james8
14
It’s just made available yesterday. Yipee!
1 Like
tkataja
15
It is not generally available for API users or at least not documented?
2 Likes
any one have figured out how to supply an image to API call and ask question from it? the chat gpt is able to do it now
1 Like
I’ve been trying to figure out how to supply an image to the API but I haven’t got it working yet. Even the following does not work:
response = openai.ChatCompletion.create(
model=“gpt-4”,
messages=[
{“role”: “system”, “content”: “You are a helpful assistant.”},
{“role”: “user”, “content”: f"what is this image {img_url}"}
]
)
output: “I’m sorry for the inconvenience. As a text-based AI, I don’t have the ability to view or interpret images. You may want to use an image search engine or AI that specializes in image recognition for assistance.”
Hopefully someone can figure it out.
1 Like
_j
18
You can stop wasting your time asking and looking. There is no date of API availability
Plus and Enterprise users will get to experience voice and images in the next two weeks. We’re excited to roll out these capabilities to other groups of users, including developers, soon after.
When the API starts taking lists instead of strings as “content”, then one might conclude something is going on. When you get the response “Sorry, I can’t help with that”, then you know it’s working as designed.
1 Like
Amazing! But I was wondering what the syntax is for uploading png files as context. Is there a place where they outline the documentation?
This is not possible right now. You have to wait, then the documentation will reflect how to do it.
1 Like
have you figured it out yet? because i also need to input images using the API and i cannot find anything on the web
_j
22
There’s no “figuring out” something that hasn’t been released and doesn’t have a solid release date either.
“I’m excited about my ‘come wash my car’ AI plugin” doesn’t mean I’m merely hiding the documentation on how to use it.
1 Like
okay thank you, I thought that it was released. no need to be angry about it lol (with peace and love)
1 Like
_j
25
It’s natural to be excited, and hearing an ambiguous announcement could lead one to think it’s available. OpenAI has had the gpt-4 machine vision (YouTube) trained model internally for over a year - before anybody had heard of ChatGPT.
We’ve seen many announced products from OpenAI slowly trickle out to users in alpha, beta, insider, limited release, tier-1 partner forms also, to find image identification and performance concerns with the ingenuity of a wider audience. Everyone saying “look at this” to the AI on day one, and the service crashing, would not be an ideal outcome if there were release problems.
Knowing that it is coming down, at least, you can consider ways that computer vision and the ability to receive an image description could work in your own application beyond mere novelty.
Does anyone have a way of inputing an image with the API?
No image input with the API yet. Whoever gets that superpower first will surely be bragging here 
1 Like
I would imagine that will be something they announce at their Dev Day.
_j
29
That superpower can be granted for your apps also… $13 billion dollars. API developers have to distinguish themselves from the market lead and pricing model of free and available, from the company they purchase their own services from.
The image you’ve shared is quite intriguing! Here’s a description:
This is a photo-realistic image set in a futuristic factory. The scene is dominated by a row of robotic arms affixed to the ceiling, each holding a human-like head. These heads are intriguingly covered in a rainbow-colored metallic foil and have various wires and cables attached to them. Workers, clad in green lab coats, are diligently working on these heads. The background reveals a well-equipped laboratory, adding to the overall futuristic theme.
As for a title, considering the elements in the image, how about “Synthetic Spectrum: The Birth of Tomorrow”? This title captures both the colorful aspect (Spectrum) and the futuristic theme (The Birth of Tomorrow) of your artwork. Let me know what you think! 
1 Like
I think the image represents all those dudes that chose to cryogenically freeze their head, in hopes of being reborn sometime in the future. Except in the future, the humans are 1/6th the size of todays humans because there was a big push to shrink humans to make things cheaper, including the mystery gnome army employed by cybernetic restoration corporations 
But I’m not sure where you get the $13 billion dollars comment above, I’m lost.
BTW, not all API developers are trying to make a product to sell to the public. Most of us are making internal products that make our business more efficient.
4 Likes
_j
31
Did you input the image through API or the web interface?
At the moment, it is only allowed via the web interface.
2 Likes
