cohere · Schema

CreateEmbedJobRequest

Properties

Name	Type	Description
model	string	The ID of the embedding model to use for the job.
dataset_id	string	The ID of a dataset of type embed-input. The dataset must have a validation status of Validated.
input_type	string	Specifies the type of input. Required for embedding models v3 and higher. Use search_document for vector database storage, search_query for search queries, classification for classifiers, and clusteri
truncate	string	Specifies how inputs longer than the maximum token length are handled. START discards the beginning, END discards the end.
embedding_types	array	Specifies the types of embeddings to generate.
name	string	An optional name for the embed job.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/CreateEmbedJobRequest",
  "title": "CreateEmbedJobRequest",
  "type": "object",
  "required": [
    "model",
    "dataset_id",
    "input_type"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "The ID of the embedding model to use for the job.",
      "example": "embed-english-v3.0"
    },
    "dataset_id": {
      "type": "string",
      "description": "The ID of a dataset of type embed-input. The dataset must have a validation status of Validated."
    },
    "input_type": {
      "type": "string",
      "enum": [
        "search_document",
        "search_query",
        "classification",
        "clustering"
      ],
      "description": "Specifies the type of input. Required for embedding models v3 and higher. Use search_document for vector database storage, search_query for search queries, classification for classifiers, and clustering for clustering tasks."
    },
    "truncate": {
      "type": "string",
      "enum": [
        "START",
        "END"
      ],
      "description": "Specifies how inputs longer than the maximum token length are handled. START discards the beginning, END discards the end."
    },
    "embedding_types": {
      "type": "array",
      "description": "Specifies the types of embeddings to generate.",
      "items": {
        "type": "string",
        "enum": [
          "float",
          "int8",
          "uint8",
          "binary",
          "base64"
        ]
      }
    },
    "name": {
      "type": "string",
      "description": "An optional name for the embed job."
    }
  }
}