Elastic Delivers GPU Infrastructure to Self-Managed Elasticsearch Customers via Cloud Connect

Modern semantic search relies on vector embeddings for high-quality results. Now available in Elasticsearch 9.3, EIS on Cloud Connect allows self-managed customers to seamlessly leverage GPU-based embedding and reranking models, including leading Jina models, without the operational overhead of managing infrastructure. This enables teams to implement powerful semantic search capabilities quickly and efficiently. Self-managed clusters can keep their existing architecture and data in place while securely offloading embedding generation and search inference to Elastic Cloud’s managed GPU fleet.

“With Elastic Inference Service via Cloud Connect, we’re making it easier for self-managed customers to adopt semantic search without taking on the complexity of GPU infrastructure,” said Steve Kearns, general manager, Search at Elastic. “With a single setup, self-managed customers can access a range of cloud services from automated diagnostics to fast AI inference, all while keeping their data on-premises.”

Availability

EIS via Cloud Connect is available immediately for Elastic Enterprise self-managed customers on Elastic Stack 9.3. To start a trial, create an Elastic Cloud account here.

Additional Resources

• Blog: Skip MLOps: Managed cloud inference for self-managed Elasticsearch with EIS via Cloud Connect
• Guide to Configuring Cloud Connect

About Elastic

Elastic (NYSE: ESTC), the Search AI Company, integrates its deep expertise in search technology with artificial intelligence to help everyone transform all of their data into answers, actions, and outcomes. Elastic's Search AI Platform — the foundation for its search, observability, and security solutions — is used by thousands of companies, including more than 50% of the Fortune 500. Learn more at elastic.co.

Elastic and associated marks are trademarks or registered trademarks of elasticsearch BV and its subsidiaries. All other company and product names may be trademarks of their respective owners.

View source version on businesswire.com: https://www.businesswire.com/news/home/20260202349548/en/