CreateDatasetRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/CreateDatasetRequest",
  "title": "CreateDatasetRequest",
  "type": "object",
  "required": [
    "name",
    "type",
    "data"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "The name of the dataset."
    },
    "type": {
      "type": "string",
      "description": "The type of dataset. Currently embed-input is the primary type used with the Embed Jobs API.",
      "enum": [
        "embed-input",
        "reranker-finetune-input",
        "prompt-completion-finetune-input",
        "single-label-classification-finetune-input",
        "chat-finetune-input"
      ]
    },
    "data": {
      "type": "string",
      "format": "binary",
      "description": "The data file to upload."
    },
    "delimiter": {
      "type": "string",
      "description": "The delimiter used for CSV file uploads."
    },
    "dry_run": {
      "type": "boolean",
      "description": "When true, validates the data without creating the dataset."
    },
    "keep_fields": {
      "type": "string",
      "description": "Comma-separated list of field names to persist in the dataset."
    }
  }
}