litellm
litellm copied to clipboard
[Feature]: Implement OpenAI moderation as a guardrail
The Feature
being able to pass every prompt to the openai omni moderation model before sending it to the requested model
Motivation, pitch
it will reduce the cost of sending bad prompt to a model and pay for tokens
Are you a ML Ops Team?
Yes
Twitter / LinkedIn details
No response
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.