DatavineDatavine/Docs
Getting Started

Quickstart

Connect your BigQuery project and run your first query in under 10 minutes.

You'll need a Google Cloud Platform project with BigQuery and Vertex AI APIs enabled, and a service account with BigQuery Data Viewer, BigQuery Job User, and Vertex AI User roles. See Connecting a GCP Project for full details.

Step-by-step setup

1

Create your Datavine account

Go to datavine.app and sign up with your email or Google account. You'll be taken through a short onboarding wizard.

Choose Personal workspace if you're working alone, or Organization if you want to invite teammates.

2

Create a GCP service account

In the Google Cloud Console, navigate to IAM → Service Accounts.

Click Create Service Account, give it a name like datavine-reader, and grant it these two roles:

  • roles/bigquery.dataViewer
  • roles/bigquery.jobUser
  • roles/aiplatform.user (for AI features)

Also enable the Vertex AI API in your GCP project for AI SQL generation, Data Chat, and anomaly analysis to work.

Then go to Keys → Add Key → Create new key → JSON. Download the JSON file.

3

Connect your GCP project

In Datavine, open Settings → Connections or click Connect Project on the dashboard.

Enter your GCP Project ID (found in the Google Cloud Console header, e.g. my-project-123456).

Upload the service account JSON file you downloaded in step 2. Credentials are encrypted at rest and never exposed to the browser.

4

Run your first query

Navigate to SQL Editor in the left sidebar. Your datasets will appear in the left panel.

Click any table to see its schema, or type a query directly:

sql
SELECT *
FROM `your-project.your-dataset.your-table`
LIMIT 100

Press Cmd/Ctrl + Enter to run. Results appear in the panel below.

5

Try AI SQL generation

In the SQL Editor, click Visual Query Builder at the top. Describe what you want in plain English:

"Show me total revenue by customer for the last 30 days, ordered by highest first"

Datavine uses Vertex AI (Gemini) to generate the SQL. Review it, then click Run.

What's next?