Class: OpenAI::Resources::Moderations

Inherits:

Object

• Object
• OpenAI::Resources::Moderations

Defined in:

lib/openai/resources/moderations.rb,
sig/openai/resources/moderations.rbs

Overview

Given text and/or image inputs, classifies if those inputs are potentially harmful.

Instance Method Summary

• #create(input:, model: nil, request_options: {}) ⇒ OpenAI::Models::ModerationCreateResponse

  Classifies if text and/or image inputs are potentially harmful.

• #initialize(client:) ⇒ Moderations constructor private

  A new instance of Moderations.

Constructor Details

#initialize(client:) ⇒ Moderations

This method is part of a private API. You should avoid using this method if possible, as it may be removed or be changed in the future.

Returns a new instance of Moderations.

Parameters:

• client (OpenAI::Client)
• client: (OpenAI::Client)

# File 'lib/openai/resources/moderations.rb', line 44

def initialize(client:)
  @client = client
end

Instance Method Details

#create(input:, model: nil, request_options: {}) ⇒ OpenAI::Models::ModerationCreateResponse

Classifies if text and/or image inputs are potentially harmful. Learn more in the moderation guide.

Parameters:

• input (String, Array<String>, Array<OpenAI::Models::ModerationImageURLInput, OpenAI::Models::ModerationTextInput>) —

  Input (or inputs) to classify. Can be a single string, an array of strings, or an array of multi-modal input objects similar to other models.

• model (String, Symbol, OpenAI::Models::ModerationModel) —

  The content moderation model you would like to use. Learn more in the moderation guide, and learn about available models here.

• request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

• (OpenAI::Models::ModerationCreateResponse)

See Also:

• Models::ModerationCreateParams

# File 'lib/openai/resources/moderations.rb', line 29

def create(params)
  parsed, options = OpenAI::ModerationCreateParams.dump_request(params)
  @client.request(
    method: :post,
    path: "moderations",
    body: parsed,
    model: OpenAI::Models::ModerationCreateResponse,
    security: {bearer_auth: true},
    options: options
  )
end