TopGit tracks metabase/dataset-generator on GitHub. The project has 765 stars. AI Dataset Generator – Create realistic datasets for demos, learning, and dashboards
Snapshot summary built from the project's own GitHub metadata — there's no written TopGit review yet. The page will update automatically when a full review is published.
WHY NO REVIEW YET
TopGit writes full reviews for the most-starred, most-requested repositories. This page is a snapshot until then — see the READ ME tab for the original README in full.
Generate realistic datasets for demos, learning, and dashboards. Instantly preview data, export as CSV or SQL, and explore with Metabase.
Want to try it without setup? We've hosted this tool at metabase.com/ai-data-generator
Features:
Conversational prompt builder: choose business type, schema, row count, and more
Real-time data preview in the browser
Export as CSV (single file or multi-table ZIP) or as SQL inserts
One-click Metabase launch for data exploration (see Using Metabase for details)
Local vs Web: When running locally, you can spin up Metabase in Docker and use LiteLLM for multi-provider LLM support. On the web, the app defaults to OpenAI and redirects to Metabase Cloud for data exploration.
Usage Flow
Select your business type, schema, and other parameters.
Click "Preview Data" to generate a 10-row sample (incurs a small LLM cost, depending on provider).
Download CSV/SQL for as many rows as you want—no extra cost, always uses the same schema/columns as the preview.
Prerequisites
Node.js (18 or later)
OpenAI API key
Docker (optional, for Metabase and multi-provider LLM support)
Getting Started
Clone the repo:
git clone <your-repo-url>
cd dataset-generator
Create your .env file:
Create a .env file in the project root with your OpenAI API key:
OPENAI_API_KEY=sk-your-openai-key-here
Optionally, you can also set:
# Change the OpenAI model (defaults to gpt-4o)
LLM_MODEL=gpt-4o
Start the Next.js app:
npm install
npm run dev
The app runs at http://localhost:3000
Generate a dataset:
Use the prompt builder to define your dataset.
Click "Preview Data" to see a sample.
Export or Explore:
Download your dataset as CSV or SQL Inserts.
Click "Start Metabase" to spin up Metabase in Docker.
Once Metabase is ready, click "Open Metabase" to explore your data.
In Metabase, use the "Upload Data" feature to analyze your CSV files
Or connect to your own database where you've loaded the data
When done, click "Stop Metabase" to shut down and clean up Docker containers.
Advanced: Multi-Provider LLM Support
By default, the app uses OpenAI directly. If you want to use other LLM providers (Anthropic, Google, etc.), you can optionally run the LiteLLM service:
Add provider keys to your .env file:
# Keep your OpenAI key as fallback
OPENAI_API_KEY=sk-your-openai-key-here
# Add other provider keys
ANTHROPIC_API_KEY=your-anthropic-key-here
GOOGLE_GENAI_API_KEY=your-google-key-here
# LiteLLM configuration
LITELLM_MASTER_KEY=sk-1234
LITELLM_SALT_KEY=sk-1234
# Set model for your preferred provider
LLM_MODEL=claude-3-sonnet-20240229
Start LiteLLM service:
docker compose up litellm db_litellm
When LiteLLM is running, the app automatically detects it and routes requests through the multi-provider gateway instead of directly to OpenAI.
How It Works
The dataset generator uses a two-stage process to create realistic business data. First, it leverages large language models to
generate detailed data specifications based on your business type and parameters. Then, it uses these specifications to create
unlimited amounts of realistic data locally.
When you preview a dataset, the app uses OpenAI (or LiteLLM if running) to generate a detailed data spec (schema, business rules, event logic) for your chosen business type and parameters.
All actual data rows are generated locally using Faker, based on the LLM-generated spec.
Downloading or exporting data never calls an LLM again—it's instant and free.
Cost & Data Generation Summary
Action
Calls LLM?
Cost?
Uses LLM?
Uses Faker?
Row Count
Preview
Yes
~$0.05
Yes
Yes
10
Download CSV
No
$0
No
Yes
100+
Download SQL
No
$0
No
Yes
100+
The above costs and behavior are based on testing with the OpenAI GPT-4o model. Costs and token usage may vary with other providers/models.
You only pay for the preview/spec generation (e.g., ~$0.05 per preview with OpenAI GPT-4o)
All downloads use the same columns/spec, just with more rows, and are free
Caching: After your first preview, the app remembers your data structure. If you preview the same business type and settings again, it reuses that structure (free) instead of generating a new one. This saves money and time. You'll see "Using cached spec" in the terminal when this happens. Check cache stats: curl http://localhost:3000/api/cache/stats or clear: curl -X DELETE http://localhost:3000/api/cache/clear.
Project Structure
/app/page.tsx – Main UI and prompt builder
/app/api/generate/route.ts – Synthetic data generator (OpenAI direct or via LiteLLM)
/app/api/metabase/start|stop|status/route.ts – Docker orchestration for Metabase
/lib/export/ – CSV/SQL export logic
/docker-compose.yml – Used for Metabase and LiteLLM services
public enforceYourBusinessRules(record: DataRecord): void {
// Add validation logic for your business type
// e.g., ensure realistic pricing, date relationships, etc.
}
Update lib/data-factory.ts - Call your new enforcer method:
// In the generate() method, add your enforcer
this.dataEnforcer.enforceYourBusinessRules(record);
Test your changes - Generate a preview to ensure realistic data ranges and proper field validation
TopGit's last sync did not record any GitHub topics for metabase/dataset-generator. GitHub topics appear in the right sidebar of a repository page; that's the authoritative place to check.
How active is development on metabase/dataset-generator?
The most recent commit recorded on metabase/dataset-generator was 30 days ago, based on the GitHub push timestamp. The repository has 48 forks — one of the better signals of community interest.
How many stars does metabase/dataset-generator have?
metabase/dataset-generator has 765 GitHub stars — refresh the page for the live number, or check github.com/metabase/dataset-generator. TopGit mirrors GitHub's count but does not claim minute-by-minute accuracy.
What language is metabase/dataset-generator written in?
metabase/dataset-generator is written primarily in TypeScript. GitHub's language field is based on the largest share of bytes in the default branch.
What license does metabase/dataset-generator use?
metabase/dataset-generator is released under the MIT license. Always verify the LICENSE file directly on GitHub for the authoritative terms — license strings can be edited out of sync with a project's actual stance.
Where can I see metabase/dataset-generator in action?
The project maintains a homepage at https://www.metabase.com/ai-data-generator. The README tab on this page also usually contains screenshots and a quickstart.
Where do I read more about metabase/dataset-generator?
This TopGit page is a snapshot — the READ ME tab shows the project's own README content (links stripped, images preserved). The GitHub repository at github.com/metabase/dataset-generator is the definitive source.
Read full README in the tab above.
Want a second opinion on dataset-generator?
Ask an AI that can read this page — one click and you get its take on dataset-generator.