Hazelcast adds vector search
Hazelcast has made sure it keeps its platform progression evolving in line with current major trends and now introduced vector search.
As TechTarget reminds us, vector search (sometimes referred to as vector similarity search), is a technique that uses vectors — numerical representations of data — as the basis to conduct searches and identify relevance.
“A vector, in the context of a vector search, is defined as a set of numbers mathematically computed and designed to represent data across multiple dimensions. The data that a vector represents can be text, an image or audio. So, instead of a keyword search executed with, for example, traditional search engine technology, the search is done on the vectors, or numbers, to resolve queries,” writes Sean Michael Kerner.
in the latest release of its Hazelcast Platform, a core architecture combines distributed compute, in-memory data storage, integration and vector search.
The company suggests that the introduction of vector search in Hazelcast Platform enables users to deploy a end-to-end pipeline to query structured and unstructured data with the flexibility to generate vector data structures and embeddings from text plot summaries.
In addition to unifying multiple components, the Hazelcast Platform is said to work well when factoring in vector embeddings and retrievals.
In internal benchmark tests of 1 million OpenAI angular vectors, Hazelcast Platform delivers single-digit millisecond latency when uploading, indexing and searching vectors with 98% precision.
“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 latest 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.”
While applicable to all industries, vector search can immediately benefit transaction authorisation applications.
For example, in financial use cases such as know-your-customer (KYC) and anti-money laundering (AML), vector search can augment and expedite the verification process with semantic search across text, imagery and other sources to improve the accuracy and speed of determining whether a transaction is legitimate or fraudulent.
In addition to vector search, Hazelcast Platform also features ‘Jet Job Placement Control’ to enable users to separate the compute functionality of Hazelcast Platform nodes from the data store component to provide further flexibility and resilience for compute-intensive workloads. Also here we find Client Multi-Member Routing to improve resilience, performance and control for applications connecting to geographically dispersed clusters.