Eden AI Explicit Content API

openapi: 3.2.0
info:
  title: Image Features Explicit Content API
  version: '2.0'
  description: Your project description
servers:
- url: https://api.edenai.run/v2
tags:
- name: Explicit Content
paths:
  /image/explicit_content/:
    post:
      operationId: image_explicit_content_create
      description: 'Available Providers


        |Provider|Model|Version|Price|Billing unit|

        |----|----|-------|-----|------------|

        |**amazon**|-|`boto3 (v1.15.18)`|1.0 (per 1000 file)|1 file

        |**google**|-|`v1`|1.5 (per 1000 file)|1 file

        |**microsoft**|-|`v3.2`|1.0 (per 1000 file)|1 file

        |**sentisight**|-|`v3.3.1`|0.75 (per 1000 file)|1 file

        |**openai**|**gpt-4o**|`v1`|24.0 (per 1000 file)|1 file

        |**openai**|-|`v1`|24.0 (per 1000 file)|1 file


        Supported Models


        Default Models


        |Name|Value|

        |----|-----|

        |**openai**|`gpt-4o`|'
      summary: Explicit Content Detection
      tags:
      - Explicit Content
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/imageanonymizationimagelandmark_detectionimageexplicit_contentimagedeepfake_detectionImageRequest'
            examples:
              RequestExample:
                value:
                  providers: amazon,google,microsoft,sentisight,openai
                  file_url: http://edenai-resource-example.jpg
                summary: Request Example
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/imageanonymizationimagelandmark_detectionimageexplicit_contentimagedeepfake_detectionImageRequest'
            examples:
              RequestExample:
                value:
                  providers: amazon,google,microsoft,sentisight,openai
                  file: /edenai/edenai/features/image/samples/data/explicit_content.jpeg
                summary: Request Example
        required: true
      security:
      - FeatureApiAuth: []
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/imageexplicit_contentResponseModel'
              examples:
                ResponseExample:
                  value:
                    amazon:
                      nsfw_likelihood: 5
                      nsfw_likelihood_score: 0.9282218933105468
                      items:
                      - label: Graphic Violence Or Gore
                        likelihood: 5
                        likelihood_score: 0.9282218933105468
                        category: Violence
                        subcategory: GraphicViolenceOrGore
                      - label: Violence
                        likelihood: 5
                        likelihood_score: 0.9282218933105468
                        category: Violence
                        subcategory: Violence
                      cost: 0.0
                    google:
                      nsfw_likelihood: 3
                      nsfw_likelihood_score: 0.6
                      items:
                      - label: Adult
                        likelihood: 1
                        likelihood_score: 0.2
                        category: Sexual
                        subcategory: Sexual
                      - label: Spoof
                        likelihood: 1
                        likelihood_score: 0.2
                        category: Other
                        subcategory: Spoof
                      - label: Medical
                        likelihood: 3
                        likelihood_score: 0.6
                        category: Content
                        subcategory: Medical
                      - label: Violence
                        likelihood: 3
                        likelihood_score: 0.6
                        category: Violence
                        subcategory: Violence
                      - label: Racy
                        likelihood: 1
                        likelihood_score: 0.2
                        category: HateAndExtremism
                        subcategory: Racy
                      cost: 0.0
                    microsoft:
                      nsfw_likelihood: 3
                      nsfw_likelihood_score: 0.5288681387901306
                      items:
                      - label: Gore
                        likelihood: 3
                        likelihood_score: 0.5288681387901306
                        category: Violence
                        subcategory: GraphicViolenceOrGore
                      - label: Adult
                        likelihood: 1
                        likelihood_score: 0.00892699882388115
                        category: Sexual
                        subcategory: Sexual
                      - label: Racy
                        likelihood: 1
                        likelihood_score: 0.011913839727640152
                        category: HateAndExtremism
                        subcategory: Racy
                      cost: 0.0
                    sentisight:
                      nsfw_likelihood: 0
                      nsfw_likelihood_score: 0.0
                      items:
                      - label: nudity
                        likelihood: 0
                        likelihood_score: 0.0
                        category: Sexual
                        subcategory: Nudity
                      cost: 0.0
                    openai:
                      nsfw_likelihood: 3
                      nsfw_likelihood_score: 0.81
                      items:
                      - label: Gore
                        likelihood: 4
                        likelihood_score: 0.85
                        category: Violence
                        subcategory: null
                      - label: Adult
                        likelihood: 1
                        likelihood_score: 0.05
                        category: Sexual
                        subcategory: null
                      - label: Racy
                        likelihood: 1
                        likelihood_score: 0.02
                        category: HateAndExtremism
                        subcategory: null
                      usage:
                        completion_tokens: 147
                        prompt_tokens: 1437
                        total_tokens: 1584
                        completion_tokens_details:
                          accepted_prediction_tokens: 0
                          audio_tokens: 0
                          reasoning_tokens: 0
                          rejected_prediction_tokens: 0
                        prompt_tokens_details:
                          audio_tokens: 0
                          cached_tokens: 0
                      cost: 0.0
                  summary: Response Example
          description: ''
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequest'
          description: ''
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
          description: ''
        '403':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
          description: ''
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundResponse'
          description: ''
components:
  schemas:
    BadRequest:
      type: object
      properties:
        error:
          $ref: '#/components/schemas/NestedBadRequest'
      required:
      - error
    imageexplicit_contentExplicitContentDataClass:
      properties:
        nsfw_likelihood:
          description: An integer representing the likelihood of NSFW content. Higher values indicate a higher likelihood.
          title: Nsfw Likelihood
          type: integer
        nsfw_likelihood_score:
          description: A floating-point score representing the confidence level of the NSFW likelihood assessment. This is typically a value between 0.0 and 1.0.
          title: Nsfw Likelihood Score
          type: integer
        items:
          description: A list of items identified as potentially explicit. Each item contains details of the explicit content detected.
          items:
            $ref: '#/components/schemas/ExplicitItem'
          title: Items
          type: array
        original_response:
          default: null
          description: original response sent by the provider, hidden by default, show it by passing the `show_original_response` field to `true` in your request
          title: Original Response
        status:
          allOf:
          - $ref: '#/components/schemas/StatusEnum'
          title: Status
      required:
      - nsfw_likelihood
      - nsfw_likelihood_score
      - status
      title: imageexplicit_contentExplicitContentDataClass
      type: object
    NotFoundResponse:
      type: object
      properties:
        details:
          type: string
          default: Not Found
    imageexplicit_contentResponseModel:
      properties:
        openai:
          $ref: '#/components/schemas/imageexplicit_contentExplicitContentDataClass'
          default: null
        clarifai:
          $ref: '#/components/schemas/imageexplicit_contentExplicitContentDataClass'
          default: null
        amazon:
          $ref: '#/components/schemas/imageexplicit_contentExplicitContentDataClass'
          default: null
        microsoft:
          $ref: '#/components/schemas/imageexplicit_contentExplicitContentDataClass'
          default: null
        api4ai:
          $ref: '#/components/schemas/imageexplicit_contentExplicitContentDataClass'
          default: null
        sentisight:
          $ref: '#/components/schemas/imageexplicit_contentExplicitContentDataClass'
          default: null
        google:
          $ref: '#/components/schemas/imageexplicit_contentExplicitContentDataClass'
          default: null
      title: imageexplicit_contentResponseModel
      type: object
    FieldError:
      type: object
      properties:
        <parameter_name>:
          type: array
          items:
            type: string
      required:
      - <parameter_name>
    Error:
      type: object
      properties:
        error:
          $ref: '#/components/schemas/NestedError'
      required:
      - error
    imageanonymizationimagelandmark_detectionimageexplicit_contentimagedeepfake_detectionImageRequest:
      type: object
      properties:
        settings:
          type: string
          default: {}
          description: "A dictionnary or a json object to specify specific models to use for some providers. <br>                     It can be in the following format: {\"google\" : \"google_model\", \"ibm\": \"ibm_model\"...}.\n                     "
        providers:
          type: array
          items:
            type: string
            minLength: 1
          description: 'It can be one (ex: **''amazon''** or **''google''**) or multiple provider(s) (ex: **''amazon,microsoft,google''**)             that the data will be redirected to in order to get the processed results.<br>             Providers can also be invoked with specific models (ex: providers: **''amazon/model1, amazon/model2, google/model3''**)'
        fallback_providers:
          type: array
          items:
            type: string
          default: []
          description: "Providers in this list will be used as fallback if the call to provider in `providers` parameter fails.\n    To use this feature, you must input **only one** provider in the `providers` parameter. but you can put up to 5 fallbacks.\n\nThey will be tried in the same order they are input, and it will stop to the first provider who doesn't fail.\n\n\n*Doesn't work with async subfeatures.*\n    "
          maxItems: 5
        response_as_dict:
          type: boolean
          default: true
          description: "Optional : When set to **true** (default), the response is an object of responses with providers names as keys : <br> \n                  ``` {\"google\" : { \"status\": \"success\", ... }, } ``` <br>\n                When set to **false** the response structure is a list of response objects : <br> \n                   ``` [{\"status\": \"success\", \"provider\": \"google\" ... }, ] ```. <br>\n                  "
        attributes_as_list:
          type: boolean
          default: false
          description: "Optional : When set to **false** (default) the structure of the extracted items is list of objects having different attributes : <br>\n     ```{'items': [{\"attribute_1\": \"x1\",\"attribute_2\": \"y2\"}, ... ]}``` <br>\n     When it is set to **true**, the response contains an object with each attribute as a list : <br>\n     ```{ \"attribute_1\": [\"x1\",\"x2\", ...], \"attribute_2\": [y1, y2, ...]}``` "
        show_base_64:
          type: boolean
          default: true
        show_original_response:
          type: boolean
          default: false
          description: "Optional : Shows the original response of the provider.<br>\n        When set to **true**, a new attribute *original_response* will appear in the response object."
        file:
          type: string
          format: binary
          description: 'File to analyse in binary format to be used with *content-type*: **multipart/form-data** <br> **Does not work with application/json !**'
          pattern: (?:jpg|jpeg|png|tiff)$
        file_url:
          type:
          - string
          - 'null'
          format: uri
          description: 'File **URL** to analyse to be used with with *content-type*: **application/json**.'
      required:
      - providers
    ExplicitItem:
      properties:
        label:
          description: ''
          title: Label
          type: string
        likelihood:
          description: ''
          title: Likelihood
          type: integer
        likelihood_score:
          description: ''
          title: Likelihood Score
          type: integer
        category:
          $ref: '#/components/schemas/CategoryType'
          description: 'The category of the detected content. Possible values include: ''Toxic'', ''Content'', ''Sexual'', ''Violence'', ''DrugAndAlcohol'', ''Finance'', ''HateAndExtremism'', ''Safe'', ''Other''.'
        subcategory:
          description: 'The subcategory of content. Possible values:


            Toxic Subcategories:

            - Insult

            - Obscene

            - Derogatory

            - Profanity

            - Threat

            - Toxic


            Content Subcategories:

            - MiddleFinger

            - PublicSafety

            - Health

            - Explicit

            - QRCode

            - Medical

            - Politics

            - Legal


            Sexual Subcategories:

            - SexualActivity

            - SexualSituations

            - Nudity

            - PartialNudity

            - Suggestive

            - AdultToys

            - RevealingClothes

            - Sexual


            Violence Subcategories:

            - GraphicViolenceOrGore

            - PhysicalViolence

            - WeaponViolence

            - Violence


            Drug and Alcohol Subcategories:

            - DrugProducts

            - DrugUse

            - Tobacco

            - Smoking

            - Alcohol

            - Drinking


            Finance Subcategories:

            - Gambling

            - Finance

            - MoneyContent


            Hate and Extremism Subcategories:

            - Hate

            - Harassment

            - Threatening

            - Extremist

            - Racy


            Safe Subcategories:

            - Safe

            - NotSafe


            Other Subcategories:

            - Spoof

            - Religion

            - Offensive

            - Other'
          title: Subcategory
          type: string
      required:
      - label
      - likelihood
      - likelihood_score
      - category
      - subcategory
      title: ExplicitItem
      type: object
    CategoryType:
      description: This enum are used to categorize the explicit content extracted from the text
      enum:
      - Toxic
      - Content
      - Sexual
      - Violence
      - DrugAndAlcohol
      - Finance
      - HateAndExtremism
      - Safe
      - Other
      title: CategoryType
      type: string
    StatusEnum:
      enum:
      - sucess
      - fail
      type: string
    NestedError:
      type: object
      properties:
        type:
          type: string
        message:
          type: string
      required:
      - message
      - type
    NestedBadRequest:
      type: object
      properties:
        type:
          type: string
        message:
          $ref: '#/components/schemas/FieldError'
      required:
      - message
      - type
  securitySchemes:
    FeatureApiAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT