How can I upload an image via the API and ask a question related to it? What are the technical parameters or process?
I know we can do it via the browser. How do I do it via the API?
3 Likes
The API Support is not available now it should be within a month for developers.
Then you can play around.
1 Like
Can you elaborate on what you mean by “Developers” or how one “qualifies”?
Users using the API? Chat Plus members? Something else?
An application programming interface (API) is used by application developers (programmers) to build end-user products.
There is no GPT-4 multimodal support for general API users.
The OpenAI blog announcement of the image feature within ChatGPT, (which is a consumer web page chatbot and application developed by OpenAI), gave a mere mention that it could be coming to API in the future.
OpenAI have not said anything about the API for the image yet but I am sure they will in the future.
Having said that, there are other library/modules unrelated to OpenAI that can do object recognition which you can use together with the Chat API already.
As to the process, it will be like this:
[user uploads image] → [user send query about the image] → [image and query is sent to Vision API] → [output is sent to Chat API for summarization]
1 Like
Is there anything new on the subject? I’m very interested in this for a project too.
1 Like
I had the same question. I would love to be able to do this through the API like how you can do in the app.
1 Like
I think it just dropped today
2 Likes
It wont show up in playgrounds - but you can access the API.
Try out their quick start (OpenAI Platform) it worked for me!