Method: documents.moderateText

Moderates a document for harmful and sensitive categories.

HTTP request

POST https://language.googleapis.com/v2/documents:moderateText

The URL uses gRPC Transcoding syntax.

Request body

The request body contains data with the following structure:

JSON representation
{
  "document": {
    object (Document)
  },
  "modelVersion": enum (ModelVersion)
}
Fields
document

object (Document)

Required. Input document.

modelVersion

enum (ModelVersion)

Optional. The model version to use for documents.moderateText.

Response body

The document moderation response message.

If successful, the response body contains data with the following structure:

JSON representation
{
  "moderationCategories": [
    {
      object (ClassificationCategory)
    }
  ],
  "languageCode": string,
  "languageSupported": boolean
}
Fields
moderationCategories[]

object (ClassificationCategory)

Harmful and sensitive categories representing the input document.

languageCode

string

The language of the text, which will be the same as the language specified in the request or, if not specified, the automatically-detected language. See Document.language_code field for more details.

languageSupported

boolean

Whether the language is officially supported. The API may still return a response when the language is not supported, but it is on a best effort basis.

Authorization scopes

Requires one of the following OAuth scopes:

  • https://www.googleapis.com/auth/cloud-language
  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

ModelVersion

The model version to use for documents.moderateText.

Enums
MODEL_VERSION_UNSPECIFIED The default model version.
MODEL_VERSION_1 Use the v1 model, this model is used by default when not provided. The v1 model only returns probability (confidence) score for each category.
MODEL_VERSION_2 Use the v2 model. The v2 model only returns probability (confidence) score for each category, and returns severity score for a subset of the categories.