README for a GitHub Dataset

Write a clear README.md for a dataset you publish on GitHub or Kaggle. Describes the columns, size, quality and licence notes. Free and private.

Quick answer: Get a README.md that explains what your CSV, Excel, JSON or Parquet dataset is about.

Related: Dataset README Generator · README for a CSV Dataset · Dataset Documentation Generator · README Generator for a Dataset · AI Data Tools and Guides

How to use the README for a GitHub Dataset

Get a README.md that explains what your CSV, Excel, JSON or Parquet dataset is about.

The Dataset README Generator writes a README.md that explains your data: what it contains, how many rows and columns, and what each column means. It is built from statistics of your file and uses your own Gemini key. Add it to a repository, a shared drive or a data catalog so the next person understands the dataset. Read it once before sharing.

  1. Add your AI key
  2. Load your file
  3. Generate and edit the README

Tips

Example

Input: titanic.csv

Output: README.md ready to commit

Browse by topic

Who uses Data Utility

Frequently asked questions · Data format benchmark

Frequently asked questions

Can I use it for a Kaggle or Hugging Face dataset?

Yes. The README works as a dataset description. Add your licence and source before you publish.

What is sent to Google Gemini?

Column names, types, statistics and, if you allow it, a few sample values. Your full file is never sent.

Will the README be accurate?

It is based on statistics from your data. Always read it once, because the AI may guess the meaning of unclear columns.

What is the Data README generator?

It writes a README.md that explains what your dataset is about, with a table of columns, based on statistics from your file. Read it once before sharing, because the AI may guess the meaning of unclear columns.

Related pages

Topic guides

Guides