Dear Make Community,
I’m having trouble adding the GPT-4 Vision (gpt-4-vision-preview model) into my Make scenario. My goal is to use this model for an image-to-text extraction. However, I’m encountering a problem that I can’t seem to fix.
My flow
- Scenario1: I’ve connected my GoogleDrive to watch for new images in a folder.
- Scenario2: Within the ‘OpenAI - Analyze Images’ module, I’ve linked my ‘Web View Link’.
- Result: “The operation failed with an error. [400] You uploaded an unsupported image. Please make sure your image is below 20 MB in size and is of one the following formats: [‘png’, ‘jpeg’, ‘gif’, ‘webp’].”
Notes:
- I have tried to include every single item that has a URL from my GoogleDrive, no luck.
- I’ve also tested it using a Google Images picture, and it worked. So it must be the Image Link connection that I am using.
- The image file size is 3Mb.
I am curious as to how you all are linking your images to be analyzed?
