DataStax furthers the enhancement of AI applications with vector search availability
DataStax, the real-time AI company, is announcing that its Database-as-a-Service, Astra DB, now supports vector search—representing a leap by the company into enhanced support for AI workloads, including those using LLMs.
With AI’s surge in popularity, organizations are seeking to leverage this technology to propel positive outcomes. These AI projects, however, require extensive support to begin reaping any sort of beneficial return, according to the company.
Enter vector search: a search method that uses context and meaning—as opposed to keywords or literal values—that inspires low latency search and powerful information access. Vector search utilizes embeddings—a representation of semantic concepts as vectors—to search unstructured datasets.
Embeddings within vector search allow natural language to be the backbone of a developer’s search experience, even if the mass of enterprise data is quantifiably large and differing in format.
Following the introduction of vector search to DataStax’s Cassandra, developers can combine the powers of embeddings, vector stores, and generative AI models to surface relevant information delivered in natural language. Cassandra’s capability to search by meaning further inspires new possibilities when producing generative AI apps.
“Vector search is a key part of the new AI stack; every developer building for AI needs to make their data easily queryable by AI agents,” said Ed Anuff, CPO at DataStax. “Unlike many other vector databases, Astra DB is not only built for global scale and availability but supports the most stringent enterprise-level requirements for managing sensitive data including HIPAA, PCI, and PII regulations. It’s therefore an ideal option for both startups and enterprises that manage sensitive user information and want to build impactful generative AI applications.”
DataStax’s partnership with Google Cloud additionally offers a wealth of opportunity for Apache Cassandra and Astra DB as the chosen database for AI applications. These innovations include CassIO, an open source library for Cassandra integration with popular generative AI SDKs; a Google Cloud BigQuery integration for seamless imports and exports to BigQuery; and Google Cloud DataFlow integration for feeding real-time data to and from Cassanra.
“Our customers consistently ask us for ways to tightly integrate data and AI capabilities,” said Stephen Orban, VP of migrations and GenAI ecosystem at Google Cloud. “By integrating Google Cloud’s generative AI capabilities into Astra DB, DataStax is adding natural language capabilities into a suite of already powerful database capabilities and giving customers a complete and unified data and AI solutions approach.”
Vector search is now generally available as a non-production use public preview in Astra DB. The tool will be first available exclusively on Google Cloud, with later availability on other public clouds to come.
To learn more about DataStax’s latest vector search capabilities, please visit www.datastax.com.