AWS Machine Learning

DECEMBER 9, 2024

With access to a wide range of generative AI foundation models (FM) and the ability to build and train their own machine learning (ML) models in Amazon SageMaker , users want a seamless and secure way to experiment with and select the models that deliver the most value for their business. For details, see Creating an AWS account.

Metrics 99

Metrics APIs Engineering Accountability 99

AWS Machine Learning

APRIL 23, 2025

For more information, see Redacting PII entities with asynchronous jobs (API). The query is then forwarded using a REST API call to an Amazon API Gateway endpoint along with the access tokens in the header. The user query is sent using an API call along with the authentication token through Amazon API Gateway.

APIs 90

APIs Healthcare Enterprise Accountability 90

AWS Machine Learning

APRIL 10, 2025

For instance, as a marketing manager for a video-on-demand company, you might want to send personalized email messages tailored to each individual usertaking into account their demographic information, such as gender and age, and their viewing preferences. Train an Amazon Personalize Top picks for you recommender.

Personalization 98

Personalization APIs Advertising Accountability 98

AWS Machine Learning

JANUARY 24, 2025

Fine-tuning pre-trained language models allows organizations to customize and optimize the models for their specific use cases, providing better performance and more accurate outputs tailored to their unique data and requirements. Model customization in Amazon Bedrock involves the following actions: Create training and validation datasets.

Best practices 113

Best practices Accountability industry standards Metrics 113

AWS Machine Learning

OCTOBER 30, 2024

Enabling Global Resiliency for an Amazon Lex bot is straightforward using the AWS Management Console , AWS Command Line Interface (AWS CLI), or APIs. If this option isn’t visible, the Global Resiliency feature may not be enabled for your account. To better understand the solution, refer to the following architecture diagram.

Chatbots 109

Chatbots Interactive Voice Response APIs Telecommunications 109

AWS Machine Learning

JANUARY 28, 2025

Similarly, maintaining detailed information about the datasets used for training and evaluation helps identify potential biases and limitations in the models knowledge base. It functions as a standalone HTTP server that provides various REST API endpoints for monitoring, recording, and visualizing experiment runs.

Management 108

Management APIs Engineering Metrics 108

AWS Machine Learning

JANUARY 24, 2025

Contrast that with Scope 4/5 applications, where not only do you build and secure the generative AI application yourself, but you are also responsible for fine-tuning and training the underlying large language model (LLM). These steps might involve both the use of an LLM and external data sources and APIs.

APIs 112

APIs Scripts Best practices Management 112

AWS Machine Learning

OCTOBER 19, 2023

In this post, we discuss how to use the Custom Moderation feature in Amazon Rekognition to enhance the accuracy of your pre-trained content moderation API. You can train a custom adapter with as few as 20 annotated images in less than 1 hour. Create a project A project is a container to store your adapters.

APIs 132

APIs Best practices Advertising Accountability 132

AWS Machine Learning

APRIL 10, 2025

Demystifying RAG and model customization RAG is a technique to enhance the capability of pre-trained models by allowing the model access to external domain-specific data sources. Unlike fine-tuning, in RAG, the model doesnt undergo any training and the model weights arent updated to learn the domain knowledge.

APIs 120

APIs Metrics Best practices Construction 120

AWS Machine Learning

NOVEMBER 21, 2024

As large language models (LLMs) increasingly integrate more multimedia capabilities, human feedback becomes even more critical in training them to generate rich, multi-modal content that aligns with human quality standards. The path to creating effective AI models for audio and video generation presents several distinct challenges.

APIs 98

APIs Feedback Telecommunications Management 98

AWS Machine Learning

FEBRUARY 13, 2024

Features are inputs to ML models used during training and inference. Also, when features used to train models offline in batch are made available for real-time inference, it’s hard to keep the two feature stores synchronized. For a deep dive, refer to Cross account feature group discoverability and access.

Accountability 128

Accountability Government Engineering Scripts 128

AWS Machine Learning

FEBRUARY 12, 2025

Many use cases involve using pre-trained large language models (LLMs) through approaches like Retrieval Augmented Generation (RAG). Fine-tuning is a supervised training process where labeled prompt and response pairs are used to further train a pre-trained model to improve its performance for a particular use case.

APIs 75

APIs Management Benchmark Scripts 75

AWS Machine Learning

NOVEMBER 19, 2024

Discover how the fully managed infrastructure of SageMaker enables high-performance, low cost ML throughout the ML lifecycle, from building and training to deploying and managing models at scale. AWS Trainium and AWS Inferentia deliver high-performance AI training and inference while reducing your costs by up to 50%.

APIs 101

APIs Enterprise Best practices Government 101

AWS Machine Learning

APRIL 29, 2024

This often means the method of using a third-party LLM API won’t do for security, control, and scale reasons. First, the AWS Trainium accelerator provides a high-performance, cost-effective, and readily available solution for training and fine-tuning large models. The following figure illustrates this workflow.

APIs 124

APIs Engineering Scripts Management 124

AWS Machine Learning

NOVEMBER 13, 2024

The Amazon Bedrock single API access, regardless of the models you choose, gives you the flexibility to use different FMs and upgrade to the latest model versions with minimal code changes. Amazon Titan FMs provide customers with a breadth of high-performing image, multimodal, and text model choices, through a fully managed API.

Engineering 115

Engineering Management APIs Healthcare 115

AWS Machine Learning

JANUARY 29, 2025

Large organizations often have many business units with multiple lines of business (LOBs), with a central governing entity, and typically use AWS Organizations with an Amazon Web Services (AWS) multi-account strategy. LOBs have autonomy over their AI workflows, models, and data within their respective AWS accounts.

Enterprise 91

Enterprise Government Finance Accountability 91

AWS Machine Learning

MARCH 3, 2025

The vision encoder was specifically trained to natively handle variable image sizes, enabling Pixtral to accurately interpret high-resolution diagrams, charts, and documents while maintaining fast inference speeds for smaller images such as icons, clipart, and equations. To begin using Pixtral 12B, choose Deploy.

Benchmark 101

Benchmark APIs Enterprise Construction 101

AWS Machine Learning

DECEMBER 3, 2024

Agent architecture The following diagram illustrates the serverless agent architecture with standard authorization and real-time interaction, and an LLM agent layer using Amazon Bedrock Agents for multi-knowledge base and backend orchestration using API or Python executors. Domain-scoped agents enable code reuse across multiple agents.

Sales 108

Sales APIs Engineering Analytics 108

AWS Machine Learning

FEBRUARY 24, 2025

It provides a collection of pre-trained models that you can deploy quickly, accelerating the development and deployment of ML applications. One of the key components of SageMaker JumpStart is model hubs, which offer a vast catalog of pre-trained models, such as Mistral, for a variety of tasks.

APIs 87

APIs Enterprise Benchmark Feedback 87

AWS Machine Learning

MARCH 28, 2024

Large language models (LLMs) are generally trained on large publicly available datasets that are domain agnostic. For example, Meta’s Llama models are trained on datasets such as CommonCrawl , C4 , Wikipedia, and ArXiv. The resulting LLM outperforms LLMs trained on non-domain-specific datasets when tested on finance-specific tasks.

Finance 126

Finance Metrics Banking Engineering 126

AWS Machine Learning

FEBRUARY 21, 2025

While these models are trained on vast amounts of generic data, they often lack the organization-specific context and up-to-date information needed for accurate responses in business settings. The function checks the semantic cache (Amazon Bedrock Knowledge Bases) using the Retrieve API. which is received by the Invoke Agent function.

Engineering 121

Engineering APIs Analytics Enterprise 121

AWS Machine Learning

MARCH 6, 2025

Amazon Bedrock is a fully managed service that offers a choice of high-performing Foundation Models (FMs) from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon via a single API, along with a broad set of capabilities you need to build generative AI applications with security, privacy, and responsible AI.

Metrics 114

Metrics Enterprise APIs Engineering 114

CCNG

JUNE 7, 2023

Handling Basic Inquiries : Chat GPT can assist with basic inquiries such as order status, account information, shipping details, or product specifications. Language Support : Chat GPT can be trained in multiple languages, enabling contact centers to provide support to customers globally without the need for multilingual agents.

Contact Center 195

Contact Center CCNG APIs Scripts 195

AWS Machine Learning

NOVEMBER 6, 2023

Within hours, you can annotate your sample documents using the AWS Management Console and train an adapter. Adapters are components that plug in to the Amazon Textract pre-trained deep learning model, customizing its output based on your annotated documents. Adapters can be created via the console or programmatically via the API.

APIs 127

APIs Best practices Banking Accountability 127

AWS Machine Learning

MARCH 10, 2023

Online fraud has a widespread impact on businesses and requires an effective end-to-end strategy to detect and prevent new account fraud and account takeovers, and stop suspicious payment transactions. You can also use Amazon SageMaker to train a proprietary fraud detection model.

APIs 140

APIs Banking Accountability Analytics 140

AWS Machine Learning

FEBRUARY 12, 2025

Amazon Bedrock , a fully managed service offering high-performing foundation models from leading AI companies through a single API, has recently introduced two significant evaluation capabilities: LLM-as-a-judge under Amazon Bedrock Model Evaluation and RAG evaluation for Amazon Bedrock Knowledge Bases.

Metrics 96

Metrics Engineering Benchmark APIs 96

AWS Machine Learning

AUGUST 1, 2024

Amazon 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, Mistral AI, Stability AI, and Amazon through a single API. Amazon Bedrock service starts an import job in an AWS operated deployment account.

APIs 125

APIs Scripts Real estate Accountability 125

AWS Machine Learning

JANUARY 31, 2024

We provide guidance on building, training, and deploying deep learning networks on Amazon SageMaker. With training and practice, ELA can also learn to identify image scaling, quality, cropping, and resave transformations. Prerequisites To follow along with this post, complete the following prerequisites: Have an AWS account.

APIs 118

APIs Banking Construction Accountability 118

AWS Machine Learning

JULY 10, 2024

Frontier large language models (LLMs) like Anthropic Claude on Amazon Bedrock are trained on vast amounts of data, allowing Anthropic Claude to understand and generate human-like text. Solution overview Fine-tuning is a technique in natural language processing (NLP) where a pre-trained language model is customized for a specific task.

APIs 131

APIs Airlines Metrics Engineering 131

AWS Machine Learning

APRIL 8, 2025

Additionally, the integration of SageMaker features in iFoods infrastructure automates critical processes, such as generating training datasets, training models, deploying models to production, and continuously monitoring their performance. In this post, we show how iFood uses SageMaker to revolutionize its ML operations.

Engineering 103

Engineering Virtual Agent Management Technology 103

TeleDirect

APRIL 16, 2025

Your medical call center must be fully compliant with the Health Insurance Portability and Accountability Act (HIPAA). Look for a service that has: Encrypted data storage Secure call recording Staff trained in handling PHI (Protected Health Information) Internal audits and compliance reporting 3.

Call Center 62

Call Center Healthcare Call flow Scripts 62

AWS Machine Learning

FEBRUARY 29, 2024

Its collaborative capabilities such as real-time coediting and sharing notebooks within the team ensures smooth teamwork, while the scalability and high-performance training caters to large datasets. For high availability, multiple identical private isolated subnets are provisioned.

APIs 128

APIs Transportation Construction Analytics 128

AWS Machine Learning

NOVEMBER 13, 2023

Amazon Personalize provisions the necessary infrastructure and manages the entire machine learning (ML) pipeline, including processing the data, identifying features, using the most appropriate algorithms, and training, optimizing, and hosting the models. An interaction is an event that you record and then import as training data.

Personalization 115

Personalization APIs Accountability Engineering 115

AWS Machine Learning

JUNE 5, 2024

In this post, we show how to use Amazon Comprehend Custom to train and host an ML model to classify if the input email is an phishing attempt or not. Comprehend Custom builds customized NLP models on your behalf, using training data that you provide. For minimum training requirements, see General quotas for document classification.

APIs 117

APIs Metrics Accountability Enterprise 117

AWS Machine Learning

FEBRUARY 7, 2024

Select your options and train the model. Deploy the API to make predictions. Prerequisites The following are prerequisite steps for this solution: Sign up for an AWS account. Set up permissions that allows your AWS account to access Amazon Fraud Detector. Create the model. Review model performance. Deploy the model.

APIs 134

APIs Accountability Metrics Engineering 134

AWS Machine Learning

JULY 11, 2024

This allows customers to further pre-train selected models using their own proprietary data to tailor model responses to their business context. This allows customers to further pre-train selected models using their own proprietary data to tailor model responses to their business context. This data must be in the JSON Line format.

APIs 128

APIs Accountability Enterprise Best practices 128

AWS Machine Learning

OCTOBER 8, 2024

Challenges with traditional onboarding The traditional onboarding process for banks faces challenges in the current digital landscape because many institutions don’t have fully automated account-opening systems. This constraint impacts the flexibility for customers to initiate account opening at their preferred time.

Banking 116

Banking APIs Accountability Engineering 116