Auto Ontology (GitHub Repo)
NVIDIA's Auto Ontology framework enables AI agents to query enterprise data with semantic precision by building a knowledge graph over relational metadata.
Deep dive
- Automatically discovers schemas and maps business terms across databases.
- Implements a semantic catalog using Postgres and pgvector.
- Provides tools for users to certify definitions and SQL expressions.
- Exposes functionality via MCP for integration with Claude Desktop or Cursor.
- Leverages NVIDIA NIM endpoints (Nemotron models) for reasoning and embedding tasks.
- Enforces authentication via Better Auth and provides a web UI for auditing SQL generation.
Decoder
- Ontology: A formal representation of knowledge as a set of concepts within a domain and the relationships between those concepts.
- MCP (Model Context Protocol): An open standard that allows AI assistants to connect to data sources, tools, and systems in a standardized way.
- NIM (NVIDIA Inference Microservice): A set of optimized containers and APIs for running AI models across various hardware.
Original article
Auto Ontology
Agents can retrieve documents and query databases, but reliability gates agentic analytics: a revenue metric answered faster is worth nothing if the number is wrong. Agents need a context layer that tells them where data lives, what it means, whether to use it, how to use it, where it came from, and what is similar. NVIDIA Auto Ontology is an open library that builds that layer from enterprise metadata, reconciles definitions across systems, and exposes it to any agent harness through MCP, CLI, and API. It complements the semantic models customers already own.
It enables developers to:
- Discover: generate enterprise ontologies from metadata; connect existing ontologies and semantic models; build AI-ready knowledge graphs.
- Ground: give agents trusted business meaning for metrics, entities, and relationships; reconcile inconsistent definitions across systems.
- Validate: check generated queries against certified definitions and lineage; return provenance with every answer.
- Expose: serve context to any agent harness through MCP, CLI, and API. Learn: fold certified corrections and usage back into the ontology, so shared context improves with every question.
Benchmarks
To run a text-to-SQL benchmark such as BIRD, refer to the ontology SQL evaluation repository.
Licensing & contributions. Auto Ontology is distributed under the Apache License 2.0. Third-party open-source components bundled, linked, or otherwise used by this project are listed in
THIRD_PARTY_NOTICES.md. This project is currently not accepting external contributions.
Key Features
- Natural-language querying of structured data — questions are translated to SQL and executed against connected databases, powered by NVIDIA NIM.
- Semantic catalog / ontology layer over relational sources, stored in Postgres alongside the catalog it describes.
- Authentication & RBAC —using Better Auth.
- Web UI for chat, analysis, data catalog, analytics, and settings.
- Flexible deployment — Helm chart for Kubernetes or Docker Compose for a local stack.
Software Components
| Component | Technology | Role | Default port |
|---|---|---|---|
| Frontend | Next.js 16 (React 19, TypeScript, Tailwind CSS 4), Better Auth, Prisma | Web UI, authentication, API gateway | 3000 |
| Backend | FastAPI (Python 3.12+), LangChain | Chat / NL-to-SQL, catalog, datasource APIs | 3001 |
| Ingestion worker | FastAPI (Python 3.12+) | Ingests tabular data and writes embeddings | 3002 |
| Postgres + pgvector | Relational Database | App metadata, the catalog and ontology, vector store | 5432 |
| HashiCorp Vault | Optional | Secure storage of connection credentials | — |
NVIDIA NIM
Auto Ontology uses NVIDIA NIM endpoints for inference — either the hosted NVIDIA API catalog or self-hosted NIMs.
Model triplets
Each model role is configured by a triplet of environment variables — <PREFIX>_ENDPOINT (URL), <PREFIX>_API_KEY, and <PREFIX>_MODEL:
| Prefix | Role |
|---|---|
DEFAULT_MODELS |
Shared default; every field below falls back to it. |
REASONING |
Main chat / NL-to-SQL model. |
NON_REASONING |
Lighter model used for entity extraction. |
EMBED |
Text-embedding model (must match between ingest and query). |
RERANK |
Reranker used by the retrieval flow. |
Quickstart
-
Clone the repository and create
.env:git clone https://github.com/NVIDIA/auto-ontology.git && cd auto-ontology cp .env.example .env -
Start Postgres and load the sample database.
-
Build and start the rest of the stack:
docker compose up -d --build -
Open http://localhost:3000 and sign in.
How it works
Auto-Ontology works in three stages: it generates an ontology, people certify it, and the agent answers questions from it.
The ontology holds three kinds of definition:
- Terms. Business concepts such as Customer or Invoice Line, each with a description and synonyms, mapped to the columns that hold them.
- SQL attributes. Reviewed SQL expressions under a term, such as a margin or a rolling total. The agent reuses them, so answers compute each measure the same way.
- Relationships. How tables join, including bridge tables, inferred from keys and from the data.
Integrate with us
To integrate an agent platform, application, or storage provider with Auto-Ontology, open an integration request.
License
Auto-Ontology is licensed under the Apache License, Version 2.0. SPDX identifier: Apache-2.0.
Notice and Disclaimer
NOTICE AND DISCLAIMER: This software automatically retrieves, accesses or interacts with external materials. Those retrieved materials are not distributed with this software and are governed solely by separate terms, conditions and licenses. Use this software and the retrieved materials at your own risk.
Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi