News
Entertainment
Science & Technology
Life
Culture & Art
Hobbies
News
Entertainment
Science & Technology
Culture & Art
Hobbies
Harnessing Amazon Bedrock generative AI for resilient supply chain | AWS Machine Learning Blog
By leveraging the generative AI capabilities and tooling of Amazon Bedrock, you can create an intelligent nerve center that connects diverse data sources, converts data into actionable insights, and creates a comprehensive plan to mitigate supply chain risks. This post walks through how Amazon Bedrock Flows connects your business systems, monitors medical device shortages, and provides mitigation strategies based on knowledge from Amazon Bedrock Knowledge Bases or data stored in Amazon S3 directly. You’ll learn how to create a system that stays ahead of supply chain risks.
Accelerate digital pathology slide annotation workflows on AWS using H-optimus-0 | AWS Machine Learning Blog
In this post, we demonstrate how to use H-optimus-0 for two common digital pathology tasks: patch-level analysis for detailed tissue examination, and slide-level analysis for broader diagnostic assessment. Through practical examples, we show you how to adapt this FM to these specific use cases while optimizing computational resources.
How Travelers Insurance classified emails with Amazon Bedrock and prompt engineering | AWS Machine Learning Blog
In this post, we discuss how FMs can reliably automate the classification of insurance service emails through prompt engineering. When formulating the problem as a classification task, an FM can perform well enough for production environments, while maintaining extensibility into other tasks and getting up and running quickly. All experiments were conducted using Anthropic’s Claude models on Amazon Bedrock.
Streamline grant proposal reviews using Amazon Bedrock | AWS Machine Learning Blog
The AWS Social Responsibility & Impact (SRI) team recognized an opportunity to augment this function using generative AI. The team developed an innovative solution to streamline grant proposal review and evaluation by using the natural language processing (NLP) capabilities of Amazon Bedrock. In this post, we explore the technical implementation details and key learnings from the team’s Amazon Bedrock powered grant proposal review solution, providing a blueprint for organizations seeking to optimize their grants management processes.
DeepSeek-R1 model now available in Amazon Bedrock Marketplace and Amazon SageMaker JumpStart | AWS Machine Learning Blog
Today, we are announcing that DeepSeek AI’s first-generation frontier model, DeepSeek-R1, is available through Amazon SageMaker JumpStart and Amazon Bedrock Marketplace to deploy for inference. You can now use DeepSeek-R1 to build, experiment, and responsibly scale your generative AI ideas on AWS. In this post, we demonstrate how to get started with DeepSeek-R1 on Amazon […]
How Open Universities Australia modernized their data platform and significantly reduced their ETL costs with AWS Cloud Development Kit and AWS Step Functions | AWS Big Data Blog
At Open Universities Australia (OUA), we empower students to explore a vast array of degrees from renowned Australian universities, all delivered through online learning. In this post, we show you how we used AWS services to replace our existing third-party ETL tool, improving the team’s productivity and producing a significant reduction in our ETL operational costs.
How Aetion is using generative AI and Amazon Bedrock to unlock hidden insights about patient populations | AWS Machine Learning Blog
In this post, we review how Aetion’s Smart Subgroups Interpreter enables users to interact with Smart Subgroups using natural language queries. Powered by Amazon Bedrock and Anthropic’s Claude 3 large language models (LLMs), the interpreter responds to user questions expressed in conversational language about patient subgroups and provides insights to generate further hypotheses and evidence.
Deploy DeepSeek-R1 distilled Llama models with Amazon Bedrock Custom Model Import | AWS Machine Learning Blog
In this post, we demonstrate how to deploy distilled versions of DeepSeek-R1 models using Amazon Bedrock Custom Model Import. We focus on importing the variants currently supported DeepSeek-R1-Distill-Llama-8B and DeepSeek-R1-Distill-Llama-70B, which offer an optimal balance between performance and resource efficiency.
Hybrid big data analytics with Amazon EMR on AWS Outposts | AWS Big Data Blog
In this post, we dive into the transformative features of EMR on Outposts, showcasing its flexibility as a native hybrid data analytics service that allows seamless data access and processing both on premises and in the cloud.
Generative AI operating models in enterprise organizations with Amazon Bedrock | AWS Machine Learning Blog
As generative AI adoption grows, organizations should establish a generative AI operating model. An operating model defines the organizational design, core processes, technologies, roles and responsibilities, governance structures, and financial models that drive a business’s operations. In this post, we evaluate different generative AI operating model architectures that could be adopted.
How Aqua Security exports query data from Amazon Aurora to deliver value to their customers at scale | AWS Database Blog
Aqua Security is the pioneer in securing containerized cloud native applications from development to production. Like many organizations, Aqua faced the challenge of efficiently exporting and analyzing large volumes of data to meet their business requirements. Specifically, Aqua needed to export and query data at scale to share with their customers for continuous monitoring and security analysis. In this post, we explore how Aqua addressed this challenge by using aws_s3.query_export_to_s3 function with their Amazon Aurora PostgreSQL-Compatible Edition and AWS Step Functions to streamline their query output export process, enabling scalable and cost-effective data analysis.
Deploy DeepSeek-R1 Distilled Llama models in Amazon Bedrock | AWS Machine Learning Blog
In this post, we demonstrate how to deploy distilled versions of DeepSeek-R1 models using Amazon Bedrock Custom Model Import. We focus on importing the variants currently supported DeepSeek-R1-Distill-Llama-8B and DeepSeek-R1-Distill-Llama-70B, which offer an optimal balance between performance and resource efficiency.
How MuleSoft achieved cloud excellence through an event-driven Amazon Redshift lakehouse architecture | AWS Big Data Blog
In our previous thought leadership blog post Why a Cloud Operating Model we defined a COE Framework and showed why MuleSoft implemented it and the benefits they received from it. In this post, we'll dive into the technical implementation describing how MuleSoft used Amazon EventBridge, Amazon Redshift, Amazon Redshift Spectrum, Amazon S3, & AWS Glue to implement it.
Optimizing AI responsiveness: A practical guide to Amazon Bedrock latency-optimized inference | AWS Machine Learning Blog
In this post, we explore how Amazon Bedrock latency-optimized inference can help address the challenges of maintaining responsiveness in LLM applications. We'll dive deep into strategies for optimizing application performance and improving user experience. Whether you're building a new AI application or optimizing an existing one, you'll find practical guidance on both the technical aspects of latency optimization and real-world implementation approaches. We begin by explaining latency in LLM applications.
Monitor the health of Amazon Aurora PostgreSQL instances in large-scale deployments | AWS Database Blog
In this post, we show you how to achieve better visibility into the health of your Amazon Aurora PostgreSQL instances, proactively address potential issues, and maintain the smooth operation of your database infrastructure. The solution is designed to scale with your deployment, providing robust and reliable monitoring for even the largest fleets of instances.
Develop a RAG-based application using Amazon Aurora with Amazon Kendra | AWS Machine Learning Blog
RAG retrieves data from a preexisting knowledge base (your data), combines it with the LLM’s knowledge, and generates responses with more human-like language. However, in order for generative AI to understand your data, some amount of data preparation is required, which involves a big learning curve. In this post, we walk you through how to convert your existing Aurora data into an index without needing data preparation for Amazon Kendra to perform data search and implement RAG that combines your data along with LLM knowledge to produce accurate responses.
Track LLM model evaluation using Amazon SageMaker managed MLflow and FMEval | AWS Machine Learning Blog
In this post, we show how to use FMEval and Amazon SageMaker to programmatically evaluate LLMs. FMEval is an open source LLM evaluation library, designed to provide data scientists and machine learning (ML) engineers with a code-first experience to evaluate LLMs for various aspects, including accuracy, toxicity, fairness, robustness, and efficiency.
Introducing the GraphRAG Toolkit | AWS Database Blog
Amazon Neptune recently released the GraphRAG Toolkit, an open source Python library that makes it straightforward to build graph-enhanced Retrieval Augmented Generation (RAG) workflows. In this post, we describe how you can get started with the toolkit. We begin by looking at the benefits of adding a graph to your RAG application. Then we show you how to set up a quick start environment and install the toolkit. Lastly, we discuss some of the design considerations that led to the toolkit’s graph model and its approach to content retrieval.
Image and video prompt engineering for Amazon Nova Canvas and Amazon Nova Reel | AWS Machine Learning Blog
Amazon has introduced two new creative content generation models on Amazon Bedrock: Amazon Nova Canvas for image generation and Amazon Nova Reel for video creation. These models transform text and image inputs into custom visuals, opening up creative opportunities for both professional and personal projects. Nova Canvas, a state-of-the-art image generation model, creates professional-grade images […]
Oracle Application Express for Amazon RDS for Oracle demystified | AWS Database Blog
Oracle Application Express (APEX) allows you to quickly develop and deploy compelling applications that solve real problems and provide immediate value. In this post, we cover the steps for installing, configuring, and upgrading an APEX repository in Amazon RDS for Oracle and ORDS. We also show how to handle APEX when performing snapshot restore or point-in-time recovery (PITR).
Create a SageMaker inference endpoint with custom model & extended container | AWS Machine Learning Blog
This post walks you through the end-to-end process of deploying a single custom model on SageMaker using NASA’s Prithvi model. The Prithvi model is a first-of-its-kind temporal Vision transformer pre-trained by the IBM and NASA team on contiguous US Harmonised Landsat Sentinel 2 (HLS) data. It can be finetuned for image segmentation using the mmsegmentation library for use cases like burn scars detection, flood mapping, and multi-temporal crop classification.
How Iterate.ai uses Amazon MemoryDB to accelerate and cost-optimize their workforce management conversational AI agent | AWS Database Blog
Iterate.ai is an enterprise AI platform company delivering innovative AI solutions to industries such as retail, finance, healthcare, and quick-service restaurants. Among its standout offerings is Frontline, a workforce management platform powered by AI, designed to support and empower Frontline workers. Available on both the Apple App Store and Google Play, Frontline uses advanced AI tools to streamline operational efficiency and enhance communication among dispersed workforces. In this post, we give an overview of durable semantic caching in Amazon MemoryDB, and share how Iterate used this functionality to accelerate and cost-optimize Frontline.
Security best practices to consider while fine-tuning models in Amazon Bedrock | AWS Machine Learning Blog
In this post, we implemented secure fine-tuning jobs in Amazon Bedrock, which is crucial for protecting sensitive data and maintaining the integrity of your AI models. By following the best practices outlined in this post, including proper IAM role configuration, encryption at rest and in transit, and network isolation, you can significantly enhance the security posture of your fine-tuning processes.
OpenSearch Vector Engine is now disk-optimized for low cost, accurate vector search | AWS Big Data Blog
OpenSearch Vector Engine can now run vector search at a third of the cost on OpenSearch 2.17+ domains. You can now configure k-NN (vector) indexes to run on disk mode, optimizing it for memory-constrained environments, and enable low-cost, accurate vector search that responds in low hundreds of milliseconds. Disk mode provides an economical alternative to memory mode when you don’t need near single-digit latency. In this post, you’ll learn about the benefits of this new feature, the underlying mechanics, customer success stories, and getting started.
Secure a generative AI assistant with OWASP Top 10 mitigation | AWS Machine Learning Blog
In this post, we show you an example of a generative AI assistant application and demonstrate how to assess its security posture using the OWASP Top 10 for Large Language Model Applications, as well as how to apply mitigations for common threats.
Enhance your customer’s omnichannel experience with Amazon Bedrock and Amazon Lex | AWS Machine Learning Blog
In this post, we show you how to set up Amazon Lex for an omnichannel chatbot experience and Amazon Bedrock to be your secondary validation layer. This allows your customers to potentially provide out-of-band responses both at the intent and slot collection levels without having to be re-prompted, allowing for a seamless customer experience.
Access Amazon S3 Iceberg tables from Databricks using AWS Glue Iceberg REST Catalog in Amazon SageMaker Lakehouse | AWS Big Data Blog
In this post, we will show you how Databricks on AWS general purpose compute can integrate with the AWS Glue Iceberg REST Catalog for metadata access and use Lake Formation for data access. To keep the setup in this post straightforward, the Glue Iceberg REST Catalog and Databricks cluster share the same AWS account.
Streamline custom environment provisioning for Amazon SageMaker Studio: An automated CI/CD pipeline approach | AWS Machine Learning Blog
In this post, we show how to create an automated continuous integration and delivery (CI/CD) pipeline solution to build, scan, and deploy custom Docker images to SageMaker Studio domains. You can use this solution to promote consistency of the analytical environments for data science teams across your enterprise.
Video security analysis for privileged access management using generative AI and Amazon Bedrock | AWS Machine Learning Blog
In this post, we show you an innovative solution to a challenge faced by security teams in highly regulated industries: the efficient security analysis of vast amounts of video recordings from Privileged Access Management (PAM) systems. We demonstrate how you can use Anthropic’s Claude 3 family of models and Amazon Bedrock to perform the complex task of analyzing video recordings of server console sessions and perform queries to highlight any potential security anomalies.
Introducing multi-turn conversation with an agent node for Amazon Bedrock Flows (preview) | AWS Machine Learning Blog
Today, we’re excited to announce multi-turn conversation with an agent node (preview), a powerful new capability in Flows. This new capability enhances the agent node functionality, enabling dynamic, back-and-forth conversations between users and flows, similar to a natural dialogue in a flow execution.
Diving deep into the new Amazon Aurora Global Database writer endpoint | AWS Database Blog
On October 22, 2024, we announced the availability of the Aurora Global Database writer endpoint, a highly available and fully managed endpoint for your global database that Aurora automatically updates to point to the current writer instance in your global cluster after a cross-Region switchover or failover, alleviating the need for application changes and simplifying routing requests to the writer instance. In this post, we dive deep into the new Global Database writer endpoint, covering its benefits and key considerations for using it with your applications.
How Cato Networks uses Amazon Bedrock to transform free text search into structured GraphQL queries | AWS Machine Learning Blog
Accurately converting free text inputs into structured data is crucial for applications that involve data management and user interaction. In this post, we introduce a real business use case from Cato Networks that significantly improved user experience. By using Amazon Bedrock, we gained access to state-of-the-art generative language models with built-in support for JSON schemas and structured data.
How Skello uses AWS DMS to synchronize data from a monolithic application to microservices | AWS Database Blog
Skello is a human resources (HR) software-as-a-service (SaaS) platform that focuses on employee scheduling and workforce management. It caters to various sectors, including hospitality, retail, healthcare, construction, and industry. In this post, we show how Skello uses AWS Database Migration Service (AWS DMS) to synchronize data from an monolithic architecture to microservices and perform data ingestion from the monolithic architecture and microservices to our data lake.
Use Amazon Neptune Analytics to analyze relationships in your data faster, Part 1: Introducing Parquet and CSV import and export | AWS Database Blog
In this two-part series, we show how you can import and export using Parquet and CSV to quickly gather insights from your existing graph data. Part 1 introduces the import and export functionalities, and walks you through how to quickly get started with them. In Part 2, we show how you can use the new data mobility improvements in Neptune Analytics to enhance fraud detection.
Generate vector embeddings for your data using AWS Lambda as a processor for Amazon OpenSearch Ingestion | AWS Big Data Blog
In this post, we demonstrate how to use the OpenSearch Ingestion’s Lambda processor to generate embeddings for your source data and ingest them to an OpenSearch Serverless vector collection. This solution uses the flexibility of OpenSearch Ingestion pipelines with a Lambda processor to dynamically generate embeddings.
Use Amazon Neptune Analytics to analyze relationships in your data faster, Part 2: Enhancing fraud detection with Parquet and CSV import and export | AWS Database Blog
In this two-part series, we show how you can import and export using Parquet and CSV to quickly gather insights from your existing graph data. In Part 1, we introduced the import and export functionalities, and walked you through how to quickly get started with them. In this post, we show how you can use the new data mobility improvements in Neptune Analytics to enhance fraud detection.
Solve forecasting challenges for the retail and CPG industry using Amazon SageMaker Canvas | AWS Machine Learning Blog
In this post, we show you how Amazon Web Services (AWS) helps in solving forecasting challenges by customizing machine learning (ML) models for forecasting. We dive into Amazon SageMaker Canvas and explain how SageMaker Canvas can solve forecasting challenges for retail and consumer packaged goods (CPG) enterprises.
How Orca Security optimized their Amazon Neptune database performance | AWS Database Blog
Orca Security, an AWS Partner, is an independent cybersecurity software provider whose patented agentless-first cloud security platform is trusted by hundreds of enterprises globally. At Orca Security, we use a variety of metrics to assess the significance of security alerts on cloud assets. Our Amazon Neptune database plays a critical role in calculating the exposure of individual assets within a customer’s cloud environment. By building a graph that maps assets and their connectivity between one another and to the broader internet, the Orca Cloud Security Platform can evaluate both how an asset is exposed as well as how an attacker could potentially move laterally within an account. In this post, we explore some of the key strategies we’ve adopted to maximize the performance of our Amazon Neptune database.
Monitor server-side latency for Amazon MemoryDB for Valkey | AWS Database Blog
Amazon MemoryDB is a Valkey– and Redis OSS-compatible, durable, in-memory database service that delivers ultra-fast performance. With MemoryDB, data is stored in memory with Multi-AZ durability, which enables you to achieve microsecond read and single-digit millisecond write latency and high throughput. MemoryDB is often used for building durable microservices and latency-sensitive database workloads such as […]