QDRANT launched QDrant Cloud Inference, managed service that allows developers to generate, store and index text and insert images in QDrant cloud. The service that uses integrated models in the managed vector search engine is designed to simplify construction applications with multimodal search, search-visual generation and hybrid search, according to the company.
Announced on July 15, QDRANT Cloud Inference is managed by a vector database offering multimodal inference and the use of separate models for inserting images and text, natively integrated into the QDrant cloud. Service dense, thin and video insert with vector search in one managed environment. Users can generate, store and insert index into a single API call, turn unstructured text and images into search vectors in one environment, QDrant said.
Direct integration of the model’s inference into QDRANT cloud removes the need for a separate inference infrastructure, manual piping and transmission of reducing data, simplifying workflows, accelerating development cycles and eliminating unnecessary network hops for developers. “Traditionally, the insertion of generation and vector search has been elaborated into developers’ jobs,” said André Zayarni, CEO and co -founder of QDART. “With the cloud inference QDRANT it’s the only tool: one call of API with optimal resources for each component.”