Turbopuffer, a serverless vector database, is transitioning from a vector-index-centric architecture to a generalized search database with a new storage engine. The company is moving the ANN vector index from primary to secondary status to support diverse query plans at greater scale, evolving beyond its original specialized use case.
Turbopuffer, a serverless vector database company, is fundamentally redesigning its storage architecture in version 3, moving from a vector index-centric design to a generalized search database. The shift demotes the ANN vector index from primary to secondary status, enabling support for more query plans and greater scale while maintaining backward compatibility with existing features like attribute filtering and full-text search.