Search the Community

April has been packed with new releases! Last week continued that trend with many new releases supporting a variety of domains such as security, analytics, devops, and many more, as well as more exciting new capabilities within generative AI. If you missed the AWS Summit London 2024, you can now watch the sessions on demand, including the keynote by Tanuja Randery, VP & Marketing Director, EMEA, and many of the break-out sessions which will continue to be released over the coming weeks. Last week’s launches Here are some of the highlights that caught my attention this week: Manual and automatic rollback from any stage in AWS CodePipeline – You can now rollback any stage, other than Source, to any previously known good state in if you use a V2 pipeline in AWS CodePipeline. You can configure automatic rollback which will use the source changes from the most recent successful pipeline execution in the case of failure, or you can initiate a manual rollback for any stage from the console, API or SDK and choose which pipeline execution you want to use for the rollback. AWS CodeArtifact now supports RubyGems – Ruby community, rejoice, you can now store your gems in AWS CodeArtifact! You can integrate it with RubyGems.org, and CodeArtifact will automatically fetch any gems requested by the client and store them locally in your CodeArtifact repository. That means that you can have a centralized place for both your first-party and public gems so developers can access their dependencies from a single source. Create a repository in AWS CodeArtifact and choose “rubygems-store” to connect your repository to RubyGems.org on the “Public upstream repositories” dropdown. Amazon EventBridge Pipes now supports event delivery through AWS PrivateLink – You can now deliver events to an Amazon EventBridge Pipes target without traversing the public internet by using AWS PrivateLink. You can poll for events in a private subnet in your Amazon Virtual Private Cloud (VPC) without having to deploy any additional infrastructure to keep your traffic private. Amazon Bedrock launches continue. You can now run scalable, enterprise-grade generative AI workloads with Cohere Command R & R+. And Amazon Titan Text V2 is now optimized for improving Retrieval-Augmented Generation (RAG). AWS Trusted Advisor – last year we launched Trusted Advisor APIs enabling you to programmatically consume recommendations. A new API is available now that you can use to exclude resources from recommendations. Amazon EC2 – there have been two new great launches this week for EC2 users. You can now mark your AMIs as “protected” to avoid them being deregistered by accident. You can also now easily discover your active AMIs by simply describing them. Amazon CodeCatalyst – you can now view your git commit history in the CodeCatalyst console. General Availability Many new services and capabilities became generally available this week. Amazon Q in QuickSight – Amazon Q has brought generative BI to Amazon QuickSight giving you the ability to build beautiful dashboards automatically simply by using natural language and it’s now generally available. To get started, head to the Quicksight Pricing page to explore all options or start a 30-day free trial which allows up to 4 users per QuickSight account to use all the new generative AI features. With the new generative AI features enabled by Amazon Q in Amazon QuickSight you can use natural language queries to build, sort and filter dashboards. (source: AWS Documentation) Amazon Q Business (GA) and Amazon Q Apps (Preview) – Also generally available now is Amazon Q Business which we launched last year at AWS re:Invent 2023 with the ability to connect seamlessly with over 40 popular enterprise systems, including Microsoft 365, Salesforce, Amazon Simple Storage Service (Amazon S3), Gmail, and so many more. This allows Amazon Q Business to know about your business so your employees can generate content, solve problems, and take actions that are specific to your business. We have also launched support for custom plug-ins, so now you can create your own integrations with any third-party application. With general availability of Amazon Q Business we have also launched the ability to create your own custom plugins to connect to any third-party API. Another highlight of this release is the launch of Amazon Q Apps, which enables you to quickly generate an app from your conversation with Amazon Q Business, or by describing what you would like it to generate for you. All guardrails from Amazon Q Business apply, and it’s easy to share your apps with colleagues through an admin-managed library. Amazon Q Apps is in preview now. Check out Channy Yun’s post for a deeper dive into Amazon Q Business and Amazon Q Apps, which guides you through these new features. Amazon Q Developer – you can use Q Developer to completely change your developer flow. It has all the capabilities of what was previously known as Amazon CodeWhisperer, such as Q&A, diagnosing common errors, generating code including tests, and many more. Now it has expanded, so you can use it to generate SQL, and build data integration pipelines using natural language. In preview, it can describe resources in your AWS account and help you retrieve and analyze cost data from AWS Cost Explorer. For a full list of AWS announcements, be sure to keep an eye on the ‘What’s New with AWS?‘ page. Other AWS news Here are some additional projects, blog posts, and news items that you might find interesting: AWS open source news and updates – My colleague Ricardo writes about open source projects, tools, and events from the AWS Community. Discover Claude 3 – If you’re a developer looking for a good source to get started with Claude 3 them I recommend this great post from my colleague Haowen Huang: Mastering Amazon Bedrock with Claude 3: Developer’s Guide with Demos. Upcoming AWS events Check your calendars and sign up for upcoming AWS events: AWS Summits – Join free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Register in your nearest city: Singapore (May 7), Seoul (May 16–17), Hong Kong (May 22), Milan (May 23), Stockholm (June 4), and Madrid (June 5). AWS re:Inforce – Explore 2.5 days of immersive cloud security learning in the age of generative AI at AWS re:Inforce, June 10–12 in Pennsylvania. AWS Community Days – Join community-led conferences that feature technical discussions, workshops, and hands-on labs led by expert AWS users and industry leaders from around the world: Turkey (May 18), Midwest | Columbus (June 13), Sri Lanka (June 27), Cameroon (July 13), Nigeria (August 24), and New York (August 28). GOTO EDA Day London – Join us in London on May 14 to learn about event-driven architectures (EDA) for building highly scalable, fault tolerant, and extensible applications. This conference is organized by GOTO, AWS, and partners. Browse all upcoming AWS led in-person and virtual events and developer-focused events. That’s all for this week. Check back next Monday for another Weekly Roundup! — Matheus Guimaraes This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS! View the full article

Amazon Titan Text Embeddings V2, a new embeddings model in the Amazon Titan family of models, is now generally available in Amazon Bedrock. Using Titan Text Embeddings V2, customers can perform various natural language processing (NLP) tasks by representing text data as numerical vectors, known as embeddings. These embeddings capture the semantic and contextual relationships between words, phrases, or documents in a high-dimensional vector space. This model is optimized for Retrieval-Augmented Generations (RAG) use cases and is also well suited for a variety of other tasks such as information retrieval, question and answer chatbots, classification, and personalized recommendations. View the full article

The Amazon Titan family of models, available exclusively in Amazon Bedrock, is built on top of 25 years of Amazon expertise in artificial intelligence (AI) and machine learning (ML) advancements. Amazon Titan foundation models (FMs) offer a comprehensive suite of pre-trained image, multimodal, and text models accessible through a fully managed API. Trained on extensive datasets, Amazon Titan models are powerful and versatile, designed for a range of applications while adhering to responsible AI practices. The latest addition to the Amazon Titan family is Amazon Titan Text Embeddings V2, the second-generation text embeddings model from Amazon now available within Amazon Bedrock. This new text embeddings model is optimized for Retrieval-Augmented Generation (RAG). It is pre-trained on 100+ languages and on code. Amazon Titan Text Embeddings V2 now lets you choose the size of of the output vector (either 256, 512, or 1024). Larger vector sizes create more detailed responses, but will also increase the computational time. Shorter vector lengths are less detailed but will improve the response time. Using smaller vectors helps to reduce your storage costs and the latency to search and retrieve document extracts from a vector database. We measured the accuracy of the vectors generated by Amazon Titan Text Embeddings V2 and we observed that vectors with 512 dimensions keep approximately 99 percent of the accuracy provided by vectors with 1024 dimensions. Vectors with 256 dimensions keep 97 percent of the accuracy. This means that you can save 75 percent in vector storage (from 1024 down to 256 dimensions) and keep approximately 97 percent of the accuracy provided by larger vectors. Amazon Titan Text Embeddings V2 also proposes an improved unit vector normalization that helps improve the accuracy when measuring vector similarity. You can choose between normalized or unnormalized versions of the embeddings based on your use case (normalized is more accurate for RAG use cases). Normalization of a vector is the process of scaling it to have a unit length or magnitude of 1. It is useful to ensure that all vectors have the same scale and contribute equally during vector operations, preventing some vectors from dominating others due to their larger magnitudes. This new text embeddings model is well-suited for a variety of use cases. It can help you perform semantic searches on documents, for example, to detect plagiarism. It can classify labels into data-based learned representations, for example, to categorize movies into genres. It can also improve the quality and relevance of retrieved or generated search results, for example, recommending content based on interest using RAG. How embeddings help to improve accuracy of RAG Imagine you’re a superpowered research assistant for a large language model (LLM). LLMs are like those brainiacs who can write different creative text formats, but their knowledge comes from the massive datasets they were trained on. This training data might be a bit outdated or lack specific details for your needs. This is where RAG comes in. RAG acts like your assistant, fetching relevant information from a custom source, like a company knowledge base. When the LLM needs to answer a question, RAG provides the most up-to-date information to help it generate the best possible response. To find the most up-to-date information, RAG uses embeddings. Imagine these embeddings (or vectors) as super-condensed summaries that capture the key idea of a piece of text. A high-quality embeddings model, such as Amazon Titan Text Embeddings V2, can create these summaries accurately, like a great assistant who can quickly grasp the important points of each document. This ensures RAG retrieves the most relevant information for the LLM, leading to more accurate and on-point answers. Think of it like searching a library. Each page of the book is indexed and represented by a vector. With a bad search system, you might end up with a pile of books that aren’t quite what you need. But with a great search system that understands the content (like a high-quality embeddings model), you’ll get exactly what you’re looking for, making the LLM’s job of generating the answer much easier. Amazon Titan Text Embeddings V2 overview Amazon Titan Text Embeddings V2 is optimized for high accuracy and retrieval performance at smaller dimensions for reduced storage and latency. We measured that vectors with 512 dimensions maintain approximately 99 percent of the accuracy provided by vectors with 1024 dimensions. Those with 256 dimensions offer 97 percent of the accuracy. Max tokens 8,192 Languages 100+ in pre-training Fine-tuning supported No Normalization supported Yes Vector size 256, 512, 1,024 (default) How to use Amazon Titan Text Embeddings V2 It’s very likely you will interact with Amazon Titan Text Embeddings V2 indirectly through Knowledge Bases for Amazon Bedrock. Knowledge Bases takes care of the heavy lifting to create a RAG-based application. However, you can also use the Amazon Bedrock Runtime API to directly invoke the model from your code. Here is a simple example in the Swift programming language (just to show you you can use any programming language, not just Python): import Foundation import AWSBedrockRuntime let text = "This is the text to transform in a vector" // create an API client let client = try BedrockRuntimeClient(region: "us-east-1") // create the request let request = InvokeModelInput( accept: "application/json", body: """ { "inputText": "\(text)", "dimensions": 256, "normalize": true } """.data(using: .utf8), contentType: "application/json", modelId: "amazon.titan-embed-text-v2:0") // send the request let response = try await client.invokeModel(input: request) // decode the response let response = String(data: (response.body!), encoding: .utf8) print(response ?? "") The model takes three parameters in its payload: inputText – The text to convert to embeddings. normalize – A flag indicating whether or not to normalize the output embeddings. It defaults to true, which is optimal for RAG use cases. dimensions – The number of dimensions the output embeddings should have. Three values are accepted: 256, 512, and 1024 (the default value). I added the dependency on the AWS SDK for Swift in my Package.swift. I type swift run to build and run this code. It prints the following output (truncated to keep it brief): {"embedding":[-0.26757812,0.15332031,-0.015991211...-0.8203125,0.94921875], "inputTextTokenCount":9} As usual, do not forget to enable access to the new model in the Amazon Bedrock console before using the API. Amazon Titan Text Embeddings V2 will soon be the default LLM proposed by Knowledge Bases for Amazon Bedrock. Your existing knowledge bases created with the original Amazon Titan Text Embeddings model will continue to work without changes. To learn more about the Amazon Titan family of models, view the following video: The new Amazon Titan Text Embeddings V2 model is available today in Amazon Bedrock in the US East (N. Virginia) and US West (Oregon) AWS Regions. Check the full Region list for future updates. To learn more, check out the Amazon Titan in Amazon Bedrock product page and pricing page. Also, do not miss this blog post to learn how to use Amazon Titan Text Embeddings models. You can also visit our community.aws site to find deep-dive technical content and to discover how our Builder communities are using Amazon Bedrock in their solutions. Give Amazon Titan Text Embeddings V2 a try in the Amazon Bedrock console today, and send feedback to AWS re:Post for Amazon Bedrock or through your usual AWS Support contacts. -- sebView the full article

You can now access Cohere’s newest state-of-the-art enterprise foundation model family, Command R+ and Command R, in Amazon Bedrock. These generative AI models are highly scalable, optimized for long context tasks like advanced retrieval-augmented generation (RAG) with citations to mitigate hallucinations, multi-step tool use to automate complex business tasks, and are multilingual in 10 languages to support global business operations. View the full article

This was a busy week for Amazon Bedrock with many new features! Using GitHub Actions with AWS CodeBuild is much easier. Also, Amazon Q in Amazon CodeCatalyst can now manage more complex issues. I was amazed to meet so many new and old friends at the AWS Summit London. To give you a quick glimpse, here’s AWS Hero Yan Cui starting his presentation at the AWS Community stage. Last week’s launches With so many interesting new features, I start with generative artificial intelligence (generative AI) and then move to the other topics. Here’s what got my attention: Amazon Bedrock – For supported architectures such as Llama, Mistral, or Flan T5, you can now import custom models and access them on demand. Model evaluation is now generally available to help you evaluate, compare, and select the best foundation models (FMs) for your specific use case. You can now access Meta’s Llama 3 models. Agents for Amazon Bedrock – A simplified agent creation and return of control, so that you can define an action schema and get the control back to perform those action without needing to create a specific AWS Lambda function. Agents also added support for Anthropic Claude 3 Haiku and Sonnet to help build faster and more intelligent agents. Knowledge Bases for Amazon Bedrock – You can now ingest data from up to five data sources and provide more complete answers. In the console, you can now chat with one of your documents without needing to set up a vector database (read more in this Machine Learning blog post). Guardrails for Amazon Bedrock – The capability to implement safeguards based on your use cases and responsible AI policies is now available with new safety filters and privacy controls. Amazon Titan – The new watermark detection feature is now generally available in Amazon Bedrock. In this way, you can identify images generated by Amazon Titan Image Generator using an invisible watermark present in all images generated by Amazon Titan. Amazon CodeCatalyst – Amazon Q can now split complex issues into separate, simpler tasks that can then be assigned to a user or back to Amazon Q. CodeCatalyst now also supports approval gates within a workflow. Approval gates pause a workflow that is building, testing, and deploying code so that a user can validate whether it should be allowed to proceed. Amazon EC2 – You can now remove an automatically assigned public IPv4 address from an EC2 instance. If you no longer need the automatically assigned public IPv4 (for example, because you are migrating to using a private IPv4 address for SSH with EC2 instance connect), you can use this option to quickly remove the automatically assigned public IPv4 address and reduce your public IPv4 costs. Network Load Balancer – Now supports Resource Map in AWS Management Console, a tool that displays all your NLB resources and their relationships in a visual format on a single page. Note that Application Load Balancer already supports Resource Map in the console. AWS CodeBuild – Now supports managed GitHub Action self-hosted runners. You can configure CodeBuild projects to receive GitHub Actions workflow job events and run them on CodeBuild ephemeral hosts. Amazon Route 53 – You can now define a standard DNS configuration in the form of a Profile, apply this configuration to multiple VPCs, and share it across AWS accounts. AWS Direct Connect – Hosted connections now support capacities up to 25 Gbps. Before, the maximum was 10 Gbps. Higher bandwidths simplify deployments of applications such as advanced driver assistance systems (ADAS), media and entertainment (M&E), artificial intelligence (AI), and machine learning (ML). NoSQL Workbench for Amazon DynamoDB – A revamped operation builder user interface to help you better navigate, run operations, and browse your DynamoDB tables. Amazon GameLift – Now supports in preview end-to-end development of containerized workloads, including deployment and scaling on premises, in the cloud, or for hybrid configurations. You can use containers for building, deploying, and running game server packages. For a full list of AWS announcements, be sure to keep an eye on the What's New at AWS page. Other AWS news Here are some additional projects, blog posts, and news items that you might find interesting: GQL, the new ISO standard for graphs, has arrived – GQL, which stands for Graph Query Language, is the first new ISO database language since the introduction of SQL in 1987. Authorize API Gateway APIs using Amazon Verified Permissions and Amazon Cognito – Externalizing authorization logic for application APIs can yield multiple benefits. Here’s an example of how to use Cedar policies to secure a REST API. Build and deploy a 1 TB/s file system in under an hour – Very nice walkthrough for something that used to be not so easy to do in the recent past. Let’s Architect! Discovering Generative AI on AWS – A new episode in this amazing series of posts that provides a broad introduction to the domain and then shares a mix of videos, blog posts, and hands-on workshops. Building scalable, secure, and reliable RAG applications using Knowledge Bases for Amazon Bedrock – This post explores the new features (including AWS CloudFormation support) and how they align with the AWS Well-Architected Framework. Using the unified CloudWatch Agent to send traces to AWS X-Ray – With added support for the collection of AWS X-Ray and OpenTelemetry traces, you can now provision a single agent to capture metrics, logs, and traces. The executive’s guide to generative AI for sustainability – A guide for implementing a generative AI roadmap within sustainability strategies. AWS open source news and updates – My colleague Ricardo writes about open source projects, tools, and events from the AWS Community. Check out Ricardo’s page for the latest updates. Upcoming AWS events Check your calendars and sign up for upcoming AWS events: AWS Summits – Join free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Register in your nearest city: Singapore (May 7), Seoul (May 16–17), Hong Kong (May 22), Milan (May 23), Stockholm (June 4), and Madrid (June 5). AWS re:Inforce – Explore 2.5 days of immersive cloud security learning in the age of generative AI at AWS re:Inforce, June 10–12 in Pennsylvania. AWS Community Days – Join community-led conferences that feature technical discussions, workshops, and hands-on labs led by expert AWS users and industry leaders from around the world: Turkey (May 18), Midwest | Columbus (June 13), Sri Lanka (June 27), Cameroon (July 13), Nigeria (August 24), and New York (August 28). GOTO EDA Day London – Join us in London on May 14 to learn about event-driven architectures (EDA) for building highly scalable, fault tolerant, and extensible applications. This conference is organized by GOTO, AWS, and partners. Browse all upcoming AWS led in-person and virtual events and developer-focused events. That’s all for this week. Check back next Monday for another Weekly Roundup! — Danilo This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS! View the full article

Agents for Amazon Bedrock enable generative AI applications to automate multi-step tasks across company systems and data sources. Agents removes the undifferentiated lifting of orchestration, infrastructure hosting and management, and we’re making building Agents easier than ever. View the full article

You can now access Meta’s Llama 3 models, Llama 3 8B and Llama 3 70B, in Amazon Bedrock. Meta Llama 3 is designed for you to build, experiment, and responsibly scale your generative artificial intelligence applications. You can now use these two new Llama 3 models in Amazon Bedrock enabling you to easily experiment with and evaluate even more top foundation models for your use case. View the full article

Model Evaluation on Amazon Bedrock allows you to evaluate, compare, and select the best foundation models for your use case. Amazon Bedrock offers a choice of automatic evaluation and human evaluation. You can use automatic evaluation with predefined algorithms for metrics such as accuracy, robustness, and toxicity. Additionally, for those metrics or subjective and custom metrics, such as friendliness, style, and alignment to brand voice, you can set up a human evaluation workflow with a few clicks. Human evaluation workflows can leverage your own employees or an AWS-managed team as reviewers. Model evaluation provides built-in curated datasets or you can bring your own datasets. View the full article

Amazon Titan Image Generator enables content creators with rapid ideation and iteration resulting in high efficiency image generation. The Amazon Titan Image Generator model is now generally available in Amazon Bedrock, helping you easily build and scale generative AI applications with new image generation and image editing capabilities. View the full article

Knowledge Bases for Amazon Bedrock allows you to connect foundation models (FMs) to internal company data sources to deliver more relevant, context-specific, and accurate responses. Knowledge Bases (KB) now provides a real-time, zero-setup, and low-cost method to securely chat with single documents. View the full article

Knowledge Bases for Amazon Bedrock is a fully managed Retrieval-Augmented Generation (RAG) capability that allows you to connect foundation models (FMs) to internal company data sources to deliver more relevant and accurate responses. Knowledge Bases now supports adding multiple data sources, across accounts. View the full article

Amazon Titan Image Generator's new watermark detection feature is now generally available in Amazon Bedrock. All Amazon Titan-generated images contain an invisible watermark, by default. The watermark detection mechanism allows you to identify images generated by Amazon Titan Image Generator, a foundation model that allows users to create realistic, studio-quality images in large volumes and at low cost, using natural language prompts. View the full article

We are excited to announce the preview of Custom Model Import for Amazon Bedrock. Now you can import customized models into Amazon Bedrock to accelerate your generative AI application development. This new feature allows you to leverage your prior model customization investments within Amazon Bedrock and consume them in the same fully-managed manner as Bedrock’s existing models. For supported architectures such as Llama, Mistral, or Flan T5, you can now import models customized anywhere and access them on-demand. View the full article

Agents for Amazon Bedrock enable developers to create generative AI-based applications that can complete complex tasks for a wide range of use cases and deliver answers based on company knowledge sources. In order to complete complex tasks, with high accuracy, reasoning capabilities of the underlying foundational model (FM) play a critical role. View the full article

Today, we are announcing the general availability of Guardrails for Amazon Bedrock that enables customers to implement safeguards across large language models (LLMs) based on their use cases and responsible AI policies. Customers can create multiple guardrails tailored to different use cases and apply them on multiple LLMs, providing a consistent user experience and standardizing safety controls across generative AI applications. View the full article

AWS Summits continue to rock the world, with events taking place in various locations around the globe. AWS Summit London (April 24) is the last one in April, and there are nine more in May, including AWS Summit Berlin (May 15–16), AWS Summit Los Angeles (May 22), and AWS Summit Dubai (May 29). Join us to connect, collaborate, and learn about AWS! While you decide which summit to attend, let’s look at the last week’s new announcements. Last week’s launches Last week was another busy one in the world of artificial intelligence (AI). Here are some launches that got my attention. Anthropic’s Claude 3 Opus now available in Amazon Bedrock – After Claude 3 Sonnet and Claude 3 Haiku, two of the three state-of-the-art models of Anthropic’s Claude 3, Opus is now available in Amazon Bedrock. Cluade 3 Opus is at the forefront of generative AI, demonstrating comprehension and fluency on complicated tasks at nearly human levels. Like the rest of the Claude 3 family, Opus can process images and return text outputs. Claude 3 Opus shows an estimated twofold gain in accuracy over Claude 2.1 on difficult open-ended questions, reducing the likelihood of faulty responses. Meta Llama 3 now available in Amazon SageMaker JumpStart – Meta Llama 3 is now available in Amazon SageMaker JumpStart, a machine learning (ML) hub that can help you accelerate your ML journey. You can deploy and use Llama 3 foundation models (FMs) with a few steps in Amazon SageMaker Studio or programmatically through the Amazon SageMaker Python SDK. Llama is available in two parameter sizes, 8B and 70B, and can be used to support a broad range of use cases, with improvements in reasoning, code generation, and instruction following. The model will be deployed in an AWS secure environment under your VPC controls, helping ensure data security. Built-in SQL extension with Amazon SageMaker Studio Notebooks – SageMaker Studio’s JupyterLab now includes a built-in SQL extension to discover, explore, and transform data from various sources using SQL and Python directly within the notebooks. You can now seamlessly connect to popular data services and easily browse and search databases, schemas, tables, and views. You can also preview data within the notebook interface. New features such as SQL command completion, code formatting assistance, and syntax highlighting improve developer productivity. To learn more, visit Explore data with ease: Use SQL and Text-to-SQL in Amazon SageMaker Studio JupyterLab notebooks and the SageMaker Developer Guide. AWS Split Cost Allocation Data for Amazon EKS – You can now receive granular cost visibility for Amazon Elastic Kubernetes Service (Amazon EKS) in the AWS Cost and Usage Reports (CUR) to analyze, optimize, and chargeback cost and usage for your Kubernetes applications. You can allocate application costs to individual business units and teams based on how Kubernetes applications consume shared Amazon EC2 CPU and memory resources. You can aggregate these costs by cluster, namespace, and other Kubernetes primitives to allocate costs to individual business units or teams. These cost details will be accessible in the CUR 24 hours after opt-in. You can use the Containers Cost Allocation dashboard to visualize the costs in Amazon QuickSight and the CUR query library to query the costs using Amazon Athena. AWS KMS automatic key rotation enhancements – AWS Key Management Service (AWS KMS) introduces faster options for automatic symmetric key rotation. You can now customize rotation frequency between 90 days to 7 years, invoke key rotation on demand for customer-managed AWS KMS keys, and view the rotation history for any rotated AWS KMS key. There is a nice post on the Security Blog you can visit to learn more about this feature, including a little bit of history about cryptography. Amazon Personalize automatic solution training – Amazon Personalize now offers automatic training for solutions. With automatic training, you can set a cadence for your Amazon Personalize solutions to automatically retrain using the latest data from your dataset group. This process creates a newly trained machine learning (ML) model, also known as a solution version, and maintains the relevance of Amazon Personalize recommendations for end users. Automatic training mitigates model drift and makes sure recommendations align with users’ evolving behaviors and preferences. With Amazon Personalize, you can personalize your website, app, ads, emails, and more, using the same machine learning technology used by Amazon, without requiring any prior ML experience. To get started with Amazon Personalize, visit our documentation. For a full list of AWS announcements, be sure to keep an eye on the What's New at AWS page. We launched existing services and instance types in additional Regions: Amazon RDS for Oracle extends support for x2iedn in Asia Pacific (Hyderabad, Jakarta, and Osaka), Europe (Milan and Paris), US West (N. California), AWS GovCloud (US-East), and AWS GovCloud (US-West). X2iedn instances are targeted for enterprise-class high-performance databases with high compute (up to 128 vCPUs), large memory (up to 4 TB) and storage throughput requirements (up to 256K IOPS) with a 32:1 ratio of memory to vCPU. Amazon MSK is now available in Canada West (Calgary) Region. Amazon Managed Streaming for Apache Kafka (Amazon MSK) is a fully managed service for Apache Kafka and Kafka Connect that makes it easier for you to build and run applications that use Apache Kafka as a data store. Amazon Cognito is now available in Europe (Spain) Region. Amazon Cognito makes it easy to add authentication, authorization, and user management to your web and mobile apps supporting sign-in with social identity providers such as Apple, Facebook, Google, and Amazon, and enterprise identity providers through standards such as SAML 2.0 and OpenID Connect. AWS Network Manager is now available in AWS Israel (Tel Aviv) Region. AWS Network Manager reduces the operational complexity of managing global networks across AWS and on-premises locations by providing a single global view of your private network. AWS Storage Gateway is now available in AWS Canada West (Calgary) Region. AWS Storage Gateway is a hybrid cloud storage service that provides on-premises applications access to virtually unlimited storage in the cloud. Amazon SQS announces support for FIFO dead-letter queue redrive in the AWS GovCloud (US) Regions. Dead-letter queue redrive is an enhanced capability to improve the dead-letter queue management experience for Amazon Simple Queue Service (Amazon SQS) customers. Amazon EC2 R6gd instances are now available in Europe (Zurich) Region. R6gd instances are powered by AWS Graviton2 processors and are built on the AWS Nitro System. These instances offer up to 25 Gbps of network bandwidth, up to 19 Gbps of bandwidth to the Amazon Elastic Block Store (Amazon EBS), up to 512 GiB RAM, and up to 3.8TB of NVMe SSD local instance storage. Amazon Simple Email Service is now available in the AWS GovCloud (US-East) Region. Amazon Simple Email Service (SES) is a scalable, cost-effective, and flexible cloud-based email service that allows you to send marketing, notification, and transactional emails from within any application. To learn more, visit Amazon SES page. AWS Glue Studio Notebooks is now available in the Middle East (UAE), Asia Pacific (Hyderabad), Asia Pacific (Melbourne), Israel (Tel Aviv), Europe (Spain), and Europe (Zurich) Regions. AWS Glue Studio Notebooks provides interactive job authoring in AWS Glue, which helps simplify the process of developing data integration jobs. To learn more, visit Authoring code with AWS Glue Studio notebooks. Amazon S3 Access Grants is now available in in the Middle East (UAE), Asia Pacific (Melbourne), Asia Pacific (Hyderabad), and Europe (Spain) Regions. Amazon Simple Storage Service (Amazon S3) Access Grants map identities in directories such as Microsoft Entra ID, or AWS Identity and Access Management (IAM) principals, to datasets in S3. This helps you manage data permissions at scale by automatically granting S3 access to end-users based on their corporate identity. To learn more, visit Amazon S3 Access Grants page. Other AWS news Here are some additional news that you might find interesting: The PartyRock Generative AI Hackathon winners – The PartyRock Generative AI Hackathon concluded with over 7,650 registrants submitting 1,200 projects across four challenge categories, featuring top winners like Parable Rhythm – The Interactive Crime Thriller, Faith – Manga Creation Tools, and Arghhhh! Zombie. Participants showed remarkable creativity and technical prowess, with prizes totaling $60,000 in AWS credits. I tried the Faith – Manga Creation Tools app using my daughter Arya’s made-up stories and ideas and the result was quite impressive. Visit Jeff Barr’s post to learn more about how to try the apps for yourself. AWS open source news and updates – My colleague Ricardo writes about open source projects, tools, and events from the AWS Community. Check out Ricardo’s page for the latest updates. Upcoming AWS events Check your calendars and sign up for upcoming AWS events: AWS Summits – Join free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Register in your nearest city: Singapore (May 7), Seoul (May 16–17), Hong Kong (May 22), Milan (May 23), Stockholm (June 4), and Madrid (June 5). AWS re:Inforce – Explore cloud security in the age of generative AI at AWS re:Inforce, June 10–12 in Pennsylvania for 2.5 days of immersive cloud security learning designed to help drive your business initiatives. AWS Community Days – Join community-led conferences that feature technical discussions, workshops, and hands-on labs led by expert AWS users and industry leaders from around the world: Turkey (May 18), Midwest | Columbus (June 13), Sri Lanka (June 27), Cameroon (July 13), Nigeria (August 24), and New York (August 28). You can browse all upcoming AWS led in-person and virtual events and developer-focused events here. That’s all for this week. Check back next Monday for another Weekly Roundup! — Esra This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS! View the full article

Anthropic’s Claude 3 Opus foundation model, the most advanced and intelligent model in the Claude 3 Family, is now available on Amazon Bedrock. The Claude 3 family of models (Claude 3 Opus, Claude 3 Sonnet, and Claude 3 Haiku) is the next generation of state-of-the-art models from Anthropic. Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models from leading AI companies, like Anthropic, along with a broad set of capabilities that provide you with the easiest way to build and scale generative AI applications. View the full article

We are living in the generative artificial intelligence (AI) era; a time of rapid innovation. When Anthropic announced its Claude 3 foundation models (FMs) on March 4, we made Claude 3 Sonnet, a model balanced between skills and speed, available on Amazon Bedrock the same day. On March 13, we launched the Claude 3 Haiku model on Amazon Bedrock, the fastest and most compact member of the Claude 3 family for near-instant responsiveness. Today, we are announcing the availability of Anthropic’s Claude 3 Opus on Amazon Bedrock, the most intelligent Claude 3 model, with best-in-market performance on highly complex tasks. It can navigate open-ended prompts and sight-unseen scenarios with remarkable fluency and human-like understanding, leading the frontier of general intelligence. With the availability of Claude 3 Opus on Amazon Bedrock, enterprises can build generative AI applications to automate tasks, generate revenue through user-facing applications, conduct complex financial forecasts, and accelerate research and development across various sectors. Like the rest of the Claude 3 family, Opus can process images and return text outputs. Claude 3 Opus shows an estimated twofold gain in accuracy over Claude 2.1 on difficult open-ended questions, reducing the likelihood of faulty responses. As enterprise customers rely on Claude across industries like healthcare, finance, and legal research, improved accuracy is essential for safety and performance. How does Claude 3 Opus perform? Claude 3 Opus outperforms its peers on most of the common evaluation benchmarks for AI systems, including undergraduate-level expert knowledge (MMLU), graduate-level expert reasoning (GPQA), basic mathematics (GSM8K), and more. It exhibits high levels of comprehension and fluency on complex tasks, leading the frontier of general intelligence. Source: https://www.anthropic.com/news/claude-3-family Here are a few supported use cases for the Claude 3 Opus model: Task automation: planning and execution of complex actions across APIs, databases, and interactive coding Research: brainstorming and hypothesis generation, research review, and drug discovery Strategy: advanced analysis of charts and graphs, financials and market trends, and forecasting To learn more about Claude 3 Opus’s features and capabilities, visit Anthropic’s Claude on Bedrock page and Anthropic Claude models in the Amazon Bedrock documentation. Claude 3 Opus in action If you are new to using Anthropic models, go to the Amazon Bedrock console and choose Model access on the bottom left pane. Request access separately for Claude 3 Opus. To test Claude 3 Opus in the console, choose Text or Chat under Playgrounds in the left menu pane. Then choose Select model and select Anthropic as the category and Claude 3 Opus as the model. To test more Claude prompt examples, choose Load examples. You can view and run examples specific to Claude 3 Opus, such as analyzing a quarterly report, building a website, and creating a side-scrolling game. By choosing View API request, you can also access the model using code examples in the AWS Command Line Interface (AWS CLI) and AWS SDKs. Here is a sample of the AWS CLI command: aws bedrock-runtime invoke-model \ --model-id anthropic.claude-3-opus-20240229-v1:0 \ --body "{\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\" Your task is to create a one-page website for an online learning platform.\\n\"}]}],\"anthropic_version\":\"bedrock-2023-05-31\",\"max_tokens\":2000,\"temperature\":1,\"top_k\":250,\"top_p\":0.999,\"stop_sequences\":[\"\\n\\nHuman:\"]}" \ --cli-binary-format raw-in-base64-out \ --region us-east-1 \ invoke-model-output.txt As I mentioned in my previous Claude 3 model launch posts, you need to use the new Anthropic Claude Messages API format for some Claude 3 model features, such as image processing. If you use Anthropic Claude Text Completions API and want to use Claude 3 models, you should upgrade from the Text Completions API. My colleagues, Dennis Traub and Francois Bouteruche, are building code examples for Amazon Bedrock using AWS SDKs. You can learn how to invoke Claude 3 on Amazon Bedrock to generate text or multimodal prompts for image analysis in the Amazon Bedrock documentation. Here is sample JavaScript code to send a Messages API request to generate text: // claude_opus.js - Invokes Anthropic Claude 3 Opus using the Messages API. import { BedrockRuntimeClient, InvokeModelCommand } from "@aws-sdk/client-bedrock-runtime"; const modelId = "anthropic.claude-3-opus-20240229-v1:0"; const prompt = "Hello Claude, how are you today?"; // Create a new Bedrock Runtime client instance const client = new BedrockRuntimeClient({ region: "us-east-1" }); // Prepare the payload for the model const payload = { anthropic_version: "bedrock-2023-05-31", max_tokens: 1000, messages: [{ role: "user", content: [{ type: "text", text: prompt }] }] }; // Invoke Claude with the payload and wait for the response const command = new InvokeModelCommand({ contentType: "application/json", body: JSON.stringify(payload), modelId }); const apiResponse = await client.send(command); // Decode and print Claude's response const decodedResponseBody = new TextDecoder().decode(apiResponse.body); const responseBody = JSON.parse(decodedResponseBody); const text = responseBody.content[0].text; console.log(`Response: ${text}`); Now, you can install the AWS SDK for JavaScript Runtime Client for Node.js and run claude_opus.js. npm install @aws-sdk/client-bedrock-runtime node claude_opus.js For more examples in different programming languages, check out the code examples section in the Amazon Bedrock User Guide, and learn how to use system prompts with Anthropic Claude at Community.aws. Now available Claude 3 Opus is available today in the US West (Oregon) Region; check the full Region list for future updates. Give Claude 3 Opus a try in the Amazon Bedrock console today and send feedback to AWS re:Post for Amazon Bedrock or through your usual AWS Support contacts. — Channy View the full article

AWS Community Days conferences are in full swing with AWS communities around the globe. The AWS Community Day Poland was hosted last week with more than 600 cloud enthusiasts in attendance. Community speakers Agnieszka Biernacka, Krzysztof Kąkol, and more, presented talks which captivated the audience and resulted in vibrant discussions throughout the day. My teammate, Wojtek Gawroński, was at the event and he’s already looking forward to attending again next year! Last week’s launches Here are some launches that got my attention during the previous week. Amazon CloudFront now supports Origin Access Control (OAC) for Lambda function URL origins – Now you can protect your AWS Lambda URL origins by using Amazon CloudFront Origin Access Control (OAC) to only allow access from designated CloudFront distributions. The CloudFront Developer Guide has more details on how to get started using CloudFront OAC to authenticate access to Lambda function URLs from your designated CloudFront distributions. AWS Client VPN and AWS Verified Access migration and interoperability patterns – If you’re using AWS Client VPN or a similar third-party VPN-based solution to provide secure access to your applications today, you’ll be pleased to know that you can now combine the use of AWS Client VPN and AWS Verified Access for your new or existing applications. These two announcements related to Knowledge Bases for Amazon Bedrock caught my eye: Metadata filtering to improve retrieval accuracy – With metadata filtering, you can retrieve not only semantically relevant chunks but a well-defined subset of those relevant chunks based on applied metadata filters and associated values. Custom prompts for the RetrieveAndGenerate API and configuration of the maximum number of retrieved results – These are two new features which you can now choose as query options alongside the search type to give you control over the search results. These are retrieved from the vector store and passed to the Foundation Models for generating the answer. For a full list of AWS announcements, be sure to keep an eye on the What’s New at AWS page. Other AWS news AWS open source news and updates – My colleague Ricardo writes this weekly open source newsletter in which he highlights new open source projects, tools, and demos from the AWS Community. Upcoming AWS events AWS Summits – These are free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Whether you’re in the Americas, Asia Pacific & Japan, or EMEA region, learn here about future AWS Summit events happening in your area. AWS Community Days – Join an AWS Community Day event just like the one I mentioned at the beginning of this post to participate in technical discussions, workshops, and hands-on labs led by expert AWS users and industry leaders from your area. If you’re in Kenya, or Nepal, there’s an event happening in your area this coming weekend. You can browse all upcoming in-person and virtual events here. That’s all for this week. Check back next Monday for another Weekly Roundup! – Veliswa This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS. View the full article

Knowledge Bases for Amazon Bedrock is a fully managed Retrieval-Augmented Generation (RAG) capability that allows you to connect foundation models (FMs) to internal company data sources to deliver relevant and accurate responses. We are excited to add new capabilities for building enterprise-ready RAG. Knowledge Bases now supports AWS CloudFormation and Service Quotas. View the full article

We’re just two days away from AWS Summit Sydney (April 10–11) and a month away from the AWS Summit season in Southeast Asia, starting with the AWS Summit Singapore (May 7) and the AWS Summit Bangkok (May 30). If you happen to be in Sydney, Singapore, or Bangkok around those dates, please join us. Last Week’s Launches If you haven’t read last week’s Weekly Roundup yet, Channy wrote about the AWS Chips Taste Test, a new initiative from Jeff Barr as part of April’ Fools Day. Here are some launches that caught my attention last week: New Amazon EC2 G6 instances — We announced the general availability of Amazon EC2 G6 instances powered by NVIDIA L4 Tensor Core GPUs. G6 instances can be used for a wide range of graphics-intensive and machine learning use cases. G6 instances deliver up to 2x higher performance for deep learning inference and graphics workloads compared to Amazon EC2 G4dn instances. To learn more, visit the Amazon EC2 G6 instance page. Mistral Large is now available in Amazon Bedrock — Veliswa wrote about the availability of the Mistral Large foundation model, as part of the Amazon Bedrock service. You can use Mistral Large to handle complex tasks that require substantial reasoning capabilities. In addition, Amazon Bedrock is now available in the Paris AWS Region. Amazon Aurora zero-ETL integration with Amazon Redshift now in additional Regions — Zero-ETL integration announcements were my favourite launches last year. This Zero-ETL integration simplifies the process of transferring data between the two services, allowing customers to move data between Amazon Aurora and Amazon Redshift without the need for manual Extract, Transform, and Load (ETL) processes. With this announcement, Zero-ETL integrations between Amazon Aurora and Amazon Redshift is now supported in 11 additional Regions. Announcing AWS Deadline Cloud — If you’re working in films, TV shows, commercials, games, and industrial design and handling complex rendering management for teams creating 2D and 3D visual assets, then you’ll be excited about AWS Deadline Cloud. This new managed service simplifies the deployment and management of render farms for media and entertainment workloads. AWS Clean Rooms ML is Now Generally Available — Last year, I wrote about the preview of AWS Clean Rooms ML. In that post, I elaborated a new capability of AWS Clean Rooms that helps you and your partners apply machine learning (ML) models on your collective data without copying or sharing raw data with each other. Now, AWS Clean Rooms ML is available for you to use. Knowledge Bases for Amazon Bedrock now supports private network policies for OpenSearch Serverless — Here’s exciting news for you who are building with Amazon Bedrock. Now, you can implement Retrieval-Augmented Generation (RAG) with Knowledge Bases for Amazon Bedrock using Amazon OpenSearch Serverless (OSS) collections that have a private network policy. Amazon EKS extended support for Kubernetes versions now generally available — If you’re running Kubernetes version 1.21 and higher, with this Extended Support for Kubernetes, you can stay up-to-date with the latest Kubernetes features and security improvements on Amazon EKS. AWS Lambda Adds Support for Ruby 3.3 — Coding in Ruby? Now, AWS Lambda supports Ruby 3.3 as its runtime. This update allows you to take advantage of the latest features and improvements in the Ruby language. Amazon EventBridge Console Enhancements — The Amazon EventBridge console has been updated with new features and improvements, making it easier for you to manage your event-driven applications with a better user experience. Private Access to the AWS Management Console in Commercial Regions — If you need to restrict access to personal AWS accounts from the company network, you can use AWS Management Console Private Access. With this launch, you can use AWS Management Console Private Access in all commercial AWS Regions. From community.aws The community.aws is a home for us, builders, to share our learnings with building on AWS. Here’s my Top 3 posts from last week: 14 LLMs fought 314 Street Fighter matches. Here’s who won by Banjo Obayomi Build an AI image catalogue! – Claude 3 Haiku by Alan Blockley Following the path of Architecture as Code by Christian Bonzelet Other AWS News Here are some additional news items, open-source projects, and Twitch shows that you might find interesting: Build On Generative AI – Join Tiffany and Darko to learn more about generative AI, see their demos and discuss different aspects of generative AI with the guest speakers. Streaming every Monday on Twitch, 9:00 AM US PT. AWS open source news and updates – If you’re looking for various open-source projects and tools from the AWS community, please read the AWS open-source newsletter maintained by my colleague, Ricardo. Upcoming AWS events Check your calendars and sign up for these AWS events: AWS Summits – Join free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Register in your nearest city: Amsterdam (April 9), Sydney (April 10–11), London (April 24), Singapore (May 7), Berlin (May 15–16), Seoul (May 16–17), Hong Kong (May 22), Milan (May 23), Dubai (May 29), Thailand (May 30), Stockholm (June 4), and Madrid (June 5). AWS re:Inforce – Explore cloud security in the age of generative AI at AWS re:Inforce, June 10–12 in Pennsylvania for two-and-a-half days of immersive cloud security learning designed to help drive your business initiatives. AWS Community Days – Join community-led conferences that feature technical discussions, workshops, and hands-on labs led by expert AWS users and industry leaders from around the world: Poland (April 11), Bay Area (April 12), Kenya (April 20), and Turkey (May 18). You can browse all upcoming in-person and virtual events. That’s all for this week. Check back next Monday for another Weekly Roundup! — Donnie This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS! View the full article

Mistral Large, Mistral AI’s flagship cutting-edge text generation model is now generally available on Amazon Bedrock. Mistral Large is widely known for its top-tier reasoning capabilities, specific instruction following, and multilingual translation abilities. It excels in coding and mathematical tasks and is natively fluent in English, French, Spanish, German, and Italian, with a nuanced understanding of grammar and cultural context. Mistral Large performs well on retrieval augmented generation (RAG) use cases, its 32K token context window facilitates precise information retrieval from lengthy documents. View the full article

Last month, we announced the availability of two high-performing Mistral AI models, Mistral 7B and Mixtral 8x7B on Amazon Bedrock. Mistral 7B, as the first foundation model of Mistral, supports English text generation tasks with natural coding capabilities. Mixtral 8x7B is a popular, high-quality, sparse Mixture-of-Experts (MoE) model, that is ideal for text summarization, question and answering, text classification, text completion, and code generation. Today, we’re announcing the availability of Mistral Large on Amazon Bedrock. Mistral Large is ideal for complex tasks that require substantial reasoning capabilities, or ones that are highly specialized, such as Synthetic Text Generation or Code Generation. What you need to know about Mistral Large: It’s natively fluent in English, French, Spanish, German, and Italian, with a nuanced understanding of grammar and cultural context. It has a 32K token context window allows precise information recall from large documents. Its precise instruction-following enables you to design your moderation policies – the folks at Mistral AI used it to set up the system-level moderation of their beta assistant demonstrator le Chat. Your first interaction with Large Language Models (LLMs) revolves around prompts. The art of crafting effective prompts is essential for generating desirable responses from LLMs and Mistral AI has a guide with example prompts showing different prompting capabilities. Getting started with Mistral Large To get started with Mistral Large on Bedrock, you first need to get access to the model. On the Amazon Bedrock console, select Model access, and then select Manage model access. Next, select Mistral Large, and then select Save changes. Once you have access to Mistral Large, you can use the model on Bedrock. Refresh the base models table to view the updated status. To see the complex reasoning aspect of Mistral Large in action I tried the following prompt in the Playgrounds section: Prompt Calculate the difference in payment dates between the two customers whose payment amounts are closest to each other in the given dataset: '{ "transaction_id":{"0":"T1001","1":"T1002","2":"T1003","3":"T1004","4":"T1005"}, "customer_id":{"0":"C001","1":"C002","2":"C003","3":"C002","4":"C001"}, "payment_amount":{"0":125.5,"1":89.99,"2":120.0,"3":54.3,"4":210.2}, "payment_date":{"0":"2021-10-05","1":"2021-10-06","2":"2021-10-07","3":"2021-10-05","4":"2021-10-08"}, "payment_status":{"0":"Paid","1":"Unpaid","2":"Paid","3":"Paid","4":"Pending"} }' Output To find the difference in payment dates between the two customers whose payment amounts are closest to each other, we first need to identify the two closest payment amounts and then find their respective payment dates. The payment amounts are: 125.5, 89.99, 120.0, 54.3, 210.2 The two closest payment amounts are 125.5 and 120.0. The payment date for the payment amount 125.5 is '2021-10-05' and for the payment amount 120.0 is '2021-10-07'. The difference in payment dates can be calculated as follows: Date difference = |'2021-10-07' - '2021-10-05'| = 2 days So, the difference in payment dates between the two customers whose payment amounts are closest to each other is 2 days. Earlier in this post I mentioned that Mistral Large is natively fluent in several languages, with a nuanced understanding of grammar and cultural context. I tested the model’s understanding of the French language: Prompt Lequel est le plus lourd une livre de fer ou un kilogramme de plume Output Un kilogramme de plumes est plus lourd qu'une livre de fer. Pour comprendre cela, il est important de se rappeler que : 1. Une livre (lb) est une unité de mesure de masse principalement utilisée aux États-Unis et dans d'autres systèmes de mesure impériaux, tandis qu'un kilogramme (kg) est l'unité de base de masse dans le système international d'unités (SI). 2. 1 kilogramme est approximativement égal à 2,2 livres. Donc, un kilogramme de plumes est plus lourd qu'une livre de fer, car il correspond à environ 2,2 livres de plumes. Programmatically interact with Mistral Large You can also use AWS Command Line Interface (CLI) and AWS Software Development Kit (SDK) to make various calls using Amazon Bedrock APIs. Following, is a sample code in Python that interacts with Amazon Bedrock Runtime APIs with AWS SDK. If you specify in the prompt that “You will only respond with a JSON object with the key X, Y, and Z.”, you can use JSON format output in easy downstream tasks: import boto3 import json bedrock = boto3.client(service_name="bedrock-runtime", region_name='us-east-1') prompt = """ <s>[INST]You are a summarization system that can provide summaries with associated confidence scores. In clear and concise language, provide three short summaries of the following essay, along with their confidence scores. You will only respond with a JSON object with the key Summary and Confidence. Do not provide explanations.[/INST] # Essay: The generative artificial intelligence (AI) revolution is in full swing, and customers of all sizes and across industries are taking advantage of this transformative technology to reshape their businesses. From reimagining workflows to make them more intuitive and easier to enhancing decision-making processes through rapid information synthesis, generative AI promises to redefine how we interact with machines. It’s been amazing to see the number of companies launching innovative generative AI applications on AWS using Amazon Bedrock. Siemens is integrating Amazon Bedrock into its low-code development platform Mendix to allow thousands of companies across multiple industries to create and upgrade applications with the power of generative AI. Accenture and Anthropic are collaborating with AWS to help organizations—especially those in highly-regulated industries like healthcare, public sector, banking, and insurance—responsibly adopt and scale generative AI technology with Amazon Bedrock. This collaboration will help organizations like the District of Columbia Department of Health speed innovation, improve customer service, and improve productivity, while keeping data private and secure. Amazon Pharmacy is using generative AI to fill prescriptions with speed and accuracy, making customer service faster and more helpful, and making sure that the right quantities of medications are stocked for customers. To power so many diverse applications, we recognized the need for model diversity and choice for generative AI early on. We know that different models excel in different areas, each with unique strengths tailored to specific use cases, leading us to provide customers with access to multiple state-of-the-art large language models (LLMs) and foundation models (FMs) through a unified service: Amazon Bedrock. By facilitating access to top models from Amazon, Anthropic, AI21 Labs, Cohere, Meta, Mistral AI, and Stability AI, we empower customers to experiment, evaluate, and ultimately select the model that delivers optimal performance for their needs. Announcing Mistral Large on Amazon Bedrock Today, we are excited to announce the next step on this journey with an expanded collaboration with Mistral AI. A French startup, Mistral AI has quickly established itself as a pioneering force in the generative AI landscape, known for its focus on portability, transparency, and its cost-effective design requiring fewer computational resources to run. We recently announced the availability of Mistral 7B and Mixtral 8x7B models on Amazon Bedrock, with weights that customers can inspect and modify. Today, Mistral AI is bringing its latest and most capable model, Mistral Large, to Amazon Bedrock, and is committed to making future models accessible to AWS customers. Mistral AI will also use AWS AI-optimized AWS Trainium and AWS Inferentia to build and deploy its future foundation models on Amazon Bedrock, benefitting from the price, performance, scale, and security of AWS. Along with this announcement, starting today, customers can use Amazon Bedrock in the AWS Europe (Paris) Region. At launch, customers will have access to some of the latest models from Amazon, Anthropic, Cohere, and Mistral AI, expanding their options to support various use cases from text understanding to complex reasoning. Mistral Large boasts exceptional language understanding and generation capabilities, which is ideal for complex tasks that require reasoning capabilities or ones that are highly specialized, such as synthetic text generation, code generation, Retrieval Augmented Generation (RAG), or agents. For example, customers can build AI agents capable of engaging in articulate conversations, generating nuanced content, and tackling complex reasoning tasks. The model’s strengths also extend to coding, with proficiency in code generation, review, and comments across mainstream coding languages. And Mistral Large’s exceptional multilingual performance, spanning French, German, Spanish, and Italian, in addition to English, presents a compelling opportunity for customers. By offering a model with robust multilingual support, AWS can better serve customers with diverse language needs, fostering global accessibility and inclusivity for generative AI solutions. By integrating Mistral Large into Amazon Bedrock, we can offer customers an even broader range of top-performing LLMs to choose from. No single model is optimized for every use case, and to unlock the value of generative AI, customers need access to a variety of models to discover what works best based for their business needs. We are committed to continuously introducing the best models, providing customers with access to the latest and most innovative generative AI capabilities. “We are excited to announce our collaboration with AWS to accelerate the adoption of our frontier AI technology with organizations around the world. Our mission is to make frontier AI ubiquitous, and to achieve this mission, we want to collaborate with the world’s leading cloud provider to distribute our top-tier models. We have a long and deep relationship with AWS and through strengthening this relationship today, we will be able to provide tailor-made AI to builders around the world.” – Arthur Mensch, CEO at Mistral AI. Customers appreciate choice Since we first announced Amazon Bedrock, we have been innovating at a rapid clip—adding more powerful features like agents and guardrails. And we’ve said all along that more exciting innovations, including new models will keep coming. With more model choice, customers tell us they can achieve remarkable results: “The ease of accessing different models from one API is one of the strengths of Bedrock. The model choices available have been exciting. As new models become available, our AI team is able to quickly and easily evaluate models to know if they fit our needs. The security and privacy that Bedrock provides makes it a great choice to use for our AI needs.” – Jamie Caramanica, SVP, Engineering at CS Disco. “Our top priority today is to help organizations use generative AI to support employees and enhance bots through a range of applications, such as stronger topic, sentiment, and tone detection from customer conversations, language translation, content creation and variation, knowledge optimization, answer highlighting, and auto summarization. To make it easier for them to tap into the potential of generative AI, we’re enabling our users with access to a variety of large language models, such as Genesys-developed models and multiple third-party foundational models through Amazon Bedrock, including Anthropic’s Claude, AI21 Labs’s Jurrassic-2, and Amazon Titan. Together with AWS, we’re offering customers exponential power to create differentiated experiences built around the needs of their business, while helping them prepare for the future.” – Glenn Nethercutt, CTO at Genesys. As the generative AI revolution continues to unfold, AWS is poised to shape its future, empowering customers across industries to drive innovation, streamline processes, and redefine how we interact with machines. Together with outstanding partners like Mistral AI, and with Amazon Bedrock as the foundation, our customers can build more innovative generative AI applications. Democratizing access to LLMs and FMs Amazon Bedrock is democratizing access to cutting-edge LLMs and FMs and AWS is the only cloud provider to offer the most popular and advanced FMs to customers. The collaboration with Mistral AI represents a significant milestone in this journey, further expanding Amazon Bedrock’s diverse model offerings and reinforcing our commitment to empowering customers with unparalleled choice through Amazon Bedrock. By recognizing that no single model can optimally serve every use case, AWS has paved the way for customers to unlock the full potential of generative AI. Through Amazon Bedrock, organizations can experiment with and take advantage of the unique strengths of multiple top-performing models, tailoring their solutions to specific needs, industry domains, and workloads. This unprecedented choice, combined with the robust security, privacy, and scalability of AWS, enables customers to harness the power of generative AI responsibly and with confidence, no matter their industry or regulatory constraints. """ body = json.dumps({ "prompt": prompt, "max_tokens": 512, "top_p": 0.8, "temperature": 0.5, }) modelId = "mistral.mistral-large-2402-v1:0" accept = "application/json" contentType = "application/json" response = bedrock.invoke_model( body=body, modelId=modelId, accept=accept, contentType=contentType ) print(json.loads(response.get('body').read())) You can get JSON formatted output as like: { "Summaries": [ { "Summary": "The author discusses their early experiences with programming and writing, starting with writing short stories and programming on an IBM 1401 in 9th grade. They then moved on to working with microcomputers, building their own from a Heathkit, and eventually convincing their father to buy a TRS-80 in 1980. They wrote simple games, a program to predict rocket flight trajectories, and a word processor.", "Confidence": 0.9 }, { "Summary": "The author began college as a philosophy major, but found it to be unfulfilling and switched to AI. They were inspired by a novel and a PBS documentary, as well as the potential for AI to create intelligent machines like those in the novel. Despite this excitement, they eventually realized that the traditional approach to AI was flawed and shifted their focus to Lisp.", "Confidence": 0.85 }, { "Summary": "The author briefly worked at Interleaf, where they found that their Lisp skills were highly valued. They eventually left Interleaf to return to RISD, but continued to work as a freelance Lisp hacker. While at RISD, they started painting still lives in their bedroom at night, which led to them applying to art schools and eventually attending the Accademia di Belli Arti in Florence.", "Confidence": 0.9 } ] } To learn more prompting capabilities in Mistral AI models, visit Mistral AI documentation. Now Available Mistral Large, along with other Mistral AI models (Mistral 7B and Mixtral 8x7B), is available today on Amazon Bedrock in the US East (N. Virginia), US West (Oregon), and Europe (Paris) Regions; check the full Region list for future updates. Share and learn with our generative AI community at community.aws. Give Mistral Large a try in the Amazon Bedrock console today and send feedback to AWS re:Post for Amazon Bedrock or through your usual AWS Support contacts. Read about our collaboration with Mistral AI and what it means for our customers. – Veliswa. View the full article

Knowledge Bases for Amazon Bedrock is a fully managed Retrieval-Augmented Generation (RAG) capability that allows you to connect foundation models (FMs) to internal company data sources to deliver more relevant, context-specific, and accurate responses. We are excited to announce that Knowledge Bases now supports private network policies for Amazon OpenSearch Serverless (OSS). View the full article

We are excited to announce that Knowledge Bases for Amazon Bedrock now lets you create custom prompts to have greater control over personalizing the responses generated by the Foundation Model (FM). Additionally, you can configure the number of retrieved passages, which improves accuracy by providing added context to the FM. View the full article