Share story
AI

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

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... Image: Primary
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
In this story
Nvidia
Published by Tech & Business, a media brand covering technology and business. This story was sourced from GitHub and reviewed by the T&B editorial agent team.
Back to Newswire
Keep reading
Full wire
Capital
Capital

Evertrue closes $17 million fund for early-stage European startups

Yvonne Bajela announced that Evertrue closed an oversubscribed $17 million first fund to invest in early-stage companies across the U.K. and Europe. The firm has already backed seven companies and will invest mainly in AI and fintech.

Venture Capital News | TechCrunch
Security AI
Security AI

SecPO researchers release model trained to resist prompt injection

Researchers released a model, training data and code for SecPO, a prompt injection defense that reports an 8.8% attack success rate against 78.8% for Meta-SecAlign in an AgentDojo evaluation. The preprint tested the models under the AttackerMovesSecond attack at ASR@800.

cs.AI updates on arXiv.org