NVIDIA releases Auto Ontology
The story so far
NVIDIA has released Auto Ontology, a semantic layer framework based on enterprise metadata, allowing AI agents to write SQL through certified business definitions. The framework uses nvidia/nemotron-3-nano-30b-a3b as the default LLM and supports deployment via Docker Compose or Kubernetes. Performance tests show a 90% reduction in ontology creation time, but the accuracy of text-to-SQL has not been disclosed.
AI-written from the reports · Updated 16 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- MarkTechPostNVIDIA Releases Auto Ontology: An Open Semantic Layer That Grounds AI Agent SQL
NVIDIA releases Auto Ontology, a semantic layer framework based on enterprise metadata, allowing AI agents to write SQL through certified business definitions. The default LLM is nvidia/nemotron-3-nano-30b-a3b, supporting Docker Compose or Kubernetes deployment. Performance tests show a 90% reduction in ontology creation time, but the text-to-SQL accuracy has not been announced.