Datasets are simple data tables that you can use to manage your data for experiments and evaluation of your AI applications.
Datasets are available in the SDK, and they enable you to create versioned snapshots for reproducible testing.
1
Create a new dataset
Click New Dataset to create a dataset, give it a descriptive name that reflects its purpose or use case, add a description to help your team understand its context, and provide a slug that allows you to use the dataset in the SDK.
2
Add your data
Add rows and columns to structure your dataset.
You can add different column types:
Text: For prompts, model responses, or any textual data
Number: For numerical values, scores, or metrics
Boolean: For true/false flags or binary classifications
Use meaningful column names that clearly describe what each field contains,
making it easier to work with your dataset in code, ensure clarity when using evaluators, and collaborate with team members.
3
Publish your dataset version
Once you’re satisfied with your dataset structure and data:
Click Publish Version to create a stable snapshot
Published versions are immutable
Publish versions are accessible in the SDK
4
View your version history
You can access all published versions of your dataset by opening the version history modal. This allows you to: