Hazelcast is announcing the introduction of vector search in the latest release of its flagship product, Hazelcast Platform. The platform delivers a core architecture that combines distributed compute, in-memory data storage, intelligent integration, and vector search, all of which are key requirements for enterprise AI and critical applications.

The introduction of vector search in Hazelcast Platform enables enterprises to deploy a high-performance end-to-end pipeline to query structured and unstructured data. It offers the flexibility to generate vector data structures and embeddings from text plot summaries, delivering new efficiencies for data scientists to provide data insights.

“The integration of vector search in Hazelcast Platform provides the core functionality and foundation upon which developers can modernize business-critical applications and innovate for the AI era,” said Adrian Soars, CTO of Hazelcast. “This release furthers Hazelcast’s mission to simplify technology stacks and reduce total cost of ownership, enabling technology leaders to shift budget to AI initiatives and innovation.”

In addition to unifying multiple components in a single solution, Hazelcast Platform provides significant performance gains over most competitors, especially when factoring in vector embeddings and retrievals. In internal benchmark tests of 1 million OpenAI angular vectors, Hazelcast Platform outperforms competitors, consistently delivering single-digit millisecond latency when uploading, indexing, and searching vectors with 98% precision.

In addition to vector search, Hazelcast Platform continues to advance its capabilities, which provide greater flexibility, resilience, and performance for enterprise applications.

Jet Job Placement Control enables customers to separate the compute functionality of Hazelcast Platform nodes from the data store component to provide further flexibility and resilience for compute-intensive workloads.
Client Multi-Member Routing improves resilience, performance, and control for applications connecting to geographically dispersed clusters.

Availability and Support
Hazelcast is now introducing a 3-year, long-term support (LTS) to ensure customers can build for the long term with simplified upgrades.

Hazelcast Platform 5.5 is generally available today. The vector search integration is available as a preview in Hazelcast Platform 5.5 Enterprise Edition with projected availability for production use in Q4.