Text
4 min
nima allows you to automatically detect text using powerful ai detection providers example payload { "channel" "automated detection", "reason for request" "lorem abuse reason for request", "content" { "content id" "450100000tete", "title" "offensive content that matches with a bullying situation", "body" "lorem ipsum is simply dummy text of the printing and typesetting industry lorem ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book ", "rawtext" "hello, fat weirdo ", "language" "en", "token" "", "type" { "id" "txt" }, "status" "published", "customerspecific" { "boolean attribute" "true" } }, "reportee" { "id" "40644", "name" "reportee luke", "phonenumber" "070 504143", "emailaddress" "example\@gmail com", "customerspecific" { "boolean test" "true" } }, "location" { "city" "stockholm", "postalcode" "111 57", "region" "stockholm", "countrycode" "se", "ipaddress" "192 168 0 1", "customerspecific" {} } } request payload requirements for text moderation, ensure your request payload includes the following content type specific requirements attribute required description content type id yes must be set to "txt" content rawtext yes the body of the text being moderated is to be passed here content language yes if content rawtext is passed iso language code in lowercase (en, fr) content url no do not pass content url when using text moderation configuring detection rules to create a rule for automated text detection, navigate to admin settings > workflow configuration and define the following conditions required conditions channel must be set to "proactive detection" content type must be set to "text" once these conditions are set, the list of available ai detection providers will be accessible via the choose provider button language support for optimal speed and accuracy, nima allows you to specify the expected language(s) of the content being sent for detection specifying languages you can pass a comma separated list of language codes (e g , lang=en,fr,es ) this should be included in the customerspecific node at the root level of the json payload sent to the api endpoint recommendation we strongly recommend specifying the shortest possible list of languages your users are likely to use, as this yields better results in both speed and accuracy if your users are predominantly english speakers, specifying only en will be most effective other languages are available upon request please contact support regarding your specific language needs