A single-model text moderation workflow that combines classification and embedding functions to classify harmful text content.

Overview
No input available.

Notes

A single-model text moderation workflow that combines classification and embedding functions to classify harmful text content.

This workflow has 2 branches: a) text-classifier (moderation english), b) text-embed (moderation multilingual)

  • Workflow ID
    Text-Moderation
  • Description
    A single-model text moderation workflow that combines classification and embedding functions to classify harmful text content.
  • Last Updated
    Jan 30, 2022
  • Privacy
    PUBLIC
  • Share