Amazon Bedrock Knowledge Bases now supports natural language querying to retrieve structured data from your data sources. With this launch, Bedrock Knowledge Bases offers an end-to-end managed workflow for customers to build custom generative AI applications that can access and incorporate contextual information from a variety of structured and unstructured data sources. Using advanced natural language processing, Bedrock Knowledge Bases can transform natural language queries into SQL queries, allowing users to retrieve data directly from the source without the need to move or preprocess the data.

Developers often face challenges integrating structured data into generative AI applications. This includes difficulties training large language models (LLMs) to convert natural language queries to SQL queries based on complex database schemas, as well as ensuring appropriate data governance and security controls are in place. Bedrock Knowledge Bases eliminates these hurdles by providing a managed natural language to SQL (NL2SQL) module. A retail analyst can now simply ask “What were my top 5 selling products last month?”, and then Bedrock Knowledge Base automatically translates that query into SQL, execute the query against the database, and return the results – or even provide a summarized narrative response. To generate accurate SQL queries, Bedrock Knowledge Base leverages database schema, previous query history, and other contextual information that are provided about the data sources.

Bedrock Knowledge Bases supports structured data retrieval from Amazon Redshift and Amazon Sagemaker Lakehouse at this time and is available in all commercial regions where Bedrock Knowledge Bases is supported. To learn more, visit here and here . For details on pricing, please refer here .

Today Amazon Web Services, Inc. (AWS) announced the general availability of Amazon SageMaker partner AI apps, a new capability that enables customers to easily discover, deploy, and use best-in-class machine learning (ML) and generative AI (GenAI) development applications from leading app providers privately and securely, all without leaving Amazon SageMaker AI so they can develop performant AI models faster.

Until today, integrating purpose-built GenAI and ML development applications that provide specialized capabilities for a variety of model development tasks, required a considerable amount of effort. Beyond the need to invest time and effort in due diligence to evaluate existing offerings, customers had to perform undifferentiated heavy lifting in deploying, managing, upgrading and scaling these applications. Furthermore, to adhere to rigorous security and compliance protocols, organizations need their data to stay within the confines of their security boundaries without needing to move their data elsewhere, for example, to a Software as a Service (SaaS) application. Finally, the resulting developer experience is often fragmented, with developers having to switch back and forth between multiple disjointed interfaces. With SageMaker partner AI apps you can quickly subscribe to a partner solution and seamlessly integrate the app with your SageMaker development environment. SageMaker partner AI apps are fully managed and run privately and securely in your SageMaker environment reducing the risk of data and model exfiltration.

At launch, you will be able to boost your team’s productivity and reduce time to market by enabling: Comet , to track, visualize, and manage experiments for AI model development; Deepchecks , to evaluate quality and compliance for AI models; Fiddler , to validate, monitor, analyze, and improve AI models in production; and, Lakera , to protect AI applications from security threats such as prompt attacks, data loss and inappropriate content.

SageMaker partner AI apps is available in all currently supported regions except Gov Cloud. To learn more please visit SageMaker partner AI app’s developer guide .
 

Amazon Kendra is an AI-powered search service enabling organizations to build intelligent search experiences and retrieval augmented generation (RAG) systems to power generative AI applications. Starting today, AWS customers can use a new index – the GenAI Index for RAG and intelligent search. With the Kendra GenAI Index, customers get high out-of-the-box search accuracy powered by the latest information retrieval technologies and semantic models.

Kendra GenAI Index supports mobility across AWS generative AI services like Amazon Bedrock Knowledge Base and Amazon Q Business , giving customers the flexibility to use their indexed content across different use cases. It is available as a managed retriever in Bedrock Knowledge Bases, enabling customers to create a Knowledge Base powered by the Kendra GenAI Index. Customers can also integrate such Knowledge Bases with other Bedrock Services like Guardrails, Prompt Flows, and Agents to build advanced generative AI applications. The GenAI Index supports connectors for 43 different data sources, enabling customers to easily ingest content from a variety of sources.

Kendra GenAI Index is available in the US East (N. Virginia) and US West (Oregon) regions.

To learn more, see Kendra GenAI Index in the Amazon Kendra Developer Guide . For pricing, please refer to Kendra pricing page .

Amazon SageMaker HyperPod announces flexible training plans, a new capability that allows you to train generative AI models within your timelines and budgets. Gain predictable model training timelines and run training workloads within your budget requirements, while continuing to benefit from features of SageMaker HyperPod such as resiliency, performance-optimized distributed training, and enhanced observability and monitoring. 

In a few quick steps, you can specify your preferred compute instances, desired amount of compute resources, duration of your workload, and preferred start date for your generative AI model training. SageMaker then helps you create the most cost-efficient training plans, reducing time to train your model by weeks. Once you create and purchase your training plans, SageMaker automatically provisions the infrastructure and runs the training workloads on these compute resources without requiring any manual intervention. SageMaker also automatically takes care of pausing and resuming training between gaps in compute availability, as the plan switches from one capacity block to another. If you wish to remove all the heavy lifting of infrastructure management, you can also create and run training plans using SageMaker fully managed training jobs .  

SageMaker HyperPod flexible training plans are available in the US East (N. Virginia), US East (Ohio), and US West (Oregon) AWS Regions. To learn more, visit: SageMaker HyperPod , documentation , and the announcement blog . 

Amazon Bedrock Marketplace provides generative AI developers access to over 100 publicly available and proprietary foundation models (FMs), in addition to Amazon Bedrock’s industry-leading, serverless models. Customers deploy these models onto SageMaker endpoints where they can select their desired number of instances and instance types. Amazon Bedrock Marketplace models can be accessed through Bedrock’s unified APIs, and models which are compatible with Bedrock’s Converse APIs can be used with Amazon Bedrock’s tools such as Agents, Knowledge Bases, and Guardrails.

Amazon Bedrock Marketplace empowers generative AI developers to rapidly test and incorporate a diverse array of emerging, popular, and leading FMs of various types and sizes. Customers can choose from a variety of models tailored to their unique requirements, which can help accelerate the time-to-market, improve the accuracy, or reduce the cost of their generative AI workflows. For example, customers can incorporate models highly-specialized for finance or healthcare, or language translation models for Asian languages, all from a single place.

Amazon Bedrock Marketplace is supported in US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt), Europe (Ireland), Europe (London), Europe (Paris), and South America (São Paulo).

For more information, please refer to Amazon Bedrock Marketplace’s announcement blog or documentation .

Amazon announces a five-year commitment of cloud technology and technical support for organizations creating digital learning solutions that expand access for underserved learners worldwide through the AWS Education Equity Initiative. While the use of educational technologies continues to rise, many organizations lack access to cloud computing and AI resources needed to accelerate and scale their work to reach more learners in need.

Amazon is committing up to $100 million in AWS credits and technical advising to support socially-minded organizations build and scale learning solutions that utilize cloud and AI technologies. This will help reduce initial financial barriers and provide guidance on building and scaling AI-powered education solutions using AWS technologies.

Eligible recipients, including socially-minded edtechs, social enterprises, non-profits, governments, and corporate social responsibility teams, must demonstrate how their solution will benefit students from underserved communities. The initiative is now accepting applications.

To learn more and how to apply, visit the AWS Education Equity Initiative page .

Organizations are increasingly using applications with multimodal data to drive business value, improve decision-making, and enhance customer experiences. Amazon Bedrock Guardrails now supports multimodal toxicity detection for image content, enabling organizations to apply content filters to images. This new capability with Guardrails, now in public preview, removes the heavy lifting required by customers to build their own safeguards for image data or spend cycles with manual evaluation that can be error-prone and tedious.

Bedrock Guardrails helps customers build and scale their generative AI applications responsibly for a wide range of use cases across industry verticals including healthcare, manufacturing, financial services, media and advertising, transportation, marketing, education, and much more. With this new capability, Amazon Bedrock Guardrails offers a comprehensive solution, enabling the detection and filtration of undesirable and potentially harmful image content while retaining safe and relevant visuals. Customers can now use content filters for both text and image data in a single solution with configurable thresholds to detect and filter undesirable content across categories such as hate, insults, sexual, and violence, and build generative AI applications based on their responsible AI policies.

This new capability in preview is available with all foundation models (FMs) on Amazon Bedrock that support images including fine-tuned FMs in 11 AWS regions globally: US East (N. Virginia), US East (Ohio), US West (Oregon), Europe (Ireland), Europe (Frankfurt), Europe (London), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Tokyo), and Asia Pacific (Mumbai), and AWS GovCloud (US-West).

To learn more, visit the Amazon Bedrock Guardrails product page , read the News blog , and documentation .

Amazon SageMaker HyperPod now provides you with centralized governance across all generative AI development tasks, such as training and inference. You have full visibility and control over compute resource allocation, ensuring the most critical tasks are prioritized and maximizing compute resource utilization, reducing model development costs by up to 40%.

With HyperPod task governance, administrators can more easily define priorities for different tasks and set up limits for how many compute resources each team can use. At any given time, administrators can also monitor and audit the tasks that are running or waiting for compute resources through a visual dashboard. When data scientists create their tasks, HyperPod automatically runs them, adhering to the defined compute resource limits and priorities. For example, when training for a high-priority model needs to be completed as soon as possible but all compute resources are in use, HyperPod frees up resources from lower-priority tasks to support the training. HyperPod pauses the low-priority task, saves the checkpoint, and reallocates the freed-up compute resources. The preempted low-priority task will resume from the last saved checkpoint as resources become available again. And when a team is not fully using the resource limits the administrator has set up, HyperPod use those idle resources to accelerate another team’s tasks. Additionally, HyperPod is now integrated with Amazon SageMaker Studio , bringing task governance and other HyperPod capabilities into the Studio environment. Data scientists can now seamlessly interact with HyperPod clusters directly from Studio, allowing them to develop, submit, and monitor machine learning (ML) jobs on powerful accelerator-backed clusters.

Task governance for HyperPod is available in all AWS Regions where HyperPod is available: US East (N. Virginia), US West (N. California), US West (Oregon), Asia Pacific (Mumbai), Asia Pacific (Singapore), Asia Pacific (Sydney), and Asia Pacific (Tokyo), Europe (Frankfurt), Europe (Ireland), Europe (London), Europe (Stockholm), and South America (São Paulo).

To learn more, visit SageMaker HyperPod webpage , AWS News Blog , and SageMaker AI documentation .

Today, AWS announces that Amazon Bedrock now supports prompt caching. Prompt caching is a new capability that can reduce costs by up to 90% and latency by up to 85% for supported models by caching frequently used prompts across multiple API calls. It allows you to cache repetitive inputs and avoid reprocessing context, such as long system prompts and common examples that help guide the model’s response. When cache is used, fewer computing resources are needed to generate output. As a result, not only can we process your request faster, but we can also pass along the cost savings from using fewer resources.

Amazon Bedrock is a fully managed service that offers a choice of high-performing FMs from leading AI companies via a single API. Amazon Bedrock also provides a broad set of capabilities customers need to build generative AI applications with security, privacy, and responsible AI capabilities built in. These capabilities help you build tailored applications for multiple use cases across different industries, helping organizations unlock sustained growth from generative AI while providing tools to build customer trust and data governance.

Prompt caching is now available on Claude 3.5 Haiku and Claude 3.5 Sonnet v2 in US West (Oregon) and US East (N. Virginia) via cross-region inference, and Nova Micro, Nova Lite, and Nova Pro models in US East (N. Virginia). At launch, only a select number of customers will have access to this feature. To learn more about participating in the preview, see this page . To learn more about prompt caching, see our documentation and blog .

Today, AWS announces the availability of new AWS AI Service Cards for Amazon Nova Reel; Amazon Canvas; Amazon Nova Micro, Lite, and Pro; Amazon Titan Image Generator; and Amazon Titan Text Embeddings. AI Service Cards are a resource designed to enhance transparency by providing customers with a single place to find information on the intended use cases and limitations, responsible AI design choices, and performance optimization best practices for AWS AI services.

AWS AI Service Cards are part of our comprehensive development process to build services in a responsible way. They focus on key aspects of AI development and deployment, including fairness, explainability, privacy and security, safety, controllability, veracity and robustness, governance, and transparency. By offering these cards, AWS aims to empower customers with the knowledge they need to make informed decisions about using AI services in their applications and workflows. Our AI Service Cards will continue to evolve and expand as we engage with our customers and the broader community to gather feedback and continually iterate on our approach.

For more information, see the AI Service Cards for

• Amazon Nova Reel 
• Amazon Nova Canvas  
• Amazon Nova Micro, Lite and Pro  
• Amazon Titan Image Generator  
• Amazon Titan Text Embeddings  

To learn more about AI Service Cards, as well as our broader approach to building AI in a responsible way, see our Responsible AI webpage .