I’m trying to use gpt-4o to analyze a base64 encoded image, but I’m getting a message saying it’s unable to view or analyze images directly. I’ve tested the api in both flutterflow and postman and encountered the same issue. What should I do?
Welcome to the community!
Have you tried getting it to work in the playground?
https://platform.openai.com/playground/chat?models=gpt-4o
you can even click on the </> button (top right) to generate a curl command for you to make sure you don’t make any accidental mistakes:
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-4o",
"messages": [
{
"role": "system",
"content": [
{
"type": "text",
"text": "What'\''s in this image?"
}
]
},
{
"role": "user",
"content": [
{
"type": "text",
"text": "What'\''s in this image?"
},
{
"type": "image_url",
"image_url": {
"url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQAb4... ...3Fhg0KMENUUVIz//Z"
}
}
]
},
{
"role": "assistant",
"content": [
{
"type": "text",
"text": "The image shows a small cat wearing a costume that makes it look like a lion. The cat has a mane-like accessory around its head, which gives the impression of a lion'\''s mane. The cat is standing among a field of pink and white flowers, presumably daisies, with a background of greenery. The setting appears to be outdoors, in a garden or park."
}
]
}
],
"temperature": 1,
"max_tokens": 256,
"top_p": 1,
"frequency_penalty": 0,
"presence_penalty": 0,
"response_format": {
"type": "text"
}
}'
spoiler
your user message object is malformed
here’s the API reference, but the code from the playground is also good
https://platform.openai.com/docs/api-reference/chat/create