AWS Machine Learning Blog

See how AWS is democratizing generative AI with innovations like Amazon Q Apps to make AI apps from prompts, Amazon Bedrock upgrades to leverage more data sources, new techniques to curtail hallucinations, and AI skills training.

You can now register machine learning (ML) models in Amazon SageMaker Model Registry with Amazon SageMaker Model Cards, making it straightforward to manage governance information for specific model versions directly in SageMaker Model Registry in just a few clicks. In this post, we discuss a new feature that supports the integration of model cards with the model registry. We discuss the solution architecture and best practices for managing model cards with a registered model version, and walk through how to set up, operationalize, and govern your models using the integration in the model registry.

In this post, we explore the approach behind building an AWS AI-powered Chrome extension that aims to revolutionize the live streaming experience by providing real-time transcription, translation, and summarization capabilities directly within your browser.

In this post, we demonstrate how to deploy a generative AI application that can accelerate your financial statement analysis on AWS.

This post outlines a custom multilingual document extraction and content assessment framework using a combination of Anthropic’s Claude 3 on Amazon Bedrock and Amazon A2I to incorporate human-in-the-loop capabilities.

In this post, you will learn how to extract key objects from image queries using Amazon Rekognition and build a reverse image search engine using Amazon Titan Multimodal Embeddings from Amazon Bedrock in combination with Amazon OpenSearch Serverless Service.

This post describes how Agmatix, a pioneering Agtech company powering R&D for input companies and digital agronomic solutions, 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.

In this blog post, we demonstrate prompt engineering techniques to generate accurate and relevant analysis of tabular data using industry-specific language. This is done by providing large language models (LLMs) in-context sample data with features and labels in the prompt. The results are similar to fine-tuning LLMs without the complexities of fine-tuning models.

In this post, we demonstrate a solution using Amazon Bedrock Agents, Amazon Bedrock Knowledge Bases, Amazon Bedrock Developer Experience, and Amazon Personalize that allow marketers to save time and deliver efficient personalized advertising using a generative AI enhanced solution. Our solution is a marketing agent that shows how Amazon Personalize can effectively segment target customers based on relevant characteristics and behaviors. Additionally, by using Amazon Bedrock Agents and foundation models (FMs), our tool generates personalized creative content specifically tailored to each purpose. It customizes the tone, creative style, and individual preferences according to each customer’s specific prompt, providing highly customized and effective marketing communications.

In this post, we demonstrate how to fine-tune Meta’s latest Llama 3.2 text generation models, Llama 3.2 1B and 3B, using Amazon SageMaker JumpStart for domain-specific applications. By using the pre-built solutions available in SageMaker JumpStart and the customizable Meta Llama 3.2 models, you can unlock the models’ enhanced reasoning, code generation, and instruction-following capabilities to tailor them for your unique use cases.

Microsoft Teams is an enterprise collaboration tool that allows you to build a unified workspace for real-time collaboration and communication, meetings, and file and application sharing. You can exchange and store valuable organizational knowledge within Microsoft Teams. Microsoft Teams data is often siloed across different teams, channels, and chats, making it difficult to get a […]