Open waylon-brown opened 9 months ago
It would be nice to be able to "upload" images (just grab their file path and display), then send that to the Vision API so that it can interpret the image.
Image-input is once again very topical due to the release of the new GPT-4o model.
It would be nice to be able to "upload" images (just grab their file path and display), then send that to the Vision API so that it can interpret the image.