NVIDIA Releases Auto Ontology: An Open Semantic Layer That Grounds AI Agent SQL

NVIDIA has released Auto Ontology, an open library published under the Apache 2.0 license. NVIDIA Auto Ontology is a semantic layer framework that constructs a context layer from enterprise metadata. Agents then use that layer to write SQL against certified business definitions. As the repository states plainly: a fast revenue answer is worthless if the number is wrong.

TL;DR

• Library: The default LLM is nvidia/nemotron-3-nano-30b-a3b, paired with Nemotron embedding and reranking models.
• Runs on: Docker Compose for a local stack, or Kubernetes via Helm. Inference uses hosted NVIDIA NIM endpoints or self-hosted NIMs.
• Performance: Strong engineering, but thin public evidence.
• Best case: Ontology creation time cut by 90% in NVIDIA's own testing (self-reported).
• Worst case: Zero published text-to-SQL accuracy scores. The evaluation repository ships a harness, not results.
• Bottom line: An open, MCP-ready context layer that any agent harness can query—but you must run the benchmarks yourself to trust it.

What Is NVIDIA Auto Ontology?

It is a context layer that sits between an agent and the data warehouse. It tells the agent where data lives and what that data means, grounding generated SQL in certified business definitions rather than raw table and column names.

Note: The original source content was truncated at this point. The sections above reflect all available material. Additional sections—such as architecture details, deployment guidance, and evaluation results—should be added once the full article is available.

via MarkTechPost