Merge pull request #72 from RobertCraigie/robert/update-moderations

Update moderation categories to match docs

Author: schnerd

openapi.yaml

@@ -2682,29 +2682,45 @@ components:
                 properties:
                   hate:
                     type: boolean
-                    description: Whether the content was flagged as 'hate'.
+                    description: 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 harrassment.
                   hate/threatening:
                     type: boolean
-                    description: Whether the content was flagged as 'hate/threatening'.
+                    description: 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.
+                  harassment:
+                    type: boolean
+                    description: Content that expresses, incites, or promotes harassing language towards any target.
+                  harassment/threatening:
+                    type: boolean
+                    description: Harassment content that also includes violence or serious harm towards any target.
                   self-harm:
                     type: boolean
-                    description: Whether the content was flagged as 'self-harm'.
+                    description: Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders.
+                  self-harm/intent:
+                    type: boolean
+                    description: 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.
+                  self-harm/instructions:
+                    type: boolean
+                    description: 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.
                   sexual:
                     type: boolean
-                    description: Whether the content was flagged as 'sexual'.
+                    description: 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:
                     type: boolean
-                    description: Whether the content was flagged as 'sexual/minors'.
+                    description: Sexual content that includes an individual who is under 18 years old.
                   violence:
                     type: boolean
-                    description: Whether the content was flagged as 'violence'.
+                    description: Content that depicts death, violence, or physical injury.
                   violence/graphic:
                     type: boolean
-                    description: Whether the content was flagged as 'violence/graphic'.
+                    description: Content that depicts death, violence, or physical injury in graphic detail.
                 required:
                   - hate
                   - hate/threatening
+                  - harassment
+                  - harassment/threatening
                   - self-harm
+                  - self-harm/intent
+                  - self-harm/instructions
                   - sexual
                   - sexual/minors
                   - violence
@@ -2719,9 +2735,21 @@ components:
                   hate/threatening:
                     type: number
                     description: The score for the category 'hate/threatening'.
+                  harassment:
+                    type: number
+                    description: The score for the category 'harassment'.
+                  harassment/threatening:
+                    type: number
+                    description: The score for the category 'harassment/threatening'.
                   self-harm:
                     type: number
                     description: The score for the category 'self-harm'.
+                  self-harm/intent:
+                    type: number
+                    description: The score for the category 'self-harm/intent'.
+                  self-harm/instructions:
+                    type: number
+                    description: The score for the category 'self-harm/instructions'.
                   sexual:
                     type: number
                     description: The score for the category 'sexual'.
@@ -2737,7 +2765,11 @@ components:
                 required:
                   - hate
                   - hate/threatening
+                  - harassment
+                  - harassment/threatening
                   - self-harm
+                  - self-harm/intent
+                  - self-harm/instructions
                   - sexual
                   - sexual/minors
                   - violence