transitive-bullshit/agentic

ChatGPT 4 vision - send image?

mmaestrini opened this issue · 5 comments

mmaestrini commented

Describe the feature

Hi there,

is it already possible here to use the new chatgpt 4 vision that can interpret / analyse images? in the web is the default mode, not referring to the advanced data analysis.

raisonqyc commented

Looking forward to the addition of image input for gpt-api !!!!

jobpassion commented

you can use my fork:https://github.com/jobpassion/chatgpt-api ,add support for images and multimodal

assassinliujie commented

你可以使用 my fork：https://github.com/jobpassion/chatgpt-api ，添加对图像和多模态的支持

would you add the support for api?

jobpassion commented

would you add the support for api?

Currently only images and multimodal are supported for UnofficialProxyAPI, and there are no plans to add support for ChatGPTAPI at the moment.

transitive-bullshit commented

This project is undergoing a major revamp; closing out old issues as part of the prep process.

The chatgpt package is pretty outdated at this point. I recommend that you use the openai package or the openai-fetch package instead. They both have support for multimodal messages.