There is an error in the example response of the image input scenario under the chat endpoint.
What error are you getting?
From line 210 of openai.yaml
response: &chat_completion_image_example |
{
"id": "chatcmpl-123",
"object": "chat.completion",
"created": 1677652288,
"model": "gpt-3.5-turbo-0613",
"system_fingerprint": "fp_44709d6fcb",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": "\n\nHello there, how may I assist you today?",
},
"logprobs": null,
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 9,
"completion_tokens": 12,
"total_tokens": 21
}
}
Here’s replacement JSON response example to place in the file, with surrounding lines, what is received today (no logprobs, no fingerprint, correct model)
});
console.log(response.choices[0]);
}
main();
response: &chat_completion_image_example |
{
"id": "chatcmpl-123456",
"object": "chat.completion",
"created": 1708249531,
"model": "gpt-4-1106-vision-preview",
"usage": {
"prompt_tokens": 1122,
"completion_tokens": 6,
"total_tokens": 1128
},
"choices": [
{
"message": {
"role": "assistant",
"content": "Man singing in music video."
},
"finish_reason": "stop",
"index": 0
}
]
}
- title: Streaming
request:
curl: |
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
New 'messages' to reproduce the output shown
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Under six words, what’s this image?"
},
{
"type": "image_url",
"image_url": {
"url": "https://i.imgur.com/oeYzasc.jpeg"
}
}
]
}
]
1 Like
Yes, that is the correct response I received. I meant to point out that the example response is not the right one.
Thank you for providing details!