DataStax has announced the general availability of its Data API, a one-stop API for GenAI, that provides all the data and a complete stack for production GenAI and retrieval augmented generation (RAG) applications with high relevancy and low latency.
Also debuting is a completely updated developer experience for DataStax Astra DB, the best vector database for building production-level AI applications.
The new vector Data API and experience makes the proven, petabyte-scale power of Apache Cassandra available to JavaScript, Python, or full-stack application developers in a more intuitive experience for AI development.
It is specifically designed for ease of use, while offering up to 20 per cent higher relevancy, 9x higher throughput, and up to 74x faster response times than Pinecone, another vector database, by using the JVector search engine.
It introduces an intuitive dashboard, efficient data loading and exploration tools, and seamless integration with leading AI and machine learning (ML) frameworks.
“The seamless user experience, native language client support, and effortless integration with GenAI ecosystems empower us to navigate the complexities of vector search with unprecedented simplicity,” said Mark Hauptman, chief executive officer, ReelStar. “With Astra DB, we’re not just shortening the development journey; we’re accelerating innovation and efficiency in our mission to redefine the landscape of video sharing with GenAI.”
Developers can use the Data API for an out-of-the-box AI ecosystem that simplifies integrations with major GenAI ecosystem leaders like LangChain, LLamaIndex, OpenAI, Vercel, Google Vertex AI, Amazon Bedrock, GitHub Copilot, Azure, and all major platforms while supporting the breadth of security and compliance standards. Any developer can now support advanced RAG techniques such as FLARE and ReAct that must synthesize multiple responses, while still hitting latency SLAs.
“Astra DB’s Data API has been a game-changer for us to build production RAG applications that use enterprise data,” said Rahul Singh, chief executive officer, Anant.US. “The ease of use of the Astra DB experience, coupled with the capability to instantly query real-time data updates for both vector and non-vector data, is essential for production GenAI applications on real-life data workloads. This has significantly expedited our production processes.”
“The Astra DB vector experience advanced GenAI development at Aviso,” said Santosh Maddila, principal data scientist, Aviso AI. “Its user-friendly interface, language clients, smooth ecosystem integration, and flexible API have streamlined our operations, providing exceptional ease of use. Astra DB isn’t just a tool; it’s an empowering force for developers to fully leverage Gen AI’s potential. The outstanding support from product and engineering teams has been instrumental in maximising the benefits of Astra DB, ensuring a smooth and efficient experience throughout our development journey.”
“Astra DB is the backbone of our travel app at iWander, driving personalised audio guides through Gen AI,” said Antoine Nigond, chief technology officer, iWander. “Initially, we leveraged it for efficient storage using its Data API, streamlining user experience by retrieving cached guides for similar requests. As we develop our product further, we will integrate vector search to elevate recommendations based on user preferences and feedback. As a Python-centric team, we appreciate Astra DB’s user-friendly API for its seamless integration into our innovative application.”
“Astra DB is ideal for JavaScript and Python developers, simplifying vector search and large-scale data management, putting the power of Apache Cassandra behind a user-friendly but powerful API,” said Ed Anuff, chief product officer, DataStax. “This release redefines how software engineers build GenAI applications, offering a streamlined interface that simplifies and accelerates the development process for AI engineers.”
