Introducing the next generation of Amazon OpenSearch Serverless for building agent AI applications

Applications of AI


polly's voice

Today, we are announcing the next generation of Amazon OpenSearch Serverless, a fully managed search and vector engine designed for customers building AI agents. The next generation of OpenSearch Serverless can scale from zero requests per second to thousands of requests per second and back to zero when idle, delivering up to 60% cost savings compared to the cost of an OpenSearch Service cluster provisioned to peak capacity.

The next generation of OpenSearch Serverless creates resources in seconds and scales capacity up to 20x faster than previous generations. With instant resource creation and native integration with AI development platforms like Vercel and Kiro, you can deploy production-ready search and vector backends for your AI agents in minutes without managing infrastructure.

The next generation of OpenSearch Serverless is now live

Choose below to get started with the next generation of OpenSearch Serverless. Creating a collection in serverless Amazon OpenSearch Service console menu.

Create NextGen collections with instant autoscaling and zero scale for cost optimization. At release, only full-text and vector searches for collection types are supported. If you want to use your existing OpenSearch serverless infrastructure, switch to classic.

choose fast creationthe fastest way to create collections. No configuration required. A security policy matching the default settings is automatically applied. Some configuration options can be changed later.

when choosing Creating a collectionOpenSearch Serverless provisions resources in seconds.

You can also create OpenSearch serverless collections using the AWS Command Line Interface (AWS CLI) or AWS SDKs. The following is a sample CLI command to create a collection group.

aws opensearchserverless create-collection-group \
    --name channy-nextgen-group \
    --standby-replicas ENABLED \
    --generation NEXTGEN \
    --description "My NextGen collection group" \
    --capacity-limits '{
        "maxIndexingCapacityInOCU": 10,
        "maxSearchCapacityInOCU": 10,
        "minIndexingCapacityInOCU": 0,
        "minSearchCapacityInOCU": 0
    }' \
    --region "us-east-1"

You can now create collections that inherit generations from their parent collection group. Supported collection types: SEARCH and VECTORSEARCH.

aws opensearchserverless create-collection \
    --name channy-nextgen-collection \
    --type SEARCH \
    --collection-group-name channy-nextgen-group \
    --standby-replicas ENABLED \
    --description "My collection in NextGen group" \
    --region "us-east-1"

For more information about managing the next generation of OpenSearch Serverless, see the Amazon OpenSearch Serverless documentation.

Build agents faster with OpenSearch Serverless

To support building production-ready agent applications with Vercel, you can now create new OpenSearch collections or connect to existing OpenSearch Serverless collections within the Vercel console. Create a search backend in seconds and add functionality on demand as your application grows. For more information, please visit AWS on Vercel.

Claude Code, Cursor, and Kiro help you go from idea to working prototype in minutes. OpenSearch Agent Skills provides a repository of skills that bring OpenSearch intelligence directly to agents. Each skill encapsulates domain knowledge, best practices, and multi-step execution logic for a specific workflow, so agents not only get results, but also understand how those results were achieved. You can also use Kiro Powers’ OpenSearch Launchpad to accelerate your search applications with guided end-to-end architectural planning.

currently available

The next generation of Amazon OpenSearch Serverless is now generally available and available in all AWS commercial regions where Amazon OpenSearch Serverless is currently available.

With the next generation of OpenSearch Serverless, you pay for the compute you use in OpenSearch Compute Units (OCUs) for indexing, search, and GPU acceleration. Storage is charged separately per GB per month. For more information, see Amazon OpenSearch Service Pricing.

Try it out and send feedback to AWS re:Post for Amazon OpenSearch Service or through your regular AWS Support contact.

chaney





Source link