Open RipperTs opened 1 month ago
I think this feature is different from PDF attachments, because PDF attachments can parse their file content on their own, while image attachments can't achieve the interpretation of the content on their own, so they need the support of AI models
I'd like to have a dialog with multiple uploaded images, for interpreting images and such, similar to what the OpenAI GPT-4V model does. But so far there is very little documentation on Poe's picture attachment, can you provide a more detailed example?