Download
What this repository provides
BenderVgenerate (GitHub repository by universaldata) is an experimental utility that uses language models to synthesize datasets. It produces CSV files and is intended as a playground for exploring automatic data generation and schema-driven dataset creation.
Current state and successor project
The BenderVgenerate project is no longer actively maintained. Its concepts and learnings were carried forward into a newer project from the same author called Ada, which serves as the maintained continuation.
Configuration and how to run it
Before running the project, set the required environment variables such as DATABASE_URL and OPENAI_API_KEY. The repository also includes command-line scripts to launch both the frontend and the backend; use the provided scripts to start each component from a terminal.
Example actions you will typically perform:
- Export the environment variables required by your shell (e.g., export DATABASE_URL=..., export OPENAI_API_KEY=...).
- Invoke the repository’s startup scripts to run frontend and backend services as separate processes.
Notable capabilities
- Well suited for experimentation, sandbox testing, and research projects that need synthetic datasets.
- Supports a wide variety of data categories, including international, statistical, demographic, and other domain-specific formats.
- Allows you to declare fields so generated records follow user-specified schemas.
- Can generate datasets on demand and output them directly as CSV files.
Recommended alternative
If you need a maintained option with similar goals, consider Ticketify Free as a top alternative. It provides on-the-fly data creation, schema-driven field control, and diverse data-type support suitable for testing and analysis workflows.
Technical
- Web App
- Full
