Since the description of the vision model was previously ‘Ability to understand images, in addition to all other GPT-4 Turbo capabilities,’ and it has now changed to ‘Currently, GPT-4 with vision does not support the message.name parameter, functions/tools, response_format parameter,’ we would like to know when it will support these features that were claimed to be supported. This is very important for developers.
I’d find this extremely useful as well.
I’m interested in using it to extract structured data from images. This kind of thing, but for images: Using OpenAI functions and their Python library for data extraction | Simon Willison’s TILs
Any chance function call support will be added in the future?
1 Like
