I’m trying to send this user parameter from the SDK call and the REST API as recommended in How to Incorporate a UserID | OpenAI Help Center, but I’m not able to actually view the value I set in the response.
Is there any way I can get back the value I set in the user-id, so that I can perform my own abuse monitoring on users?
Not sure I follow your logic here “get back the value I set in the user-id” if you set it, you know what it is? Should be a simple matter of logging that value along with the API call prompt and reply and time/date etc. Am I missing something?
Ah gotcha, in hindsight my question is very straightforward lol. That makes sense, we have the value and we can log it as needed. A related question though, is this value actually “monitored” by OpenAI for any policy violations and such ( as shown in Safety best practices - OpenAI API)?
Your keys/account is monitored. So, if they get flags, they might either ask you what member is sending X Y or Z prompt and/or take other actions on your account. You should be using the moderation endpoint to flag anything before sending to a model anyway.