domains / families / data / nvidia-ontology-query

nvidia-ontology-query

separate

Query Auto Ontology and validate generated SQL, rows, and answers. Use for MCP or REST access, readiness, authentication, conversations, and grounded questions.

When to use

• Query the current Auto Ontology implementation from an agent without prescribing a harness, SDK, or LangGraph template. Typed workflow artifacts, statuses, gates, and handoffs are in [runtime-contract.yaml](assets/runtime-contract.yaml).

When not to use

• This skill reads and validates answers. It does not expose FastAPI directly, write semantic definitions, publish governed results, or provide a raw-schema browser. Hand mutations and publication to `nvidia-ontology-management`.

Skill page

Source