News
Cost effective deployment of vision-language models for pet behavior detection on AWS Inferentia2
2+ hour, 29+ min ago (204+ words) Before diving into the architecture, the following diagram provides a high-level view of how the system processes pet behavior detection at scale across AWS services. Before diving into the model details, the following diagram provides a high-level overview of the…...
From data lake to AI-ready analytics: Introducing new data source with S3 Tables in Amazon Quick
2+ day, 1+ hour ago (345+ words) In this post, we explore how Amazon Quick and S3 Tables work together to enable near real-time analytics and streamline modern data architectures. With this new launch, Amazon Quick now supports querying data lakes using either SPICE or Direct Query mode....
Capacity-aware inference: Automatic instance fallback for Sage Maker AI endpoints
2+ day, 2+ hour ago (1262+ words) As organizations scale generative AI workloads in production, securing reliable GPU compute has become one of the most persistent operational challenges. Large language models (LLMs) and multimodal architectures demand specific instance types and when that capacity isn't available, endpoints fail…...
Features and workflows with Amazon Timestream for Influx DB 3
1+ week, 2+ hour ago (900+ words) The managed service combines Influx Data's latest database offering with AWS infrastructure and tooling to support your time series data workflows. Visit our documentation to get started using the Amazon Timestream for Influx DB 3 today. AWS offers Influx DB 3 in…...
The transformative impact of generative AI on business workflows in a highly regulated industry
1+ week, 5+ day ago (269+ words) Figure 1: Aerospace software development lifecycle (V-Model) showing the relationship between requirements definition phases on the left and corresponding verification phases on the right, from mission requirements through system validation Current aerospace SDLC workflows might not adequately meet the industry's growing…...
Cost-effective multilingual audio transcription at scale with Parakeet-TDT and AWS Batch
1+ week, 6+ day ago (880+ words) Many organizations are archiving large media libraries, analyzing contact center recordings, preparing training data for AI, or processing on-demand video for subtitles. When data volumes grow significantly, managed automatic speech recognition (ASR) service costs can quickly become the primary constraint…...
Articul8 AI bridges the industrial expertise gap with specialized Llama 4 models and security-first AWS architecture
2+ week, 2+ hour ago (24+ words) Amazon Web Services Comment a "t" ce contenu?...
Analyzing your data catalog: Query Sage Maker Catalog metadata with SQL
2+ week, 2+ hour ago (690+ words) After you enable the metadata export feature, it runs automatically on a daily schedule: The export evaluates catalog assets and their metadata properties in the domain, converting them into Apache Iceberg table format. The data flows into downstream analytics operations…...
End-to-end lineage with DVC and Amazon Sage Maker AI MLflow apps
2+ week, 1+ day ago (1121+ words) We walk through two deployable patterns, dataset-level lineage and record-level lineage, that you can run end-to-end in your own AWS account using the companion notebooks. The architecture integrates DVC, Sage Maker AI, and Sage Maker AI MLflow App into a…...
Accelerate Apache Hadoop and Apache Iceberg on Amazon S3 with the Analytics Accelerator Library
2+ week, 2+ day ago (830+ words) Note: In our Transaction Processing Performance Council Decision Support (TPC-DS) derived benchmark testing, Analytics Accelerator Library for S3 improved query execution time by up to 1. 2 X for IO-intensive data lake workloads on Apache Spark. This approach means you don't need to…...