News
Entertainment
Science & Technology
Life
Culture & Art
Hobbies
News
Entertainment
Science & Technology
Culture & Art
Hobbies
Automate Q&A email responses with Amazon Bedrock Knowledge Bases | AWS Machine Learning Blog
In this post, we illustrate automating the responses to email inquiries by using Amazon Bedrock Knowledge Bases and Amazon Simple Email Service (Amazon SES), both fully managed services. By linking user queries to relevant company domain information, Amazon Bedrock Knowledge Bases offers personalized responses.
Enhance data governance with enforced metadata rules in Amazon DataZone | AWS Big Data Blog
We’re excited to announce a new feature in Amazon DataZone that offers enhanced metadata governance for your subscription approval process. Using this update, domain owners can define metadata requirements and enforce them on data consumers when they request subscriptions to data assets. By making it mandatory for data consumers to provide specific metadata, domain owners can achieve compliance, meet organizational standards, and support audit and reporting needs.
Streamline RAG applications with intelligent metadata filtering using Amazon Bedrock | AWS Machine Learning Blog
In this post, we explore an innovative approach that uses LLMs on Amazon Bedrock to intelligently extract metadata filters from natural language queries. By combining the capabilities of LLM function calling and Pydantic data models, you can dynamically extract metadata from user queries. This approach can also enhance the quality of retrieved information and responses generated by the RAG applications.
Introducing scaling to 0 capacity with Amazon Aurora Serverless v2 | AWS Database Blog
Amazon Aurora Serverless v2 now supports scaling capacity down to 0 ACUs, enabling you to optimize costs during periods of database inactivity. Aurora Serverless is an on-demand, auto scaling configuration of Aurora that automatically adjusts your database capacity based on your workload requirements. Aurora Serverless measures database capacity in Aurora Capacity Units (ACUs) billed per second. 1 […]
How FP8 boosts LLM training by 18% on Amazon SageMaker P5 instances | AWS Machine Learning Blog
LLM training has seen remarkable advances in recent years, with organizations pushing the boundaries of what’s possible in terms of model size, performance, and efficiency. In this post, we explore how FP8 optimization can significantly speed up large model training on Amazon SageMaker P5 instances.
Embedding secure generative AI in mission-critical public safety applications | AWS Machine Learning Blog
This post shows how Mark43 uses Amazon Q Business to create a secure, generative AI-powered assistant that drives operational efficiency and improves community service. We explain how they embedded Amazon Q Business web experience in their web application with low code, so they could focus on creating a rich AI experience for their customers.
Unify structured data in Amazon Aurora and unstructured data in Amazon S3 for insights using Amazon Q | AWS Machine Learning Blog
In today’s data-intensive business landscape, organizations face the challenge of extracting valuable insights from diverse data sources scattered across their infrastructure. Whether it’s structured data in databases or unstructured content in document repositories, enterprises often struggle to efficiently query and use this wealth of information. In this post, we explore how you can use Amazon […]
Your guide to generative AI and ML at AWS re:Invent 2024 | AWS Machine Learning Blog
In this attendee guide, we’re highlighting a few of our favorite sessions to give you a glimpse into what’s in store. To help you plan your agenda for this year’s re:Invent, here are some highlights of the generative AI and ML sessions. Visit the session catalog to learn about all our generative AI and ML sessions.
Introducing Point in Time queries and SQL/PPL support in Amazon OpenSearch Serverless | AWS Big Data Blog
Today we announced support for three new features for Amazon OpenSearch Serverless: Point in Time (PIT) search, which enables you to maintain stable sorting for deep pagination in the presence of updates, and PPL and SQL, which give you new ways to query your data. In this post, we discuss the benefits of these new features and how to get started.
Manage access controls in generative AI-powered search applications using Amazon OpenSearch Service and Amazon Cognito | AWS Big Data Blog
In this post, we show you how to manage user access to enterprise documents in generative AI-powered tools according to the access you assign to each persona. This post illustrates how to build a document search RAG solution that makes sure only authorized users can access and interact with specific documents based on their roles, departments, and other relevant attributes. It combines OpenSearch Service and Amazon Cognito custom attributes to make a tag-based access control mechanism that makes it straightforward to manage at scale.
Migrate Oracle applications and databases using AWS Application Migration Service | AWS Database Blog
Migrating an Oracle application and its underlying database to the cloud can be inherently complex. Complexity is significantly amplified by various factors, including operating system compatibility, database and application version, software availability, database storage technologies such as Automatic Storage Management (ASM), and stringent business downtime requirements. AWS Application Migration Service accelerates the migration of applications to Amazon Web Services (AWS) by automatically replicating entire servers at the block level. In this post, we show you the process of migrating Oracle E-Business Suite to AWS using Application Migration Service.
Benchmarking Amazon Aurora Limitless with pgbench | AWS Database Blog
Aurora Limitless is a database solution that grows and shrinks vertically and horizontally with the current workload requirements. In this post, we show you how to test performance with the common tool pgbench. This tool is used with single-node database management systems (DBMS) and is optimized for single-node use cases. As we shall see in this post, this doesn’t mean that the tool measure what we think when it comes to multi-node systems. We demonstrate how it works with Aurora Limitless. We also discuss the obstacles and opportunities you might encounter when using this tool with Aurora Limitless.
Automate building guardrails for Amazon Bedrock using test-driven development | AWS Machine Learning Blog
Amazon Bedrock Guardrails helps implement safeguards for generative AI applications based on specific use cases and responsible AI policies. Amazon Bedrock Guardrails assists in controlling the interaction between users and foundation models (FMs) by detecting and filtering out undesirable and potentially harmful content, while maintaining safety and privacy. In this post, we explore a solution that automates building guardrails using a test-driven development approach.
Customize small language models on AWS with automotive terminology | AWS Machine Learning Blog
In this post, we guide you through the phases of customizing SLMs on AWS, with a specific focus on automotive terminology for diagnostics as a Q&A task. We begin with the data analysis phase and progress through the end-to-end process, covering fine-tuning, deployment, and evaluation. We compare a customized SLM with a general purpose LLM, using various metrics to assess vocabulary richness and overall accuracy.
Integrate custom applications with AWS Lake Formation – Part 2 | AWS Big Data Blog
In this two-part series, we show how to integrate custom applications or data processing engines with Lake Formation using the third-party services integration feature. In this post, we explore how to deploy a fully functional web client application, built with JavaScript/React through AWS Amplify (Gen 1), that uses the same Lambda function as the backend. The provisioned web application provides a user-friendly and intuitive way to view the Lake Formation policies that have been enforced.
Automate emails for task management using Amazon Bedrock Agents, Amazon Bedrock Knowledge Bases, and Amazon Bedrock Guardrails | AWS Machine Learning Blog
In this post, we demonstrate how to create an automated email response solution using Amazon Bedrock and its features, including Amazon Bedrock Agents, Amazon Bedrock Knowledge Bases, and Amazon Bedrock Guardrails.
Integrate custom applications with AWS Lake Formation – Part 1 | AWS Big Data Blog
In this two-part series, we show how to integrate custom applications or data processing engines with Lake Formation using the third-party services integration feature. In this post, we dive deep into the required Lake Formation and AWS Glue APIs. We walk through the steps to enforce Lake Formation policies within custom data applications. As an example, we present a sample Lake Formation integrated application implemented using AWS Lambda.
Introducing Amazon MWAA micro environments for Apache Airflow | AWS Big Data Blog
Today, we’re excited to announce mw1.micro, the latest addition to Amazon MWAA environment classes. This offering is designed to provide an even more cost-effective solution for running Airflow environments in the cloud. With mw1.micro, we’re bringing the power of Amazon MWAA to teams who require a lightweight environment without compromising on essential features. In this post, we’ll explore mw1.micro characteristics, key benefits, ideal use cases, and how you can set up an Amazon MWAA environment based on this new environment class.
Racing into the future: How AWS DeepRacer fueled my AI and ML journey | AWS Machine Learning Blog
In 2018, I sat in the audience at AWS re:Invent as Andy Jassy announced AWS DeepRacer—a fully autonomous 1/18th scale race car driven by reinforcement learning. At the time, I knew little about AI or machine learning (ML). As an engineer transitioning from legacy networks to cloud technologies, I had never considered myself a developer. […]
Automate cloud security vulnerability assessment and alerting using Amazon Bedrock | AWS Machine Learning Blog
This post demonstrates a proactive approach for security vulnerability assessment of your accounts and workloads, using Amazon GuardDuty, Amazon Bedrock, and other AWS serverless technologies. This approach aims to identify potential vulnerabilities proactively and provide your users with timely alerts and recommendations, avoiding reactive escalations and other damages.
How MSD uses Amazon Bedrock to translate natural language into SQL for complex healthcare databases | AWS Machine Learning Blog
MSD, a leading pharmaceutical company, collaborates with AWS to implement a powerful text-to-SQL generative AI solution using Amazon Bedrock and Anthropic's Claude 3.5 Sonnet model. This approach streamlines data extraction from complex healthcare databases like DE-SynPUF, enabling analysts to generate SQL queries from natural language questions. The solution addresses challenges such as coded columns, non-intuitive names, and ambiguous queries, significantly reducing query time and democratizing data access.
Generate and evaluate images in Amazon Bedrock with Amazon Titan Image Generator G1 v2 and Anthropic Claude 3.5 Sonnet | AWS Machine Learning Blog
In this post, we demonstrate how to interact with the Amazon Titan Image Generator G1 v2 model on Amazon Bedrock to generate an image. Then, we show you how to use Anthropic’s Claude 3.5 Sonnet on Amazon Bedrock to describe it, evaluate it with a score from 1–10, explain the reason behind the given score, and suggest improvements to the image.
Using attribute-based access control for tag-based access authorization with Amazon DynamoDB | AWS Database Blog
Amazon DynamoDB is a serverless, NoSQL, fully managed database service that delivers single-digit millisecond latency at any scale. AWS recently announced the general availability of attribute-based access control (ABAC) for Amazon DynamoDB. ABAC is an authorization strategy that defines permissions based on attributes. In AWS, these attributes are called tags. You can attach tags to […]
How InsuranceDekho transformed insurance agent interactions using Amazon Bedrock and generative AI | AWS Machine Learning Blog
In this post, we explain how InsuranceDekho harnessed the power of generative AI using Amazon Bedrock and Anthropic’s Claude to provide responses to customer queries on policy coverages, exclusions, and more. This let our customer care agents and POSPs confidently help our customers understand the policies without reaching out to insurance subject matter experts (SMEs) or memorizing complex plans while providing sales and after-sales services. The use of this solution has improved sales, cross-selling, and overall customer service experience.
DXC transforms data exploration for their oil and gas customers with LLM-powered tools | AWS Machine Learning Blog
In this post, we show you how DXC and AWS collaborated to build an AI assistant using large language models (LLMs), enabling users to access and analyze different data types from a variety of data sources. The AI assistant is powered by an intelligent agent that routes user questions to specialized tools that are optimized for different data types such as text, tables, and domain-specific formats. It uses the LLM’s ability to understand natural language, write code, and reason about conversational context.
Build cost-effective RAG applications with Binary Embeddings in Amazon Titan Text Embeddings V2, Amazon OpenSearch Serverless, and Amazon Bedrock Knowledge Bases | AWS Machine Learning Blog
Today, we are happy to announce the availability of Binary Embeddings for Amazon Titan Text Embeddings V2 in Amazon Bedrock Knowledge Bases and Amazon OpenSearch Serverless. This post summarizes the benefits of this new binary vector support and gives you information on how you can get started.
How Coinbase provides trustworthy financial experiences through real-time user clustering with Amazon Neptune | AWS Database Blog
In this post, we discuss how Coinbase migrated their user clustering system to Amazon Neptune Database, enabling them to solve complex and interconnected data challenges at scale.
Generate AWS Resilience Hub findings in natural language using Amazon Bedrock | AWS Machine Learning Blog
This blog post discusses a solution that combines AWS Resilience Hub and Amazon Bedrock to generate architectural findings in natural language. By using the capabilities of Resilience Hub and Amazon Bedrock, you can share findings with C-suite executives, engineers, managers, and other personas within your corporation to provide better visibility over maintaining a resilient architecture.
Enrich your AWS Glue Data Catalog with generative AI metadata using Amazon Bedrock | AWS Big Data Blog
By harnessing the capabilities of generative AI, you can automate the generation of comprehensive metadata descriptions for your data assets based on their documentation, enhancing discoverability, understanding, and the overall data governance within your AWS Cloud environment. This post shows you how to enrich your AWS Glue Data Catalog with dynamic metadata using foundation models (FMs) on Amazon Bedrock and your data documentation.
Considerations for addressing the core dimensions of responsible AI for Amazon Bedrock applications | AWS Machine Learning Blog
In this post, we introduce the core dimensions of responsible AI and explore considerations and strategies on how to address these dimensions for Amazon Bedrock applications.
Fine-tune multimodal models for vision and text use cases on Amazon SageMaker JumpStart | AWS Machine Learning Blog
In this post, we showcase how to fine-tune a text and vision model, such as Meta Llama 3.2, to better perform at visual question answering tasks. The Meta Llama 3.2 Vision Instruct models demonstrated impressive performance on the challenging DocVQA benchmark for visual question answering. By using the power of Amazon SageMaker JumpStart, we demonstrate the process of adapting these generative AI models to excel at understanding and responding to natural language questions about images.
Optimize your database storage for Oracle workloads on AWS, Part 2: Using hybrid partitioning and ILM data movement policies | AWS Database Blog
This is the second post of a two-part series. In Part 1, we explored how you can use Automatic Data Optimization (ADO) and Oracle Information Lifecycle Management (ILM) policies for data compression. In this post, we demonstrate how to use Heat Map statistics to monitor data usage and integrate this information with hybrid partitioning and ILM data movement policies to move data to more cost-effective storage solutions.
Optimize your database storage for Oracle workloads on AWS, Part 1: Using ADO and ILM data compression policies | AWS Database Blog
In this two-part series, we demonstrate how to optimize storage for Oracle database workloads on AWS by using Oracle’s built-in features, such as Heat Map, Automatic Data Optimization (ADO), and hybrid partitioning. These features help classify data by its lifecycle stage and automate data management tasks to significantly reduce storage costs, while enhancing database performance, especially for growing datasets. In this post, we explore how to use ADO and Oracle ILM policies to automatically compress data based on usage patterns.
From RAG to fabric: Lessons learned from building real-world RAGs at GenAIIC – Part 2 | AWS Machine Learning Blog
This post focuses on doing RAG on heterogeneous data formats. We first introduce routers, and how they can help managing diverse data sources. We then give tips on how to handle tabular data and will conclude with multimodal RAG, focusing specifically on solutions that handle both text and image data.
How FINRA established real-time operational observability for Amazon EMR big data workloads on Amazon EC2 with Prometheus and Grafana | AWS Big Data Blog
FINRA performs big data processing with large volumes of data and workloads with varying instance sizes and types on Amazon EMR. Amazon EMR is a cloud-based big data environment designed to process large amounts of data using open source tools such as Hadoop, Spark, HBase, Flink, Hudi, and Presto. In this post, we talk about our challenges and show how we built an observability framework to provide operational metrics insights for big data processing workloads on Amazon EMR on Amazon Elastic Compute Cloud (Amazon EC2) clusters.
How GoDaddy built Lighthouse, an interaction analytics solution to generate insights on support interactions using Amazon Bedrock | AWS Machine Learning Blog
In this post, we discuss how GoDaddy’s Care & Services team, in close collaboration with the AWS GenAI Labs team, built Lighthouse—a generative AI solution powered by Amazon Bedrock. Amazon Bedrock is a fully managed service that makes foundation models (FMs) from leading AI startups and Amazon available through an API, so you can choose from a wide range of FMs to find the model that is best suited for your use case. With Amazon Bedrock, GoDaddy’s Lighthouse mines insights from customer care interactions using crafted prompts to identify top call drivers and reduce friction points in customers’ product and website experiences, leading to improved customer experience.
Cohere Embed multimodal embeddings model is now available on Amazon SageMaker JumpStart | AWS Machine Learning Blog
The Cohere Embed multimodal embeddings model is now generally available on Amazon SageMaker JumpStart. This model is the newest Cohere Embed 3 model, which is now multimodal and capable of generating embeddings from both text and images, enabling enterprises to unlock real value from their vast amounts of data that exist in image form. In this post, we discuss the benefits and capabilities of this new model with some examples.
Principal Financial Group uses QnABot on AWS and Amazon Q Business to enhance workforce productivity with generative AI | AWS Machine Learning Blog
In this post, we explore how Principal used QnABot paired with Amazon Q Business and Amazon Bedrock to create Principal AI Generative Experience: a user-friendly, secure internal chatbot for faster access to information. Using generative AI, Principal’s employees can now focus on deeper human judgment based decisioning, instead of spending time scouring for answers from data sources manually.
MultiXacts in PostgreSQL: usage, side effects, and monitoring | AWS Database Blog
PostgreSQL’s ability to handle concurrent access while maintaining data consistency relies heavily on its locking mechanisms, particularly at the row level. When multiple transactions attempt to lock the same row simultaneously, PostgreSQL turns to a specialized structure called MultiXact IDs. While MultiXacts provide an efficient way to manage multiple locks on a single row, they […]
New – Amazon DynamoDB lowers pricing for on-demand throughput and global tables | AWS Database Blog
Our continued engineering investments on how efficiently we can operate DynamoDB allow us to identify and pass on cost savings to you. Effective November 1, 2024, DynamoDB has reduced prices for on-demand throughput by 50% and global tables by up to 67%, making it more cost-effective than ever to build, scale, and optimize applications. In this post, we discuss the benefits of these price reductions, on-demand mode, and global tables.