Build an AI 'chat with image' app in 10 minutes | Bubble x OpenAI

In this tutorial you're learn how to build a simple AI application that can see and respond to user uploaded images all with no-code.

[Nolaready]

I have been searching for weeks for videos on how to do this, thanks bro

[StarterBuild]

Would love a tutorial on how you allowed users to push content to notion! Keep up the great work!

[jishnusurendran]

Extremely helpful Matt, thanks a lot!

[kianburkeai]

This is awesome - can you make a tutorial on how achieve this while using the Assistants API? That is where the real power comes from. Thanks.

[pedromiguel]

Amazing! Simple and quick. Will add it immediately to some apps I'm working on to read documents and more. Thank you

[mohammedalsaggaf]

hi bro, how are you, the results appear fine for me, but in the results and heading I see symbols such as the asterisk* symbol and the hashtag# in the results

How do I stop chatGPT API from showing symbols in the results?

[JhonataCosmo]

Very good, could you make another version of this tutorial but instead of reading a photo, the api reads and analyzes a document? Thanks.

[thatQiao]

Why using 4:13 Json-safe for text input and 11:17 trigger the custom event for hidden loading dot HTML but not just hide it directly inside the workflow?

[bestmoviestrailers]

Hey, can I ask something? is there a way to upload a pdf and ask him from the pdf to solve a problem that apears on the image provided?

[portfoliopb]

I get an error saying. Couldn't parse cURL. Check that you only include supported fields.
What should i do?

[Rmarinho]

this is a great video! great job. Can you make one like it for ChatPDF? I think it would be very useful too! Thanks for your work!

[lpnegociosdigitais]

How can i save the answer on database bubble? Like a text

[IlReverendoIl]

Can you do a video on how to do it with pdf (And OCR)? Thank you a lot

[mohammedalsaggaf]

there is some wrong when i run it:

There was an issue setting up your call.

Raw response for the API
Status code 400
{
"error": {
"message": "Invalid content type. image_url is only supported by certain models.",
"type": "invalid_request_error",
"param": "messages.[0].content.[1].type",
"code": null
}
}

what is the problem, help me please

[blah]

Would openai be able to access the image if it set as private upload for sensitive applications?

[blankblank]

This was amazing but as i was following around with the video and reached the part where you have to Initialize call for the API, i got an error that "The model `gpt-4-vision-preview` does not exist or you do not have access to it". Then i came to realize that this tutorial is for ChatGPT 4 which is for paid users only. I wish there would be a way to build this app with free tools...🥺

[Every-AI]

i am getting an error while settign up the curl

[BookingsCleanFanatics]

here was an issue setting up your call.

Raw response for the API
Status code 404
{
"error": {
"message": "The model `gpt-4o` does not exist or you do not have access to it.",
"type": "invalid_request_error",
"param": null,
"code": "model_not_found"
}
}

I got this and tried more combinations for models like chatgpt-3.5 or chatgpt-3.5-turbo but not getting ay success

[JOTT]

Hey - thanks for sharing. Can this work with PDFs? This would be super useful!