Hi All,
I am thinking of using Rasa Bot for chat moderation with my custom-trained NLP model to detect negative comments. Can I customize the Rasa Bot for this purpose?
For example, consider a chat room scenario. User A is trying to send a racist text to User B, my intention was to use a chat bot to detect the toxicity of the message and it should stop the User A to send the message or send the masked message with *.