I’ve tried to set up the API to take images but most of the information I’ve found seems outdated or doesn’t include it. I’m sure this is very simple, but how can I set it up to take images as inputs? I’m using Google Colab. Thank you!
Hi @alexcooke8282 and welcome to the community!
IMO Vision API docs are very good and provide an explanation of how to do it. If you have an image stored locally (e.g. uploaded into collab), you just read it as a binary file and perform base64 encoding, then pass that in your API call. Alternatively if the image is already hosted somewhere, you can just provide the URL.
1 Like