Skip to content

use OpenAI's moderation endpoint

Ilias Sarantopoulos requested to merge add-moderation-T329058 into main

We are using the moderation endpoint provided by OpenAI to filter the response if it is classified to belong in any of the following categories:

  • hate
  • hate/threatening
  • self-harm
  • sexual
  • sexual/minors
  • violence
  • violence/graphic

More info in the OpenAi docs https://platform.openai.com/docs/guides/moderation/overview

Bug: T329058

Merge request reports