1 min read

DataStax Launches Astra Vectorize, Simplifying Embedding Generation for Lightning-fast GenAI Application Development, with Native Microsoft Azure AI and OpenAI Integrations

Automatically Generates Embeddings with No Need to Learn and Understand Embedding APIs; Enables Companies to Easily Index Unstructured Data for GenAI Use Cases

DataStax, the generative AI data company, today announced the launch of Astra Vectorize, a new feature that performs embedding generations on the server-side. The Astra Vectorize launch includes new integrations with OpenAI and Microsoft Azure OpenAI Service to accelerate and simplify embedding generation for developers. These integrations allow organizations to compare different embedding models with just a couple of clicks, saving hours and days of development time.

Astra Vectorize is an addition to the Astra Data API that will allow users to provide raw, unstructured data—like a piece of text or an image—as a part of an insert, update, or vector search operation, and the vector embedding for that data will be automatically generated by Astra DB. With this functionality, users get an improved developer experience by abstracting the complexity of embedding models from the application code, so that they can focus on the business logic of the application, rather than integrations with external systems.

“One of the frequent questions we hear from developers is around how to generate embeddings in a more simplified and cost-effective way. It’s clearly a pain point,” said Ed Anuff, chief product officer, DataStax. “With Astra Vectorize, the process is significantly simplified because embedding generation is happening at the database layer–where indexing has always traditionally occurred–leaving developers free to focus on actual application logic, rather than the intricacies of vector embeddings.”

The Astra Vectorize native integration with Azure OpenAI provides customers with the security capabilities of Microsoft Azure while running the same models as OpenAI. Azure OpenAI offers private networking, regional availability, and responsible AI content filtering. Astra Vectorize also integrates directly with OpenAI, providing out-of-the-box embedding generation services for both platforms.

“Vectorize represents the latest milestone in our partnership with DataStax, building on a longstanding relationship and multiple Microsoft and Azure integrations like Marketplace, Security, Fabric/PowerQuery, and Semantic Kernel,” Asha Sharma, CVP, Product, Azure AI at Microsoft. “By simplifying the integration of Azure OpenAI Service into the DataStax RAG architecture, Vectorize streamlines embedding generation, reaffirming our joint commitment to empowering developers with advanced AI capabilities.”

“Since beginning our testing with Vectorize, we’ve been impressed with the results,” said Ivan Koval, CEO, TechMove AS. “In just a short time, we’ve successfully created collections, loaded datasets, and executed queries, all yielding highly relevant results. This efficiency is promising for streamlining our processes and enhancing our overall workflow.”

Leave a Reply