# Nvidia offers open library to ground AI database queries in business definitions

_Published Tuesday, November 3, 2026 at 4:06 AM EST · AI · Latest · Tier 2 — Notable_

![Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for L... — Primary](https://opengraph.githubassets.com/9e96bcc40a9a2ec571523729f84511b81f6550b19ac09cdf0a8da91f07e2589c/NVIDIA/auto-ontology)

Nvidia's Auto Ontology library provides enterprise AI agents with business definitions, data relationships and provenance through an API, command-line interface and Model Context Protocol server. The Apache 2.0 software builds this context from enterprise metadata and checks generated queries against certified definitions and data lineage.

The library supports natural-language database queries using Nvidia NIM inference endpoints and can run locally with Docker Compose or on Kubernetes. Database credentials added through its interface are stored unencrypted in Postgres unless HashiCorp Vault is configured.

## Sources

- [GitHub](https://github.com/NVIDIA/auto-ontology)

---
Canonical: https://techandbusiness.org/newswire/3eIpAkxLp1LT-7RAbrydKK
Published: 2026-11-03T09:06:53.635Z
Story chronology: 2026-11-03T07:04:50.000Z
Retrieved: 2026-11-03T11:30:37.129Z
Publisher: Tech & Business (techandbusiness.org)