Nvidia Auto Ontology v1 Semantic Layer for AI Agents

Deploys NVIDIA's open-source Auto Ontology 1.1.0, a semantic layer that builds an ontology over relational databases and answers natural-language questions as SQL. Includes the web UI, authenticated API, MCP server and a Chinook sample database. A community template, not affiliated with NVIDIA.

What you get

  • Frontend web app with login, API tokens and an authenticated /api gateway; sign-up stays closed
  • An MCP server at /mcp for Cursor, Claude or other MCP clients, signing in through Auto Ontology's OAuth
  • Private Backend (NL-to-SQL, catalog) and Ingestion (embeddings and semantic compilation every 24 h) services, with migrations run before each deploy
  • Postgres 18 with pgvector for the catalog, users and embeddings, plus a read-only Chinook sample registered and compiled on first boot
  • Images pinned to 1.1.0 by digest; only the Frontend and MCP Server have public domains

Good for

  • Giving agents governed, read-only access to company data through MCP
  • Natural-language analytics over Postgres, Snowflake, Databricks, MySQL, ClickHouse or Trino, with the generated SQL shown
  • A shared business glossary mapping terms such as active customer onto real columns
  • Scripts and scheduled jobs that ask questions through the chat completions endpoint with API tokens

Services in this template

  • Backend · from baranberkay96/auto-ontology-railway
  • Ingestion · from baranberkay96/auto-ontology-railway
  • Sample Data · from baranberkay96/auto-ontology-railway
  • Postgres · image ghcr.io/railwayapp-templates/postgres-ssl:18
  • MCP Server · from baranberkay96/auto-ontology-railway
  • Frontend · from baranberkay96/auto-ontology-railway

Questions people ask

What do I need to deploy, and how do I log in?

Paste an NVIDIA API key into DEFAULT_MODELS_API_KEY when deploying; you can create one at build.nvidia.com, or point the model settings at another OpenAI-compatible provider. Then open the Frontend URL and sign in with AUTO_ONTOLOGY_ADMIN_EMAIL (default admin@example.com) and the generated AUTO_ONTOLOGY_ADMIN_PASSWORD, both under Frontend variables.

What drives the cost?

Six services run continuously. Model calls are billed by your provider, and semantic compilation, which the template switches on at first boot, runs every 24 h over every connected database and makes model calls for new tables. Large warehouses can mean many calls; turn it off in Settings if needed.

How are database credentials handled?

This template does not include Vault, so connection credentials are stored in plaintext JSON in the Postgres catalog. Use read-only database users, keep that database private and treat its backups as secrets. Never add a domain or TCP proxy to Backend or Ingestion.

Can I use the hosted NVIDIA endpoints in production?

The template notes say the free access on build.nvidia.com is governed by NVIDIA's API Trial Terms of Service, which limit use without a paid subscription to internal testing and evaluation. For production, check NVIDIA's terms or use another provider. This is not legal advice.

How do I upgrade, and what licence applies?

Set the new tag and digest in the image variables on Backend, Frontend and MCP Server and deploy them together; never run mixed versions. Auto Ontology is Apache-2.0, and the Chinook sample data is MIT. Models carry their own licences.

Full template README

Deploy and Host Auto Ontology with Railway

Auto Ontology is NVIDIA's open-source (Apache-2.0) semantic layer for AI agents: it builds an ontology over your relational databases and answers natural-language questions as SQL. This community template runs release 1.1.0 from NVIDIA's published images with the web UI, the authenticated API, the MCP server and a sample database, so the first question works after deploy.

About Hosting Auto Ontology

Upstream ships a Docker Compose file and a Helm chart; running it yourself means a pgvector Postgres, a FastAPI backend that must never be public, an ingestion worker, two migration jobs, a Next.js front end with Better Auth, and an MCP server whose OAuth settings must match the web app's public URL. This template wires all of that on Railway's private network. Migrations run before each deploy, the admin account is created from generated variables, sign-up stays closed, and only the web app and the MCP server get public domains. You provide one value: an NVIDIA API key. A read-only Chinook database is registered as a sample connection, ingested and compiled on first boot.

Common Use Cases

  • Give Cursor, Claude or your own agents governed access to company data through MCP, with every call running as the signed-in user
  • Natural-language analytics over Postgres, Snowflake, Databricks, MySQL, ClickHouse or Trino, with the generated SQL shown
  • A shared business glossary that maps terms such as "active customer" onto real columns and reviewed SQL
  • Scripts and scheduled jobs that ask questions over the /api/chat/completions endpoint with API tokens
  • Evaluating NVIDIA Nemotron models for text-to-SQL on your own schema

Dependencies for Auto Ontology Hosting

  • Auto Ontology 1.1.0: backend + ingestion (nvcr.io/nvidia/auto-ontology), web app (nvcr.io/nvidia/auto-ontology-frontend), MCP server (nvcr.io/nvidia/auto-ontology-mcp)
  • PostgreSQL 18 with pgvector (catalog, users, embeddings)
  • PostgreSQL 18 with the Chinook sample database (optional demo source)
  • An NVIDIA API key from build.nvidia.com, or your own OpenAI-compatible / NIM endpoints

Deployment Dependencies

Implementation Details

Service Role Public
Frontend Web UI, Better Auth login, API tokens, the authenticated /api gateway; runs the Prisma migration before each deploy yes
MCP Server MCP endpoint /mcp for agent clients; sign-in through Auto Ontology's OAuth yes
Backend FastAPI: chat / NL-to-SQL, catalog, connections; runs the Alembic migration before each deploy no
Ingestion Ingests connected databases, writes embeddings, compiles the semantic layer (every 24 h and on demand) no
Postgres pgvector database, tuned to the container's limits no
Sample Data Chinook sample (11 tables, music store sales 2021–2025) with a read-only login no

Backend and Ingestion must stay private: the Backend trusts a user-id header set by the Frontend, and the Ingestion API has no authentication. Never add a domain or TCP proxy to them.

First login

  1. Paste your NVIDIA API key (nvapi-...) into DEFAULT_MODELS_API_KEY when deploying. Create one for free at build.nvidia.com.
  2. Wait until all services are healthy (first deploy: a few minutes for image pulls and builds).
  3. Open the Frontend URL. The login is AUTO_ONTOLOGY_ADMIN_EMAIL (default admin@example.com) and AUTO_ONTOLOGY_ADMIN_PASSWORD (generated), both on Frontend → Variables. To use your own email, change it there and redeploy Frontend.
  4. On first boot, Ingestion registers the chinook connection, ingests it and compiles the semantic layer (about 7 minutes in our test). Check Settings → Semantic Compilation for the first successful run. If the key was wrong or a model unavailable during that run, fix it, then use Reset Semantic Layer there: a failed run still counts as compiled.
  5. Ask in Chat: "Which artists have the most tracks?" A first answer took about 3 minutes in our test.

Self-service sign-up is disabled, as it is upstream. Add people through Settings → SSO (redirect URI https://{your-domain}/api/auth/sso/callback), or as an admin through Better Auth's admin API. The admin password is re-applied on every start: rotate it by changing the variable and redeploying Frontend.

Connect your own database

As an admin, open Settings → Connections → Add (Postgres, Snowflake, Databricks, MySQL, ClickHouse, Trino and others). Use a read-only database user. Adding a connection starts an ingest; its semantic layer is compiled on the next daily pass. To compile sooner, switch Semantic Compilation off and on again (enabling starts a run) or restart Ingestion. You can delete the chinook sample there, or remove the Sample Data service once the connection is gone. Without Vault, which this template does not include, connection credentials are stored in plaintext JSON in the Postgres catalog: keep that database private and treat its backups as secrets. You can also list connections in CONNECTION_STRINGS on Backend (comma-separated URLs); while it is set, the Connections page is hidden.

Semantic compilation cost

The template switches semantic compilation on at first boot so the sample works out of the box. It runs every 24 h over every connected database, and new tables cost model calls. Large warehouses can mean many calls. Turn it off in Settings, or set TEMPLATE_ENABLE_SEMANTIC_COMPILATION=false on Ingestion before the first deploy to keep upstream's opt-in default.

API and MCP

  • API: user menu → API Tokens → New token. Then call POST https://{your-domain}/api/chat/completions with header x-api-key: {token} and body {"question": "..."}. The response is a stream of step / result events ending in [DONE]. A token acts with its owner's role.
  • MCP: add https://{mcp-domain}/mcp to Cursor, Claude or any MCP client. The client registers itself and opens Auto Ontology's login page; no secrets go into the client config. Tools: ask_question, check_readiness, search_terms, describe_table and more, all read-only. The MCP URL is configured once, in AUTO_ONTOLOGY_MCP_PUBLIC_URL on Frontend.

Models

All model settings live on Backend (Ingestion references them). Defaults: nvidia/nemotron-3-ultra-550b-a55b for chat (upstream 1.1.0's nvidia/nemotron-3-nano-30b-a3b was retired on 2026-09-01; the chat model must support structured output), nvidia/nemotron-3-embed-1b for embeddings and nvidia/llama-nemotron-rerank-vl-1b-v2 for reranking, all on NVIDIA's API catalog. REASONING_* and NON_REASONING_* accept any OpenAI-compatible endpoint (set *_ENDPOINT, *_MODEL and *_API_KEY). Embeddings and reranking expect NVIDIA NIM-compatible APIs, either hosted or self-hosted NIM. Keep the embedding model fixed after the first ingest; changing it needs a re-ingest. NVIDIA enables models per account: 404 Function ... Not found for account in the logs means pick another model from build.nvidia.com. On HTTP 429/503, lower LLM_MAX_INFLIGHT (Backend) and SEMANTIC_LLM_MAX_INFLIGHT (Ingestion).

Scaling

Frontend can run replicas. Scale Backend vertically: each concurrent chat turn runs in its own worker process. Keep Ingestion and MCP Server at one replica, because their schedulers and sessions live in the process. Give Ingestion more RAM for large catalogs.

Upgrades

All Auto Ontology images are pinned to 1.1.0 by digest; each service builds FROM NVIDIA's image unchanged. To upgrade, set the new tag and digest in AUTO_ONTOLOGY_IMAGE on Backend (Ingestion follows it), AUTO_ONTOLOGY_FRONTEND_IMAGE on Frontend and AUTO_ONTOLOGY_MCP_IMAGE on MCP Server. Read the upstream changes, then deploy them together. Backend migrates the schema before it starts, and Ingestion waits for it. Never run mixed versions.

Costs

Estimated at Railway usage prices: about $19/month idle and $50/month with a few active users and daily ingests. Hobby plan recommended. Model calls are billed by your model provider, not Railway.

NVIDIA API terms

Hosted endpoints on build.nvidia.com are governed by NVIDIA's API Trial Terms of Service and each model's licence. The free access is meant for prototyping and evaluation. The trial terms limit use without a paid subscription to internal testing and evaluation, not production. For production, check NVIDIA's terms (for example a subscription or self-hosted NIM), or point the model settings at another provider. This summary is not legal advice.

Why Deploy Auto Ontology on Railway?

Railway runs the web app, MCP server, API, ingestion worker and both databases in one project on a private network, with HTTPS, volumes, pre-deploy migrations and logs handled for you. One API key gets you from deploy to a working NL-to-SQL demo; then you connect your own databases and agents. This is a community template. It is not affiliated with or endorsed by NVIDIA. Auto Ontology is NVIDIA's open-source project under the Apache-2.0 licence.

View Nvidia Auto Ontology v1 Semantic Layer for AI Agents on railway.com

Similar templates

TemplateCategoryDeploymentsDeploys
9Router
Self-hosted AI router for Claude, Gemini, Cursor & OpenAI tools.
AI/ML9,734
flowise-railway
Flowise - low-code LLM apps builder
AI/ML8,512
LibreChat
Open-source ChatGPT clone: multi-model, agents, search, multi-user auth
AI/ML6,762
Hermes Agent by Nous Research
Template for Hermes Agent by Nous Research
AI/ML6,413
OpenClaw
[Homebrew support] The AI that actually does things
AI/ML5,167
Hermes Agent
Self Host Hermes Agent. Autonomous AI agent w/ self-improving, tools & more
AI/ML4,092