Likewise, Venkataramani — who serves as CEO in addition to being a co-founder of Rockset — said a key aspect of adding support for vector embedding is that the vendor now enables users to manage and explore all types of data in one place .
"A single database can now store your structured data, your semi-structured data, and your vector embeddings to build rich AI applications," he said. "We're already a database that's good at storing structured and semi-structured data and combining them to build real-time applications. Now with native vector support, you can now build applications that [enable] hybrid search."
practical application
Venkataramani went on to say that one of the main use cases enabled by combining vector embeddings with structured and semi-structured data in hybrid applications is real-time personalization for e-commerce.
Every product on the website contains images and text and can be encoded as vectors. Likewise, each customer could be assigned a vector based on the set of products they viewed and purchased.
These vectors can then be combined with other data, such as which products are in stock, to filter out currently irrelevant data.
From the mix, eCommerce suppliers can discover the likelihood that customers want to buy a particular product, while also ensuring that the product being pushed out to the customer is in stock or the product is available.