as follows: We first create an Amazon Rekognition project.

Training 80

Training Metrics Social Media Customers 80

AWS Machine Learning

DECEMBER 1, 2023

As we continue to innovate to increase data science productivity, we’re excited to announce the improved SageMaker Studio experience, which allows users to select the managed Integrated Development Environment (IDE) of their choice, while having access to the SageMaker Studio resources and tooling across the IDEs.

Travel 97

Travel Training Resources Tools 97

AWS Machine Learning

APRIL 5, 2023

Overview of solution Featured results enables you to create direct mappings from exact queries to documents in your index, allowing you to bypass the usual Amazon Kendra ranking process. Search without Featured Results On the Amazon Kendra console, choose Search indexed content. Choose Add data source. Choose Next. Choose Add query.

Travel 74

Travel Policies Software Data 74

AWS Machine Learning

MARCH 12, 2024

In this post, we discuss how Leidos worked with AWS to develop an approach to privacy-preserving large language model (LLM) inference using AWS Nitro Enclaves. Overview of LLMs and Nitro Enclaves A potential use case is an LLM-based sensitive query chatbot designed to carry out a question and answering service containing PII and PHI.

Chatbots 91

Chatbots Data Policies Healthcare 91

AWS Machine Learning

NOVEMBER 6, 2023

Solution overview When starting with a new use case, you can evaluate how Textract Queries performs on your documents by navigating to the Textract console and using the Analyze Document Demo or Bulk Document Uploader. Within hours, you can annotate your sample documents using the AWS Management Console and train an adapter.

Self Service 102

Self Service Banking Training Customers 102

AWS Machine Learning

APRIL 18, 2023

Solution overview For our solution, we demonstrate how to index a OneDrive repository or folder using the Amazon Kendra connector for OneDrive. Create a OneDrive data source via the Amazon Kendra console. For more information, see Overview of access management: Permissions and policies. Index the data in the OneDrive repository.

Policies 70

Policies Groups Examples Data 70

AWS Machine Learning

FEBRUARY 13, 2024

This new capability promotes collaboration and minimizes duplicate work for teams involved in ML model and application development, particularly in enterprise environments with multiple accounts spanning different business units or functions. For a deep dive, refer to Cross account feature group discoverability and access.

Groups 106

Groups Government Resources Consumers 106

AWS Machine Learning

OCTOBER 1, 2022

AWS Panorama is a collection of machine learning (ML) devices and a software development kit (SDK) that brings computer vision to on-premises internet protocol (IP) cameras. Overview of update. On the AWS Panorama console, choose Devices in the navigation pane. The NVIDIA Jetpack SDK version 4.6.2 cuDNN 8.2.1, Choose Settings.

Software 71

Software System Management 71

AWS Machine Learning

DECEMBER 14, 2022

Solution overview. Access the Amazon Transcribe console and call Amazon Transcribe APIs. To create your S3 bucket, complete the following steps: On the Amazon S3 console, choose Create bucket. On the Amazon S3 console, choose Buckets in the navigation pane. Create an S3 bucket to store your audio input files. Conclusion.

Exercises 94

Exercises Contact Center Data How To 94

AWS Machine Learning

SEPTEMBER 28, 2022

Solution overview. Create a Dropbox data source via the Amazon Kendra console. For more information, see Overview of access management: Permissions and policies. Go to www.dropbox.com/developers. Choose App console. For Provisioning editions , select Developer edition. Prerequisites. Basic knowledge of AWS.

Groups 80

Groups Policies Examples Data 80

AWS Machine Learning

DECEMBER 21, 2022

Solution overview. Create a ServiceNow data source via the Amazon Kendra console. For more information, see Overview of access management: Permissions and policies. To store your ServiceNow credentials in Secrets Manager, compete the following steps: On the Secrets Manager console, choose Store a new secret. Choose Next.

Groups 72

Groups Policies Data Examples 72

AWS Machine Learning

NOVEMBER 9, 2023

The MLOps workflow includes the following steps: Access the SageMaker Studio domain in the development account, clone the GitHub repository, go through the process of model development using the sample model provided, and generate the train and inference pipelines. The full instructions with code are available in the GitHub repository.

Policies 100

Policies Training Resources Groups 100

AWS Machine Learning

SEPTEMBER 6, 2023

Solution overview This solution uses SageMaker JumpStart models to deploy text-to-text, text-to-image, and text embeddings models as SageMaker endpoints. Dataset overview The dataset used for this solution is pile-of-law within the Hugging Face repository. For this post, you use the AWS Cloud Development Kit (AWS CDK) using Python.

Policies 96

Policies Insurance Advertising Resources 96

AWS Machine Learning

MARCH 1, 2024

Hybrid search overview Hybrid search takes advantage of the strengths of multiple search algorithms, integrating their unique capabilities to enhance the relevance of returned search results. Question Semantic Search: RAG API Hybrid Search: RAG API How does Amazon serve the developers and enterprises? Choose Test knowledge base.

Knowledge Base 109

Knowledge Base Chatbots Policies Government 109

AWS Machine Learning

FEBRUARY 16, 2023

Solution overview In the following sections, we walk through the steps for adding documents from a data source and performing a search on those documents. On the Amazon Kendra console, go to your index and choose Data sources. Now that you have ingested some documents, you can navigate to the built-in search console to test queries.

Data 70

Data Sports Metrics Groups 70

AWS Machine Learning

MARCH 2, 2023

Overview of solution There are three main improvements to the Amazon Kendra S3 connector : VPC support – The connector now supports using your Amazon Virtual Private Cloud (Amazon VPC) networks. On the AWS Management Console , in the Region list, choose US East (N. On the Amazon S3 console, choose Create bucket. Choose Services.

Travel 86

Travel Data Connections Groups 86

AWS Machine Learning

FEBRUARY 29, 2024

You can also add data incrementally by importing records using the Amazon Personalize console or API. Solution overview The following diagram illustrates the solution architecture. After the stack is created, open the SageMaker notebook instance from the console. This search request is sent to OpenSearch Service.

e-support 91

e-support Resources Comparison Data 91

AWS Machine Learning

FEBRUARY 9, 2023

We also walk through how to use the feature through the Amazon Textract console and provide code examples to use the API and process the response with the Amazon Textract response parser library. The following screenshot shows an example of a paystub on the Signatures tab for the Analyze Document API on the Amazon Textract console.

Insurance 80

Insurance Examples Travel Banking 80

AWS Machine Learning

DECEMBER 29, 2022

The steps in this post emphasize the AWS Management Console UI, showing how technical people without a developer background or strong coding skills can build a prototype. Solution overview. On the Lookout for Equipment console, choose Create project. After the template has launched, navigate to the CloudFormation console.

Training 72

Training Analysis Resources Data 72