OpenAI /v1/moderations — Amazon Comprehend toxicity

[JGoutin]

Implement OpenAI-compatible content moderation endpoint backed by Amazon Comprehend toxicity detection.

• POST /v1/moderations

REF:

• https://platform.openai.com/docs/api-reference/moderations
• https://docs.aws.amazon.com/comprehend/latest/dg/trust-safety-toxicity.html