The Feature

Like what is done for callback logging, disable prompts+messages log in db for specified models (eg embeddings) or via request headers like what is done with x-litellm-enable-message-redaction

Motivation, pitch

Usecase:
disable storage of response from /embeddings queries that are quite big

LiteLLM is hiring a founding backend engineer, are you interested in joining us and shipping to all our users?

No

Twitter / LinkedIn details

No response