NVIDIA/auto-ontologyPublic

An open context layer that helps agents give fewer wrong answers on enterprise data.

Agents can retrieve documents and query databases, but reliability is what gates agentic analytics: a revenue figure delivered faster is worth nothing if it's wrong. Before an agent queries, it needs to know where the data lives, what it means, whether to use it, how to use it, where it came from, and what is similar.

Auto-Ontology is a service you run next to your databases to give agents that context. It compiles their metadata into an ontology: business terms mapped to columns, reviewed SQL for measures, and the relationships between tables. Agents query through the ontology, and people review it in a web UI. It complements the semantic models you already own.

With Auto-Ontology, developers can:

• Discover. Generate an ontology from database metadata, import existing semantic models, and explore the result as a semantic graph.
• Ground. Give agents one definition per business concept, mapped across tables and databases.
• Certify. Review, edit, and certify definitions in the UI or through the API.
• Validate. Check whether a question is answerable before querying, and return the SQL and the agent's steps with each answer.
• Expose. Serve context to any agent harness through MCP, agent skills, and a REST API.

The usual shortcut is to paste the schema into the agent's context window. Auto-Ontology gives the agent tools over the ontology:

The companion repository, auto-ontology-eval, measures ontology performance on benchmarks and evals.

For BIRD, BEAVER, FDABench-Lite, and Wide World Importers, each eval item pairs a question with gold SQL, and a run asks every question of the same model twice:

• Control. The model gets the database schema in its prompt.
• Treatment. Auto-Ontology's question-answering agent, the one behind Chat, works from the compiled ontology.

A deterministic verifier scores the SQL from each arm by execution match, using each benchmark's official rule where it has one. The report gives the accuracy difference and lists the questions the ontology fixed and the ones it broke. BIRD-Interact, a multi-turn benchmark where the agent asks clarifying questions, runs on its own harness.

To run the comparison on BIRD, follow the auto-ontology-eval setup, then run:

uv run python main.py --database-name bird

This runs Auto-Ontology with Docker Compose against Wide World Importers, Microsoft's sample sales database. You need Docker with Compose v2, uv, and an NVIDIA API key (nvapi-...) from build.nvidia.com.

1. Clone the repository and create .env:

   git clone https://github.com/NVIDIA/auto-ontology.git && cd auto-ontology
   cp .env.example .env

   Then set these values in .env:

   DEFAULT_MODELS_API_KEY=nvapi-...
   AUTH_SECRET=<a long random string, e.g. from openssl rand -base64 32>
   APP_URL=http://localhost:3000
   POSTGRES_PASSWORD=<a new password>
   CONNECTION_STRINGS=postgresql://postgres:<the same password>@postgres:5432/wideworldimporters
   AUTO_ONTOLOGY_ADMIN_PASSWORD=<a new password>
   PGADMIN_PASSWORD=<a new password>

   Compose publishes Postgres, pgAdmin, and the web app on the host, so replace each default password before you start it. .env.example also sets an API key per model role: replace each nvapi-your-api-key-here with your key, or delete those lines so they fall back to DEFAULT_MODELS_API_KEY.

2. Start Postgres and load the sample database. The seed script lives in auto-ontology-eval; pass it the Postgres password you set:

   docker compose up -d --wait postgres
   git clone https://github.com/NVIDIA/auto-ontology-eval.git ../auto-ontology-eval
   (cd ../auto-ontology-eval && uv sync && cp .env.example .env && \
     POSTGRES_PASSWORD='<the same password>' \
     uv run python scripts/seed/seed_wwi.py --database-name wideworldimporters --drop)

3. Build and start the rest of the stack:

   docker compose up -d --build

4. Open http://localhost:3000 and sign in with AUTO_ONTOLOGY_ADMIN_EMAIL and AUTO_ONTOLOGY_ADMIN_PASSWORD from .env. Go to Settings → Semantic Compilation and turn it on. Ingestion runs at startup; compilation starts immediately and reports Semantic compilation is ready when it finishes.

5. Ask a question in Chat:

   What was revenue for the USB food flash drive - sushi roll in Pennsylvania in June 2015?

   The agent resolves revenue, product, and state to terms in the ontology, follows their relationships to the joins it needs, and runs the query. The answer comes back with its SQL and the steps that produced it, so you can check the result against the source:

   Answer:  Revenue for USB food flash drive - sushi roll in Pennsylvania in
            June 2015 was $588.80, from 3 invoice lines.
   
   SQL:     SELECT SUM(il.extendedprice) AS revenue, COUNT(*) AS invoice_lines
            FROM sales.invoicelines il
            JOIN sales.invoices i             ON il.invoiceid = i.invoiceid
            JOIN warehouse.stockitems si      ON il.stockitemid = si.stockitemid
            JOIN sales.customers c            ON i.customerid = c.customerid
            JOIN application.cities ct        ON c.deliverycityid = ct.cityid
            JOIN application.stateprovinces sp ON ct.stateprovinceid = sp.stateprovinceid
            WHERE si.stockitemname = 'USB food flash drive - sushi roll'
              AND sp.stateprovincename = 'Pennsylvania'
              AND i.invoicedate >= '2015-06-01' AND i.invoicedate < '2015-07-01'
   
   Steps:   Resolved terms: Invoice Line (revenue), Stock Item, State Province, Invoice
            Joined: invoice line -> invoice -> customer -> city -> state province
            Validated the filter values against the data, then executed
   

6. Ask something the data can't answer. Wide World Importers has no advertising data, so a question about ad spend has nothing to resolve against. An agent connected through MCP checks answerability first and asks you to clarify:

   You:    What was return on ad spend for the sushi roll flash drive in June 2015?
   Agent:  check_answerable -> coverage 0.5; no term covers "ad spend"
   Agent:  I can find revenue for that product, but this data has no
           advertising spend, so I can't compute return on ad spend. Do you
           want June 2015 revenue instead, or is ad spend tracked in another
           source I should connect?
   

If the UI loads without its left navigation after a restart, the browser is holding a stale session cookie. Clear site data for localhost:3000 and sign in again. For other setup failures, see the setup skill's troubleshooting guide.

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.

Generate. The ingestion service builds a first draft from the source databases:

1. Read sources: extract schemas, profile columns, and sample values into the catalog.
2. Name entities: extract terms table by table and map each to columns.
3. Resolve relationships: infer joins between tables and bridge tables, and suggest SQL attributes from query history.
4. Write the ontology: store terms, relationships, and SQL attributes in Postgres, with embeddings in pgvector for retrieval.

The result is a semantic graph you can explore in the UI. In this example, one compilation of Wide World Importers produced 31 terms; selecting Order shows its description, related terms, mapped columns, and SQL attributes:

Certify. People make the draft trustworthy:

1. Test with real questions in Chat, or with check_answerable and ask_question over MCP.
2. Refine terms, descriptions, and SQL attributes in the UI or through the API.
3. Certify names, descriptions, and SQL attributes once they're correct.

Answer. For each question, the agent:

1. Classifies the intent and extracts the entities the question names.
2. Retrieves candidate terms, columns, and SQL attributes by embedding search.
3. Writes SQL from those candidates.
4. Checks the filter values and the query against the database, repairing the SQL when a check fails.
5. Runs the query and returns the answer with its SQL and the steps it took.

When the candidates can't support a query, the agent reports that the question can't be answered from this data. Predictive questions go to KumoRFM when it's configured (see Predictions).

In Chat, each answer shows its SQL, and you can view the rows, download them as CSV, or read them as a chart:

Auto-Ontology is compatible with Apache Ossie, the open standard for exchanging semantic models. Ossie includes a converter for Auto-Ontology, which Auto-Ontology uses to import and export model definitions as Ossie YAML. Use Settings → Import / Export, or POST /api/model/import and POST /api/model/export.

Keep ports 3001 and 3002 on a private network. FastAPI trusts the user identity the frontend forwards in the x-auto-ontology-user-id header, and the ingestion service's endpoints (ingest, delete, reset, compile) have no authentication of their own. Clients go through the web app on port 3000.

The MCP server gives any MCP client read-only tools over the ontology. Each user signs in through Auto-Ontology, and every call runs with that user's permissions.

Run the server against your deployment:

AUTO_ONTOLOGY_API_URL=http://localhost:3000 \
  uvx --from "git+https://github.com/NVIDIA/auto-ontology.git#subdirectory=mcp" auto-ontology-mcp

Cursor (~/.cursor/mcp.json):

{
  "mcpServers": {
    "auto-ontology": { "url": "http://localhost:3003/mcp" }
  }
}

Claude Desktop (claude_desktop_config.json), bridged with mcp-remote:

{
  "mcpServers": {
    "auto-ontology": {
      "command": "npx",
      "args": ["mcp-remote", "http://localhost:3003/mcp"]
    }
  }
}

Restart the client after editing its config, then sign in when it prompts. Sign-in, configuration, and troubleshooting are in docs/mcp.md.

Three skills teach a coding agent to work with Auto-Ontology. Start at AGENTS.md.

Ask a question with POST /api/chat/completions on the web app's origin. Mint an API token under the user menu → API Tokens. The response is a server-sent event stream: a result event carries the answer, and data: [DONE] ends the stream.

curl -N http://localhost:3000/api/chat/completions \
  -H "x-api-key: $AUTO_ONTOLOGY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"question": "How many orders shipped last week?"}'

import json
import os

import requests

response = requests.post(
    "http://localhost:3000/api/chat/completions",
    headers={"x-api-key": os.environ["AUTO_ONTOLOGY_API_TOKEN"]},
    json={"question": "How many orders shipped last week?"},
    stream=True,
    timeout=900,
)
response.raise_for_status()

for line in response.iter_lines(decode_unicode=True):
    if not line or not line.startswith("data:"):
        continue
    payload = line.removeprefix("data:").strip()
    if payload == "[DONE]":
        break
    event = json.loads(payload)
    if event["type"] == "result":
        print(event["answer"]["response"])
        print(event["answer"]["sql_code"])
    elif event["type"] == "error":
        raise RuntimeError(event["message"])

Event types, multi-turn conversations, and the gateway trust boundary are in docs/conversation-api.md. Every other operation is in the OpenAPI spec.

Auto-Ontology connects to ten engines:

• PostgreSQL
• MySQL
• Databricks
• Snowflake
• ClickHouse
• Trino
• Apache Kyuubi
• HeavyDB
• DuckDB
• SQLite

Add connections under Settings → Connections, or list them in CONNECTION_STRINGS. DuckDB and SQLite are connection-string only. See docs/connections.md for URL schemes, scoping, and credential storage.

Auto-Ontology uses four model roles. With an nvapi- key, each defaults to an NVIDIA NIM on build.nvidia.com:

To use self-hosted NIM or any OpenAI-compatible endpoint, set <ROLE>_ENDPOINT, <ROLE>_API_KEY, and <ROLE>_MODEL. Any field you leave unset falls back to DEFAULT_MODELS_<FIELD>, so the simplest setup fills in DEFAULT_MODELS_* and overrides only what differs. Use models that support structured output, and keep the embedding model the same for ingestion and queries. .env.example documents every variable.

Set KUMO_RFM_API_KEY and the agent routes predictive questions to KumoRFM. KumoRFM is a hosted service: to answer, the agent uploads the connected tables to it, capped by KUMO_MAX_TABLES (20 by default) and KUMO_MAX_ROWS_PER_TABLE (unlimited unless set). Review what that sends, and complete your organization's data review, before you enable it.

To integrate an agent platform, application, or storage provider with Auto-Ontology, open an integration request.

The Auto-Ontology team maintains the code and doesn't accept external pull requests. Integration requests and bug reports are welcome as issues. Report security vulnerabilities through SECURITY.md. Maintainer workflow is in CONTRIBUTING.md.

Auto-Ontology is licensed under the Apache License, Version 2.0. SPDX identifier: Apache-2.0.

Each NVIDIA-authored source file in this repository carries an SPDX header of the form:

SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION & AFFILIATES.
All rights reserved.
SPDX-License-Identifier: Apache-2.0

Third-party open-source components used by Auto-Ontology are enumerated, with their upstream licenses and project URLs, in THIRD_PARTY_NOTICES.md. Components added by the container images are listed separately in CONTAINER_THIRD_PARTY_NOTICES.md.

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. You are solely responsible for finding, reviewing and complying with all applicable terms, conditions, and licenses, and for verifying the security, integrity and suitability of any retrieved materials for your specific use case. This software is provided "AS IS", without warranty of any kind. The author makes no representations or warranties regarding any retrieved materials, and assumes no liability for any losses, damages, liabilities or legal consequences from your use or inability to use this software or any retrieved materials. Use this software and the retrieved materials at your own risk.

External materials Auto-Ontology interacts with at run time:

• Model endpoints you configure, by default the NVIDIA API catalog (integrate.api.nvidia.com, ai.api.nvidia.com), under each provider's and model's terms.
• The KumoRFM service, only when KUMO_RFM_API_KEY is set, under Kumo's terms.
• Your source databases, under your agreements for those systems.

Report security vulnerabilities as described in SECURITY.md.