At its developer conference on Thursday, Box showed off a new feature that will build Nvidia\u2019s Nemotron embedding system into the core of its product. <\/p>\n
Called Box Content Retrieval, the new feature allows agents to answer queries far more effectively by relying on the embedded metadata created by Nemotron.\u00a0<\/p>\n
Box says the upshot for users is faster, more accurate and less expensive queries. Nvidia\u2019s VP of generative AI software, Kari Briski, told TechCrunch that she expects queries to be answered four times faster, with 20% fewer errors and 90% fewer tokens used.<\/p>\n
The system will be available to all of Box\u2019s Enterprise Advance customers, rolling out early next year.<\/p>\n
\u201cThis dramatically boosts both the relevance of our search technology for agents,\u201d Box CEO Aaron Levie said. \u201cInstead of an agent having to kind of read through each document, we can send back chunks from the documents that are most relevant to the user\u2019s query or whatever the task is that the agent is doing.\u201d<\/p>\n
The feature is an implementation of Nvidia\u2019s Nemotron Embed project, which offers open-weight embedding models to improve automated retrieval systems. Major labs have often overlooked such models,<\/p>\n