Pull a dataset by name
Iterate over rows
Rows are yielded asDotDict objects, so both key and dot access are possible.
Index and slice
dataset[idx]returns a single row (DotDict)dataset[start:end]returns a newDatasetwith copied rows
Sliced datasets preserve backend metadata (dataset id/version/subset) when
available, so they can still be evaluated and pushed in normal workflows.
Access columns and normalized data
Minimal versioning example
Common loading errors
SDK not initialized
SDK not initialized
Dataset.pull(...) requires a valid ZeroEval initialization.Dataset not found
Dataset not found
Confirm dataset name and project context (API key/org mapping). Pull uses the project resolved from your API credentials.