Welcome to Portkey Forum

Updated 6 days ago

OpenAI content filter

"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": null,
"refusal": "I'm sorry, I can't assist with that request."
},
"logprobs": null,
"finish_reason": "stop"
}
],

possible reasons for getting this repeatedly on the same request?
s
k
3 comments
This is OpenAI’s own refusal
Remove explicit or self harm content :yodasip:
it was a picture of a mannequin wear eyeglasses. that's the only variable. Otherwise it mostly passes. 🤷‍♂️
Add a reply
Sign up and join the conversation on Discord