Skip to content
datarelix.ai docs

Quick start

Ask your database in English. Sign in, connect a database, and run your first query — in a couple of minutes.

Before you start

You’ll need:

  • A datarelix.ai account — sign in at app.datarelix.ai with Google, Microsoft Entra, or GitHub.
  • A database datarelix.ai can reach, in one of the supported engines: Postgres, MySQL, Azure SQL, Databricks, Kusto, BigQuery, Athena, Elasticsearch, or Snowflake.

datarelix.ai runs the orchestrator, the per-dialect query services, and the Python sandbox for you — there’s nothing to install or operate.

Your first query

  1. Sign in

    Open app.datarelix.ai and sign in with Google, Microsoft Entra, or GitHub.

  2. Add a connection

    Click Add connection and pick your database engine. Each engine has its own fields and auth modes — the Connections guides walk through every one, including how to create a read-only role and where to find each credential. datarelix.ai only ever reads inside the allowed scope you set (schema / database / dataset / index pattern).

  3. Let discovery run

    After you connect, datarelix.ai introspects the schema and optionally enriches each table with a short description. Better descriptions mean sharper answers — see Writing queries.

  4. Ask a question

    Pick the connection and ask in plain language:

    ask
    What tables are in this database?
    Show me the top 5 customers by lifetime value
    What was the total revenue per month?

Every answer comes back artifact-first: a table or chart, the exact SQL/KQL that ran, the tables used, and the runtime — all one click away.

Using the API

Every UI action is also a REST endpoint, so you can build agents, pipelines, and integrations on top. Create a run with your workspace API key:

Terminal window
curl -N -X POST https://app.datarelix.ai/api/v1/runs/stream \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $DATARELIX_API_KEY" \
  -d '{ "connection_id": "your-connection-id", "question": "What are the top 10 customers?" }'

See the REST API reference for the full endpoint list and Authentication for how API keys work.

Next steps

Connections Connect any of the nine supported engines.
Writing queries Get sharper answers with table mentions and limits.
Python analysis Charts and stats in the sandboxed runtime.
Dashboards Pin results and build updatable dashboards.