EvalDataset
Dataset backing an eval task.
Example Usage
typescript
import { EvalDataset } from "@meetkai/mka1/models/components";
let value: EvalDataset = {};Fields
| Field | Type | Required | Description |
|---|---|---|---|
source | components.Source | ➖ | Dataset source. Inferred from file_id or path when omitted. |
fileId | string | ➖ | File ID for a JSONL or CSV dataset uploaded with purpose 'evals'. |
format | components.EvalDatasetFormat | ➖ | N/A |
path | string | ➖ | Hugging Face dataset path, for example facebook/belebele. |
name | string | ➖ | Hugging Face dataset config/name. |
split | string | ➖ | Hugging Face split to load, for example test, train, or validation. |
revision | string | ➖ | Optional Hugging Face dataset revision. |
dataFiles | components.DataFiles | ➖ | Optional Hugging Face data_files value for json/csv/parquet style datasets. |
datasetKwargs | Record<string, any> | ➖ | Additional dataset loading kwargs retained for import/parity metadata. |
maxRows | number | ➖ | Optional safety cap for remote dataset loading. |