Back to Devoured - November 16, 2026
DEVOURED
Auto Ontology: Grounding Agents in Enterprise Data (GitHub Repo)

Auto Ontology: Grounding Agents in Enterprise Data (GitHub Repo)

Data GitHub
NVIDIA's Auto Ontology maps enterprise database metadata into a semantic graph that agents can use to generate auditable, reliable SQL queries.
What: Auto Ontology is an Apache 2.0-licensed library that builds a semantic model from databases, allowing agents to query data while validating against certified business definitions and lineage. It uses NVIDIA NIM for reasoning, supports multiple database engines, and exposes data through MCP, APIs, and a CLI.
Why it matters: Reliability is the primary bottleneck for agentic data analysis; by creating a mandatory, human-certified context layer, this tool addresses the 'hallucination' risk in text-to-SQL workflows.
Takeaway: If you are building LLM agents for data analysis, use Auto Ontology to provide a 'source of truth' layer that agents must query against rather than letting them guess table structures.
Deep dive
  • Stage 1 (Generate): Automatically extracts schemas and builds a semantic graph stored in Postgres.
  • Stage 2 (Certify): Humans review and certify business terms and SQL attributes.
  • Stage 3 (Answer): Agents use the ontology to classify intent and generate validated SQL queries.
  • Metadata: Integrates with NVIDIA NIM for LLM inference (e.g., Nemotron-3.5) and pgvector for retrieval.
  • Deployment: Uses Helm charts or Docker Compose, and includes an MCP server for integration with tools like Cursor.
Decoder
  • Ontology: A formal representation of knowledge as a set of concepts and the relationships between those concepts within a specific domain.
  • Semantic Model: A layer that abstracts database complexity into business-friendly terms.
  • Provenance: The documented history or source of a data point or query result.
  • MCP (Model Context Protocol): An open standard for connecting AI assistants to data and tools.
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

  1. Clone the repository and create .env:

    git clone https://github.com/NVIDIA/auto-ontology.git && cd auto-ontology
    cp .env.example .env
  2. Start Postgres and load the sample database.

  3. Build and start the rest of the stack:

    docker compose up -d --build
  4. 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.

Explore all 69 articles in today's digest

Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi