DataStax, the real-time AI company, announced today that Astra DB – its popular database-as-a-service (DBaaS) built on the open source Apache Cassandra® database – now supports vector search, a key capability for letting databases provide long-term memory for AI applications using large language models (LLMs) and other AI use cases.
Coming on the heels of the introduction of vector search into Cassandra, the availability of this new tool in the pay-as-you-go Astra DB service will enable developers to easily leverage the massively scalable Cassandra database for their LLM, AI assistant, and real-time generative AI projects. Goldman Sachs Research estimates that the generative AI software market could grow to $150 billion, compared to $685 billion for the global software industry.
DataStax is working closely with the Google Cloud AI/ML Center of Excellence as part of the Built with Google AI program to enable the best of Google Cloud’s generative AI offerings to enhance the capabilities and experience of customers using DataStax.
Vector search enables developers to search a database by context or meaning rather than keywords or literal values. This is done by using “embeddings,” for example Google Cloud’s API for text embedding, which can represent semantic concepts as vectors to search unstructured datasets such as text and images.
Embeddings are a powerful tool that enable search in natural language across a large corpus of data, in different formats, and extract the most relevant pieces of data.
Vector stores are required to enable extremely low latency search across databases. Altogether, embeddings, vector stores, and generative AI models like Google PaLM 2, can create powerful capabilities that dynamically combine the right information, for the right customer in their expected language. And now, because of Cassandra’s ability to search by meaning, it will play a key role in building generative AI applications.