Moderations

Create moderation

moderations.create(**kwargs) -> ModerationCreateResponse

post /moderations

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

Parameters

input: String | Array[String] | Array[ModerationMultiModalInput]

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.
- String = String
  
  A string of text to classify for moderation.
- UnionMember1 = Array[String]
  
  An array of strings to classify for moderation.
- ModerationMultiModalArray = Array[ModerationMultiModalInput]
  
  An array of multi-modal inputs to the moderation model.
  - class ModerationImageURLInput
    
    An object describing an image to classify.
    - image_url: ImageURL{ url}
      
      Contains either an image URL or a data URL for a base64 encoded image.
      - url: String
        
        Either a URL of the image or the base64 encoded image data.
    - type: :image_url
      
      Always image_url.
      - :image_url
  - class ModerationTextInput
    
    An object describing text to classify.
    - text: String
      
      A string of text to classify.
    - type: :text
      
      Always text.
      - :text
model: String | ModerationModel

The content moderation model you would like to use. Learn more in the moderation guide, and learn about available models here.
- String = String
- ModerationModel = :"omni-moderation-latest" | :"omni-moderation-2024-09-26" | :"text-moderation-latest" | :"text-moderation-stable"
  - :"omni-moderation-latest"
  - :"omni-moderation-2024-09-26"
  - :"text-moderation-latest"
  - :"text-moderation-stable"

Returns

class ModerationCreateResponse

Represents if a given text input is potentially harmful.
- id: String
  
  The unique identifier for the moderation request.
- model: String
  
  The model used to generate the moderation results.
- results: Array[Moderation]
  
  A list of moderation objects.
  - categories: Categories{ harassment, harassment_threatening, hate, 10 more}
    
    A list of the categories, and whether they are flagged or not.
    - harassment: bool
      
      Content that expresses, incites, or promotes harassing language towards any target.
    - harassment_threatening: bool
      
      Harassment content that also includes violence or serious harm towards any target.
    - hate: bool
      
      Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment.
    - hate_threatening: bool
      
      Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.
    - illicit: bool
      
      Content that includes instructions or advice that facilitate the planning or execution of wrongdoing, or that gives advice or instruction on how to commit illicit acts. For example, "how to shoplift" would fit this category.
    - illicit_violent: bool
      
      Content that includes instructions or advice that facilitate the planning or execution of wrongdoing that also includes violence, or that gives advice or instruction on the procurement of any weapon.
    - self_harm: bool
      
      Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.
    - self_harm_instructions: bool
      
      Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts.
    - self_harm_intent: bool
      
      Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders.
    - sexual: bool
      
      Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).
    - sexual_minors: bool
      
      Sexual content that includes an individual who is under 18 years old.
    - violence: bool
      
      Content that depicts death, violence, or physical injury.
    - violence_graphic: bool
      
      Content that depicts death, violence, or physical injury in graphic detail.
  - category_applied_input_types: CategoryAppliedInputTypes{ harassment, harassment_threatening, hate, 10 more}
    
    A list of the categories along with the input type(s) that the score applies to.
    - harassment: Array[:text]
      
      The applied input type(s) for the category 'harassment'.
      - :text
    - harassment_threatening: Array[:text]
      
      The applied input type(s) for the category 'harassment/threatening'.
      - :text
    - hate: Array[:text]
      
      The applied input type(s) for the category 'hate'.
      - :text
    - hate_threatening: Array[:text]
      
      The applied input type(s) for the category 'hate/threatening'.
      - :text
    - illicit: Array[:text]
      
      The applied input type(s) for the category 'illicit'.
      - :text
    - illicit_violent: Array[:text]
      
      The applied input type(s) for the category 'illicit/violent'.
      - :text
    - self_harm: Array[:text | :image]
      
      The applied input type(s) for the category 'self-harm'.
      - :text
      - :image
    - self_harm_instructions: Array[:text | :image]
      
      The applied input type(s) for the category 'self-harm/instructions'.
      - :text
      - :image
    - self_harm_intent: Array[:text | :image]
      
      The applied input type(s) for the category 'self-harm/intent'.
      - :text
      - :image
    - sexual: Array[:text | :image]
      
      The applied input type(s) for the category 'sexual'.
      - :text
      - :image
    - sexual_minors: Array[:text]
      
      The applied input type(s) for the category 'sexual/minors'.
      - :text
    - violence: Array[:text | :image]
      
      The applied input type(s) for the category 'violence'.
      - :text
      - :image
    - violence_graphic: Array[:text | :image]
      
      The applied input type(s) for the category 'violence/graphic'.
      - :text
      - :image
  - category_scores: CategoryScores{ harassment, harassment_threatening, hate, 10 more}
    
    A list of the categories along with their scores as predicted by model.
    - harassment: Float
      
      The score for the category 'harassment'.
    - harassment_threatening: Float
      
      The score for the category 'harassment/threatening'.
    - hate: Float
      
      The score for the category 'hate'.
    - hate_threatening: Float
      
      The score for the category 'hate/threatening'.
    - illicit: Float
      
      The score for the category 'illicit'.
    - illicit_violent: Float
      
      The score for the category 'illicit/violent'.
    - self_harm: Float
      
      The score for the category 'self-harm'.
    - self_harm_instructions: Float
      
      The score for the category 'self-harm/instructions'.
    - self_harm_intent: Float
      
      The score for the category 'self-harm/intent'.
    - sexual: Float
      
      The score for the category 'sexual'.
    - sexual_minors: Float
      
      The score for the category 'sexual/minors'.
    - violence: Float
      
      The score for the category 'violence'.
    - violence_graphic: Float
      
      The score for the category 'violence/graphic'.
  - flagged: bool
    
    Whether any of the below categories are flagged.

Example

require "openai"

openai = OpenAI::Client.new(api_key: "My API Key")

moderation = openai.moderations.create(input: "I want to kill them.")

puts(moderation)

Response

{
  "id": "id",
  "model": "model",
  "results": [
    {
      "categories": {
        "harassment": true,
        "harassment/threatening": true,
        "hate": true,
        "hate/threatening": true,
        "illicit": true,
        "illicit/violent": true,
        "self-harm": true,
        "self-harm/instructions": true,
        "self-harm/intent": true,
        "sexual": true,
        "sexual/minors": true,
        "violence": true,
        "violence/graphic": true
      },
      "category_applied_input_types": {
        "harassment": [
          "text"
        ],
        "harassment/threatening": [
          "text"
        ],
        "hate": [
          "text"
        ],
        "hate/threatening": [
          "text"
        ],
        "illicit": [
          "text"
        ],
        "illicit/violent": [
          "text"
        ],
        "self-harm": [
          "text"
        ],
        "self-harm/instructions": [
          "text"
        ],
        "self-harm/intent": [
          "text"
        ],
        "sexual": [
          "text"
        ],
        "sexual/minors": [
          "text"
        ],
        "violence": [
          "text"
        ],
        "violence/graphic": [
          "text"
        ]
      },
      "category_scores": {
        "harassment": 0,
        "harassment/threatening": 0,
        "hate": 0,
        "hate/threatening": 0,
        "illicit": 0,
        "illicit/violent": 0,
        "self-harm": 0,
        "self-harm/instructions": 0,
        "self-harm/intent": 0,
        "sexual": 0,
        "sexual/minors": 0,
        "violence": 0,
        "violence/graphic": 0
      },
      "flagged": true
    }
  ]
}

Domain Types

Moderation

class Moderation
- categories: Categories{ harassment, harassment_threatening, hate, 10 more}
  
  A list of the categories, and whether they are flagged or not.
  - harassment: bool
    
    Content that expresses, incites, or promotes harassing language towards any target.
  - harassment_threatening: bool
    
    Harassment content that also includes violence or serious harm towards any target.
  - hate: bool
    
    Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment.
  - hate_threatening: bool
    
    Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.
  - illicit: bool
    
    Content that includes instructions or advice that facilitate the planning or execution of wrongdoing, or that gives advice or instruction on how to commit illicit acts. For example, "how to shoplift" would fit this category.
  - illicit_violent: bool
    
    Content that includes instructions or advice that facilitate the planning or execution of wrongdoing that also includes violence, or that gives advice or instruction on the procurement of any weapon.
  - self_harm: bool
    
    Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.
  - self_harm_instructions: bool
    
    Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts.
  - self_harm_intent: bool
    
    Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders.
  - sexual: bool
    
    Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).
  - sexual_minors: bool
    
    Sexual content that includes an individual who is under 18 years old.
  - violence: bool
    
    Content that depicts death, violence, or physical injury.
  - violence_graphic: bool
    
    Content that depicts death, violence, or physical injury in graphic detail.
- category_applied_input_types: CategoryAppliedInputTypes{ harassment, harassment_threatening, hate, 10 more}
  
  A list of the categories along with the input type(s) that the score applies to.
  - harassment: Array[:text]
    
    The applied input type(s) for the category 'harassment'.
    - :text
  - harassment_threatening: Array[:text]
    
    The applied input type(s) for the category 'harassment/threatening'.
    - :text
  - hate: Array[:text]
    
    The applied input type(s) for the category 'hate'.
    - :text
  - hate_threatening: Array[:text]
    
    The applied input type(s) for the category 'hate/threatening'.
    - :text
  - illicit: Array[:text]
    
    The applied input type(s) for the category 'illicit'.
    - :text
  - illicit_violent: Array[:text]
    
    The applied input type(s) for the category 'illicit/violent'.
    - :text
  - self_harm: Array[:text | :image]
    
    The applied input type(s) for the category 'self-harm'.
    - :text
    - :image
  - self_harm_instructions: Array[:text | :image]
    
    The applied input type(s) for the category 'self-harm/instructions'.
    - :text
    - :image
  - self_harm_intent: Array[:text | :image]
    
    The applied input type(s) for the category 'self-harm/intent'.
    - :text
    - :image
  - sexual: Array[:text | :image]
    
    The applied input type(s) for the category 'sexual'.
    - :text
    - :image
  - sexual_minors: Array[:text]
    
    The applied input type(s) for the category 'sexual/minors'.
    - :text
  - violence: Array[:text | :image]
    
    The applied input type(s) for the category 'violence'.
    - :text
    - :image
  - violence_graphic: Array[:text | :image]
    
    The applied input type(s) for the category 'violence/graphic'.
    - :text
    - :image
- category_scores: CategoryScores{ harassment, harassment_threatening, hate, 10 more}
  
  A list of the categories along with their scores as predicted by model.
  - harassment: Float
    
    The score for the category 'harassment'.
  - harassment_threatening: Float
    
    The score for the category 'harassment/threatening'.
  - hate: Float
    
    The score for the category 'hate'.
  - hate_threatening: Float
    
    The score for the category 'hate/threatening'.
  - illicit: Float
    
    The score for the category 'illicit'.
  - illicit_violent: Float
    
    The score for the category 'illicit/violent'.
  - self_harm: Float
    
    The score for the category 'self-harm'.
  - self_harm_instructions: Float
    
    The score for the category 'self-harm/instructions'.
  - self_harm_intent: Float
    
    The score for the category 'self-harm/intent'.
  - sexual: Float
    
    The score for the category 'sexual'.
  - sexual_minors: Float
    
    The score for the category 'sexual/minors'.
  - violence: Float
    
    The score for the category 'violence'.
  - violence_graphic: Float
    
    The score for the category 'violence/graphic'.
- flagged: bool
  
  Whether any of the below categories are flagged.

Moderation Image URL Input

class ModerationImageURLInput

An object describing an image to classify.
- image_url: ImageURL{ url}
  
  Contains either an image URL or a data URL for a base64 encoded image.
  - url: String
    
    Either a URL of the image or the base64 encoded image data.
- type: :image_url
  
  Always image_url.
  - :image_url

Moderation Model

ModerationModel = :"omni-moderation-latest" | :"omni-moderation-2024-09-26" | :"text-moderation-latest" | :"text-moderation-stable"
- :"omni-moderation-latest"
- :"omni-moderation-2024-09-26"
- :"text-moderation-latest"
- :"text-moderation-stable"

ModerationMultiModalInput = ModerationImageURLInput | ModerationTextInput

An object describing an image to classify.
- class ModerationImageURLInput
  
  An object describing an image to classify.
  - image_url: ImageURL{ url}
    
    Contains either an image URL or a data URL for a base64 encoded image.
    - url: String
      
      Either a URL of the image or the base64 encoded image data.
  - type: :image_url
    
    Always image_url.
    - :image_url
- class ModerationTextInput
  
  An object describing text to classify.
  - text: String
    
    A string of text to classify.
  - type: :text
    
    Always text.
    - :text

Moderation Text Input

class ModerationTextInput

An object describing text to classify.
- text: String
  
  A string of text to classify.
- type: :text
  
  Always text.
  - :text

Moderation Create Response

class ModerationCreateResponse

Represents if a given text input is potentially harmful.
- id: String
  
  The unique identifier for the moderation request.
- model: String
  
  The model used to generate the moderation results.
- results: Array[Moderation]
  
  A list of moderation objects.
  - categories: Categories{ harassment, harassment_threatening, hate, 10 more}
    
    A list of the categories, and whether they are flagged or not.
    - harassment: bool
      
      Content that expresses, incites, or promotes harassing language towards any target.
    - harassment_threatening: bool
      
      Harassment content that also includes violence or serious harm towards any target.
    - hate: bool
      
      Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment.
    - hate_threatening: bool
      
      Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.
    - illicit: bool
      
      Content that includes instructions or advice that facilitate the planning or execution of wrongdoing, or that gives advice or instruction on how to commit illicit acts. For example, "how to shoplift" would fit this category.
    - illicit_violent: bool
      
      Content that includes instructions or advice that facilitate the planning or execution of wrongdoing that also includes violence, or that gives advice or instruction on the procurement of any weapon.
    - self_harm: bool
      
      Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.
    - self_harm_instructions: bool
      
      Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts.
    - self_harm_intent: bool
      
      Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders.
    - sexual: bool
      
      Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).
    - sexual_minors: bool
      
      Sexual content that includes an individual who is under 18 years old.
    - violence: bool
      
      Content that depicts death, violence, or physical injury.
    - violence_graphic: bool
      
      Content that depicts death, violence, or physical injury in graphic detail.
  - category_applied_input_types: CategoryAppliedInputTypes{ harassment, harassment_threatening, hate, 10 more}
    
    A list of the categories along with the input type(s) that the score applies to.
    - harassment: Array[:text]
      
      The applied input type(s) for the category 'harassment'.
      - :text
    - harassment_threatening: Array[:text]
      
      The applied input type(s) for the category 'harassment/threatening'.
      - :text
    - hate: Array[:text]
      
      The applied input type(s) for the category 'hate'.
      - :text
    - hate_threatening: Array[:text]
      
      The applied input type(s) for the category 'hate/threatening'.
      - :text
    - illicit: Array[:text]
      
      The applied input type(s) for the category 'illicit'.
      - :text
    - illicit_violent: Array[:text]
      
      The applied input type(s) for the category 'illicit/violent'.
      - :text
    - self_harm: Array[:text | :image]
      
      The applied input type(s) for the category 'self-harm'.
      - :text
      - :image
    - self_harm_instructions: Array[:text | :image]
      
      The applied input type(s) for the category 'self-harm/instructions'.
      - :text
      - :image
    - self_harm_intent: Array[:text | :image]
      
      The applied input type(s) for the category 'self-harm/intent'.
      - :text
      - :image
    - sexual: Array[:text | :image]
      
      The applied input type(s) for the category 'sexual'.
      - :text
      - :image
    - sexual_minors: Array[:text]
      
      The applied input type(s) for the category 'sexual/minors'.
      - :text
    - violence: Array[:text | :image]
      
      The applied input type(s) for the category 'violence'.
      - :text
      - :image
    - violence_graphic: Array[:text | :image]
      
      The applied input type(s) for the category 'violence/graphic'.
      - :text
      - :image
  - category_scores: CategoryScores{ harassment, harassment_threatening, hate, 10 more}
    
    A list of the categories along with their scores as predicted by model.
    - harassment: Float
      
      The score for the category 'harassment'.
    - harassment_threatening: Float
      
      The score for the category 'harassment/threatening'.
    - hate: Float
      
      The score for the category 'hate'.
    - hate_threatening: Float
      
      The score for the category 'hate/threatening'.
    - illicit: Float
      
      The score for the category 'illicit'.
    - illicit_violent: Float
      
      The score for the category 'illicit/violent'.
    - self_harm: Float
      
      The score for the category 'self-harm'.
    - self_harm_instructions: Float
      
      The score for the category 'self-harm/instructions'.
    - self_harm_intent: Float
      
      The score for the category 'self-harm/intent'.
    - sexual: Float
      
      The score for the category 'sexual'.
    - sexual_minors: Float
      
      The score for the category 'sexual/minors'.
    - violence: Float
      
      The score for the category 'violence'.
    - violence_graphic: Float
      
      The score for the category 'violence/graphic'.
  - flagged: bool
    
    Whether any of the below categories are flagged.

ruby/resources/moderations/index.md +934 −0 created

1# Moderations

3## Create moderation

5`moderations.create(**kwargs) -> ModerationCreateResponse`

7**post** `/moderations`

9Classifies if text and/or image inputs are potentially harmful. Learn

10more in the [moderation guide](https://platform.openai.com/docs/guides/moderation).

12### Parameters

14- `input: String | Array[String] | Array[ModerationMultiModalInput]`

16 Input (or inputs) to classify. Can be a single string, an array of strings, or

17 an array of multi-modal input objects similar to other models.

19 - `String = String`

21 A string of text to classify for moderation.

23 - `UnionMember1 = Array[String]`

25 An array of strings to classify for moderation.

27 - `ModerationMultiModalArray = Array[ModerationMultiModalInput]`

29 An array of multi-modal inputs to the moderation model.

31 - `class ModerationImageURLInput`

33 An object describing an image to classify.

35 - `image_url: ImageURL{ url}`

37 Contains either an image URL or a data URL for a base64 encoded image.

39 - `url: String`

41 Either a URL of the image or the base64 encoded image data.

43 - `type: :image_url`

45 Always `image_url`.

47 - `:image_url`

49 - `class ModerationTextInput`

51 An object describing text to classify.

53 - `text: String`

55 A string of text to classify.

57 - `type: :text`

59 Always `text`.

61 - `:text`

63- `model: String | ModerationModel`

65 The content moderation model you would like to use. Learn more in

66 [the moderation guide](https://platform.openai.com/docs/guides/moderation), and learn about

67 available models [here](https://platform.openai.com/docs/models#moderation).

69 - `String = String`

71 - `ModerationModel = :"omni-moderation-latest" | :"omni-moderation-2024-09-26" | :"text-moderation-latest" | :"text-moderation-stable"`

73 - `:"omni-moderation-latest"`

75 - `:"omni-moderation-2024-09-26"`

77 - `:"text-moderation-latest"`

79 - `:"text-moderation-stable"`

81### Returns

83- `class ModerationCreateResponse`

85 Represents if a given text input is potentially harmful.

87 - `id: String`

89 The unique identifier for the moderation request.

91 - `model: String`

93 The model used to generate the moderation results.

95 - `results: Array[Moderation]`

97 A list of moderation objects.

99 - `categories: Categories{ harassment, harassment_threatening, hate, 10 more}`

100

101 A list of the categories, and whether they are flagged or not.

102

103 - `harassment: bool`

104

105 Content that expresses, incites, or promotes harassing language towards any target.

106

107 - `harassment_threatening: bool`

108

109 Harassment content that also includes violence or serious harm towards any target.

110

111 - `hate: bool`

112

113 Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment.

114

115 - `hate_threatening: bool`

116

117 Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.

118

119 - `illicit: bool`

120

121 Content that includes instructions or advice that facilitate the planning or execution of wrongdoing, or that gives advice or instruction on how to commit illicit acts. For example, "how to shoplift" would fit this category.

122

123 - `illicit_violent: bool`

124

125 Content that includes instructions or advice that facilitate the planning or execution of wrongdoing that also includes violence, or that gives advice or instruction on the procurement of any weapon.

126

127 - `self_harm: bool`

128

129 Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.

130

131 - `self_harm_instructions: bool`

132

133 Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts.

134

135 - `self_harm_intent: bool`

136

137 Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders.

138

139 - `sexual: bool`

140

141 Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).

142

143 - `sexual_minors: bool`

144

145 Sexual content that includes an individual who is under 18 years old.

146

147 - `violence: bool`

148

149 Content that depicts death, violence, or physical injury.

150

151 - `violence_graphic: bool`

152

153 Content that depicts death, violence, or physical injury in graphic detail.

154

155 - `category_applied_input_types: CategoryAppliedInputTypes{ harassment, harassment_threatening, hate, 10 more}`

156

157 A list of the categories along with the input type(s) that the score applies to.

158

159 - `harassment: Array[:text]`

160

161 The applied input type(s) for the category 'harassment'.

162

163 - `:text`

164

165 - `harassment_threatening: Array[:text]`

166

167 The applied input type(s) for the category 'harassment/threatening'.

168

169 - `:text`

170

171 - `hate: Array[:text]`

172

173 The applied input type(s) for the category 'hate'.

174

175 - `:text`

176

177 - `hate_threatening: Array[:text]`

178

179 The applied input type(s) for the category 'hate/threatening'.

180

181 - `:text`

182

183 - `illicit: Array[:text]`

184

185 The applied input type(s) for the category 'illicit'.

186

187 - `:text`

188

189 - `illicit_violent: Array[:text]`

190

191 The applied input type(s) for the category 'illicit/violent'.

192

193 - `:text`

194

195 - `self_harm: Array[:text | :image]`

196

197 The applied input type(s) for the category 'self-harm'.

198

199 - `:text`

200

201 - `:image`

202

203 - `self_harm_instructions: Array[:text | :image]`

204

205 The applied input type(s) for the category 'self-harm/instructions'.

206

207 - `:text`

208

209 - `:image`

210

211 - `self_harm_intent: Array[:text | :image]`

212

213 The applied input type(s) for the category 'self-harm/intent'.

214

215 - `:text`

216

217 - `:image`

218

219 - `sexual: Array[:text | :image]`

220

221 The applied input type(s) for the category 'sexual'.

222

223 - `:text`

224

225 - `:image`

226

227 - `sexual_minors: Array[:text]`

228

229 The applied input type(s) for the category 'sexual/minors'.

230

231 - `:text`

232

233 - `violence: Array[:text | :image]`

234

235 The applied input type(s) for the category 'violence'.

236

237 - `:text`

238

239 - `:image`

240

241 - `violence_graphic: Array[:text | :image]`

242

243 The applied input type(s) for the category 'violence/graphic'.

244

245 - `:text`

246

247 - `:image`

248

249 - `category_scores: CategoryScores{ harassment, harassment_threatening, hate, 10 more}`

250

251 A list of the categories along with their scores as predicted by model.

252

253 - `harassment: Float`

254

255 The score for the category 'harassment'.

256

257 - `harassment_threatening: Float`

258

259 The score for the category 'harassment/threatening'.

260

261 - `hate: Float`

262

263 The score for the category 'hate'.

264

265 - `hate_threatening: Float`

266

267 The score for the category 'hate/threatening'.

268

269 - `illicit: Float`

270

271 The score for the category 'illicit'.

272

273 - `illicit_violent: Float`

274

275 The score for the category 'illicit/violent'.

276

277 - `self_harm: Float`

278

279 The score for the category 'self-harm'.

280

281 - `self_harm_instructions: Float`

282

283 The score for the category 'self-harm/instructions'.

284

285 - `self_harm_intent: Float`

286

287 The score for the category 'self-harm/intent'.

288

289 - `sexual: Float`

290

291 The score for the category 'sexual'.

292

293 - `sexual_minors: Float`

294

295 The score for the category 'sexual/minors'.

296

297 - `violence: Float`

298

299 The score for the category 'violence'.

300

301 - `violence_graphic: Float`

302

303 The score for the category 'violence/graphic'.

304

305 - `flagged: bool`

306

307 Whether any of the below categories are flagged.

308

309### Example

310

311```ruby

312require "openai"

313

314openai = OpenAI::Client.new(api_key: "My API Key")

315

316moderation = openai.moderations.create(input: "I want to kill them.")

317

318puts(moderation)

319```

320

321#### Response

322

323```json

324{

325 "id": "id",

326 "model": "model",

327 "results": [

328 {

329 "categories": {

330 "harassment": true,

331 "harassment/threatening": true,

332 "hate": true,

333 "hate/threatening": true,

334 "illicit": true,

335 "illicit/violent": true,

336 "self-harm": true,

337 "self-harm/instructions": true,

338 "self-harm/intent": true,

339 "sexual": true,

340 "sexual/minors": true,

341 "violence": true,

342 "violence/graphic": true

343 },

344 "category_applied_input_types": {

345 "harassment": [

346 "text"

347 ],

348 "harassment/threatening": [

349 "text"

350 ],

351 "hate": [

352 "text"

353 ],

354 "hate/threatening": [

355 "text"

356 ],

357 "illicit": [

358 "text"

359 ],

360 "illicit/violent": [

361 "text"

362 ],

363 "self-harm": [

364 "text"

365 ],

366 "self-harm/instructions": [

367 "text"

368 ],

369 "self-harm/intent": [

370 "text"

371 ],

372 "sexual": [

373 "text"

374 ],

375 "sexual/minors": [

376 "text"

377 ],

378 "violence": [

379 "text"

380 ],

381 "violence/graphic": [

382 "text"

383 ]

384 },

385 "category_scores": {

386 "harassment": 0,

387 "harassment/threatening": 0,

388 "hate": 0,

389 "hate/threatening": 0,

390 "illicit": 0,

391 "illicit/violent": 0,

392 "self-harm": 0,

393 "self-harm/instructions": 0,

394 "self-harm/intent": 0,

395 "sexual": 0,

396 "sexual/minors": 0,

397 "violence": 0,

398 "violence/graphic": 0

399 },

400 "flagged": true

401 }

402 ]

403}

404```

405

406## Domain Types

407

408### Moderation

409

410- `class Moderation`

411

412 - `categories: Categories{ harassment, harassment_threatening, hate, 10 more}`

413

414 A list of the categories, and whether they are flagged or not.

415

416 - `harassment: bool`

417

418 Content that expresses, incites, or promotes harassing language towards any target.

419

420 - `harassment_threatening: bool`

421

422 Harassment content that also includes violence or serious harm towards any target.

423

424 - `hate: bool`

425

426 Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment.

427

428 - `hate_threatening: bool`

429

430 Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.

431

432 - `illicit: bool`

433

434 Content that includes instructions or advice that facilitate the planning or execution of wrongdoing, or that gives advice or instruction on how to commit illicit acts. For example, "how to shoplift" would fit this category.

435

436 - `illicit_violent: bool`

437

438 Content that includes instructions or advice that facilitate the planning or execution of wrongdoing that also includes violence, or that gives advice or instruction on the procurement of any weapon.

439

440 - `self_harm: bool`

441

442 Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.

443

444 - `self_harm_instructions: bool`

445

446 Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts.

447

448 - `self_harm_intent: bool`

449

450 Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders.

451

452 - `sexual: bool`

453

454 Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).

455

456 - `sexual_minors: bool`

457

458 Sexual content that includes an individual who is under 18 years old.

459

460 - `violence: bool`

461

462 Content that depicts death, violence, or physical injury.

463

464 - `violence_graphic: bool`

465

466 Content that depicts death, violence, or physical injury in graphic detail.

467

468 - `category_applied_input_types: CategoryAppliedInputTypes{ harassment, harassment_threatening, hate, 10 more}`

469

470 A list of the categories along with the input type(s) that the score applies to.

471

472 - `harassment: Array[:text]`

473

474 The applied input type(s) for the category 'harassment'.

475

476 - `:text`

477

478 - `harassment_threatening: Array[:text]`

479

480 The applied input type(s) for the category 'harassment/threatening'.

481

482 - `:text`

483

484 - `hate: Array[:text]`

485

486 The applied input type(s) for the category 'hate'.

487

488 - `:text`

489

490 - `hate_threatening: Array[:text]`

491

492 The applied input type(s) for the category 'hate/threatening'.

493

494 - `:text`

495

496 - `illicit: Array[:text]`

497

498 The applied input type(s) for the category 'illicit'.

499

500 - `:text`

501

502 - `illicit_violent: Array[:text]`

503

504 The applied input type(s) for the category 'illicit/violent'.

505

506 - `:text`

507

508 - `self_harm: Array[:text | :image]`

509

510 The applied input type(s) for the category 'self-harm'.

511

512 - `:text`

513

514 - `:image`

515

516 - `self_harm_instructions: Array[:text | :image]`

517

518 The applied input type(s) for the category 'self-harm/instructions'.

519

520 - `:text`

521

522 - `:image`

523

524 - `self_harm_intent: Array[:text | :image]`

525

526 The applied input type(s) for the category 'self-harm/intent'.

527

528 - `:text`

529

530 - `:image`

531

532 - `sexual: Array[:text | :image]`

533

534 The applied input type(s) for the category 'sexual'.

535

536 - `:text`

537

538 - `:image`

539

540 - `sexual_minors: Array[:text]`

541

542 The applied input type(s) for the category 'sexual/minors'.

543

544 - `:text`

545

546 - `violence: Array[:text | :image]`

547

548 The applied input type(s) for the category 'violence'.

549

550 - `:text`

551

552 - `:image`

553

554 - `violence_graphic: Array[:text | :image]`

555

556 The applied input type(s) for the category 'violence/graphic'.

557

558 - `:text`

559

560 - `:image`

561

562 - `category_scores: CategoryScores{ harassment, harassment_threatening, hate, 10 more}`

563

564 A list of the categories along with their scores as predicted by model.

565

566 - `harassment: Float`

567

568 The score for the category 'harassment'.

569

570 - `harassment_threatening: Float`

571

572 The score for the category 'harassment/threatening'.

573

574 - `hate: Float`

575

576 The score for the category 'hate'.

577

578 - `hate_threatening: Float`

579

580 The score for the category 'hate/threatening'.

581

582 - `illicit: Float`

583

584 The score for the category 'illicit'.

585

586 - `illicit_violent: Float`

587

588 The score for the category 'illicit/violent'.

589

590 - `self_harm: Float`

591

592 The score for the category 'self-harm'.

593

594 - `self_harm_instructions: Float`

595

596 The score for the category 'self-harm/instructions'.

597

598 - `self_harm_intent: Float`

599

600 The score for the category 'self-harm/intent'.

601

602 - `sexual: Float`

603

604 The score for the category 'sexual'.

605

606 - `sexual_minors: Float`

607

608 The score for the category 'sexual/minors'.

609

610 - `violence: Float`

611

612 The score for the category 'violence'.

613

614 - `violence_graphic: Float`

615

616 The score for the category 'violence/graphic'.

617

618 - `flagged: bool`

619

620 Whether any of the below categories are flagged.

621

622### Moderation Image URL Input

623

624- `class ModerationImageURLInput`

625

626 An object describing an image to classify.

627

628 - `image_url: ImageURL{ url}`

629

630 Contains either an image URL or a data URL for a base64 encoded image.

631

632 - `url: String`

633

634 Either a URL of the image or the base64 encoded image data.

635

636 - `type: :image_url`

637

638 Always `image_url`.

639

640 - `:image_url`

641

642### Moderation Model

643

644- `ModerationModel = :"omni-moderation-latest" | :"omni-moderation-2024-09-26" | :"text-moderation-latest" | :"text-moderation-stable"`

645

646 - `:"omni-moderation-latest"`

647

648 - `:"omni-moderation-2024-09-26"`

649

650 - `:"text-moderation-latest"`

651

652 - `:"text-moderation-stable"`

653

654### Moderation Multi Modal Input

655

656- `ModerationMultiModalInput = ModerationImageURLInput | ModerationTextInput`

657

658 An object describing an image to classify.

659

660 - `class ModerationImageURLInput`

661

662 An object describing an image to classify.

663

664 - `image_url: ImageURL{ url}`

665

666 Contains either an image URL or a data URL for a base64 encoded image.

667

668 - `url: String`

669

670 Either a URL of the image or the base64 encoded image data.

671

672 - `type: :image_url`

673

674 Always `image_url`.

675

676 - `:image_url`

677

678 - `class ModerationTextInput`

679

680 An object describing text to classify.

681

682 - `text: String`

683

684 A string of text to classify.

685

686 - `type: :text`

687

688 Always `text`.

689

690 - `:text`

691

692### Moderation Text Input

693

694- `class ModerationTextInput`

695

696 An object describing text to classify.

697

698 - `text: String`

699

700 A string of text to classify.

701

702 - `type: :text`

703

704 Always `text`.

705

706 - `:text`

707

708### Moderation Create Response

709

710- `class ModerationCreateResponse`

711

712 Represents if a given text input is potentially harmful.

713

714 - `id: String`

715

716 The unique identifier for the moderation request.

717

718 - `model: String`

719

720 The model used to generate the moderation results.

721

722 - `results: Array[Moderation]`

723

724 A list of moderation objects.

725

726 - `categories: Categories{ harassment, harassment_threatening, hate, 10 more}`

727

728 A list of the categories, and whether they are flagged or not.

729

730 - `harassment: bool`

731

732 Content that expresses, incites, or promotes harassing language towards any target.

733

734 - `harassment_threatening: bool`

735

736 Harassment content that also includes violence or serious harm towards any target.

737

738 - `hate: bool`

739

740 Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment.

741

742 - `hate_threatening: bool`

743

744 Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste.

745

746 - `illicit: bool`

747

748 Content that includes instructions or advice that facilitate the planning or execution of wrongdoing, or that gives advice or instruction on how to commit illicit acts. For example, "how to shoplift" would fit this category.

749

750 - `illicit_violent: bool`

751

752 Content that includes instructions or advice that facilitate the planning or execution of wrongdoing that also includes violence, or that gives advice or instruction on the procurement of any weapon.

753

754 - `self_harm: bool`

755

756 Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.

757

758 - `self_harm_instructions: bool`

759

760 Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts.

761

762 - `self_harm_intent: bool`

763

764 Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders.

765

766 - `sexual: bool`

767

768 Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness).

769

770 - `sexual_minors: bool`

771

772 Sexual content that includes an individual who is under 18 years old.

773

774 - `violence: bool`

775

776 Content that depicts death, violence, or physical injury.

777

778 - `violence_graphic: bool`

779

780 Content that depicts death, violence, or physical injury in graphic detail.

781

782 - `category_applied_input_types: CategoryAppliedInputTypes{ harassment, harassment_threatening, hate, 10 more}`

783

784 A list of the categories along with the input type(s) that the score applies to.

785

786 - `harassment: Array[:text]`

787

788 The applied input type(s) for the category 'harassment'.

789

790 - `:text`

791

792 - `harassment_threatening: Array[:text]`

793

794 The applied input type(s) for the category 'harassment/threatening'.

795

796 - `:text`

797

798 - `hate: Array[:text]`

799

800 The applied input type(s) for the category 'hate'.

801

802 - `:text`

803

804 - `hate_threatening: Array[:text]`

805

806 The applied input type(s) for the category 'hate/threatening'.

807

808 - `:text`

809

810 - `illicit: Array[:text]`

811

812 The applied input type(s) for the category 'illicit'.

813

814 - `:text`

815

816 - `illicit_violent: Array[:text]`

817

818 The applied input type(s) for the category 'illicit/violent'.

819

820 - `:text`

821

822 - `self_harm: Array[:text | :image]`

823

824 The applied input type(s) for the category 'self-harm'.

825

826 - `:text`

827

828 - `:image`

829

830 - `self_harm_instructions: Array[:text | :image]`

831

832 The applied input type(s) for the category 'self-harm/instructions'.

833

834 - `:text`

835

836 - `:image`

837

838 - `self_harm_intent: Array[:text | :image]`

839

840 The applied input type(s) for the category 'self-harm/intent'.

841

842 - `:text`

843

844 - `:image`

845

846 - `sexual: Array[:text | :image]`

847

848 The applied input type(s) for the category 'sexual'.

849

850 - `:text`

851

852 - `:image`

853

854 - `sexual_minors: Array[:text]`

855

856 The applied input type(s) for the category 'sexual/minors'.

857

858 - `:text`

859

860 - `violence: Array[:text | :image]`

861

862 The applied input type(s) for the category 'violence'.

863

864 - `:text`

865

866 - `:image`

867

868 - `violence_graphic: Array[:text | :image]`

869

870 The applied input type(s) for the category 'violence/graphic'.

871

872 - `:text`

873

874 - `:image`

875

876 - `category_scores: CategoryScores{ harassment, harassment_threatening, hate, 10 more}`

877

878 A list of the categories along with their scores as predicted by model.

879

880 - `harassment: Float`

881

882 The score for the category 'harassment'.

883

884 - `harassment_threatening: Float`

885

886 The score for the category 'harassment/threatening'.

887

888 - `hate: Float`

889

890 The score for the category 'hate'.

891

892 - `hate_threatening: Float`

893

894 The score for the category 'hate/threatening'.

895

896 - `illicit: Float`

897

898 The score for the category 'illicit'.

899

900 - `illicit_violent: Float`

901

902 The score for the category 'illicit/violent'.

903

904 - `self_harm: Float`

905

906 The score for the category 'self-harm'.

907

908 - `self_harm_instructions: Float`

909

910 The score for the category 'self-harm/instructions'.

911

912 - `self_harm_intent: Float`

913

914 The score for the category 'self-harm/intent'.

915

916 - `sexual: Float`

917

918 The score for the category 'sexual'.

919

920 - `sexual_minors: Float`

921

922 The score for the category 'sexual/minors'.

923

924 - `violence: Float`

925

926 The score for the category 'violence'.

927

928 - `violence_graphic: Float`

929

930 The score for the category 'violence/graphic'.

931

932 - `flagged: bool`

933

934 Whether any of the below categories are flagged.