API Endpoints
OpenAI Moderation
This evaluator uses OpenAI’s moderation API to detect potentially harmful content in text, including harassment, hate speech, self-harm, sexual content, and violence.
Env vars: OPENAI_API_KEY
Docs: https://platform.openai.com/docs/guides/moderation/overview
POST
/
openai
/
moderation
/
evaluate
Body
application/json
List of entries to be evaluated, check the field type for the necessary keys
Evaluator settings, check the field type for what settings this evaluator supports
Optional environment variables to override the server ones
Response
200 - application/json
Available options:
processed
The model's confidence on primary category where the input violates the OpenAI's policy. The value is between 0 and 1, where higher values denote higher confidence.
Short human-readable description of the result