Oracle and NVIDIA are working together to accelerate the creation of vector embeddings and vector indexes—compute-intensive portions of AI Vector Search workloads in Oracle Database 23ai—using NVIDIA GPUs and NVIDIA cuVS.
Organizations can enable vector embedding through bulk vectorization of large volumes of input data such as text, images, and videos, as well as the fast creation and maintenance of vector indexes. With NVIDIA-accelerated AI Vector Search, Oracle Database customers can significantly improve the performance of their AI pipelines to help support high-volume AI vector workloads.
DeweyVision provides advanced computer vision and artificial intelligence capabilities to turn media into data, making it accessible, searchable, discoverable, retrievable, and actionable. DeweyVision uses Oracle Database 23ai on Oracle Autonomous Database for its AI-powered, no-code warehousing tools. These tools enable production professionals to connect their workflows and edit video footage quickly by cataloging footage in minutes and providing intuitive search capabilities.
“Oracle Database 23ai with AI Vector Search can significantly increase Dewey’s search performance while increasing the scalability of the DeweyVision platform,” said Majid Bemanian, CEO, DeweyVision. “Using NVIDIA GPUs to create the vector embeddings that we load into Oracle Database accelerates the speed at which we can ingest new data, while Autonomous Database and the converged capabilities of Oracle Database 23ai will help reduce our operational costs as we grow and open new opportunities. We believe that the combination of DeweyVision, Oracle Database 23ai, and NVIDIA GPUs running in OCI will help us achieve our goal of becoming Hollywood’s data warehouse.”
Read the full press release here: https://www.oracle.com/news/announcement/oracle-and-nvidia-collaborate-to-help-enterprises-accelerate-agentic-ai-inference-2025-03-18/