DataStax, a pioneer in generative AI data solutions, has introduced Astra Vectorize, a new tool that streamlines embedding creation directly on the server side. This release features new connections with OpenAI and Microsoft Azure OpenAI Service, which considerably accelerate and simplify the embedding creation process for developers. These interfaces allow organisations to swiftly compare various embedding approaches, saving significant development effort.
Astra Vectorize is an addition to the Astra Data API that allows users to send raw, unstructured data—such as text or images—as part of an insert, update, or vector search operation. Astra DB automatically generates vector embeddings for this data. This feature separates the complexity of embedding models from application code, allowing developers to concentrate on the business logic of their applications rather than interfaces with other systems.
With just a single line of code, Astra Vectorize makes it easy to use your data with generative AI, from generating your vectors, storing and indexing them, and them using them for search at lightning speed ✨https://t.co/CZmwRCMTto#MSBuild #GenAI #RAGApplications
— DataStax (@DataStax) May 22, 2024
“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 at 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.”
Seamless Integration with Microsoft Azure AI and OpenAI
The Astra Vectorize connection with Azure OpenAI offers users the security and dependability of Microsoft Azure while running the same models as OpenAI. Azure OpenAI supports private networking, regional availability, and responsible AI content screening. Furthermore, Astra Vectorize works directly with OpenAI, offering out-of-the-box embedding creation 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,” said 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.”
Early Success and Future Potential
Early adopters of Astra Vectorize have already seen promising results. “Since beginning our testing with Vectorize, we’ve been impressed with the results,” said Ivan Koval, CEO of 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.”
Astra Vectorize marks a significant advancement for GenAI developers in managing and utilizing unstructured data within their applications. It revolutionizes the development process, allowing developers to streamline their workflows and concentrate on creating cutting-edge AI solutions. Embrace the future of GenAI development with Astra Vectorize.
DataStax has integrated Astra Vectorize into the Data API, ensuring seamless use in both new and existing applications built with Astra DB. To illustrate its simplicity, let’s compare code examples.
First, is the code for inserting a record without Astra Vectorize, using the TypeScript client:
In this example, the application needs to call an embedding model to generate a vector from the text and then explicitly provide this vector to the database during the insert operation.
With Astra Vectorize, the process is much simpler:
A single line of code! There’s no need to understand the intricacies of embeddings—simply choose your preferred embedding service and let Astra Vectorize handle the rest. This powerful tool not only simplifies your workflow but also enhances the overall performance and scalability of your GenAI projects.
Astra Vectorize can similarly be used for search queries, further streamlining your development process.
By integrating seamlessly with leading AI platforms like Azure AI and OpenAI, DataStax continues to demonstrate its commitment to enhancing developer experiences and driving innovation in the generative AI space.