search

transitive-bullshit / agentic

AI agent stdlib that works with any LLM and TypeScript AI SDK.
https://agentic.so
MIT License
16.32k stars 2.13k forks source link

ChatGPT 4 vision - send image? #623

Closed mmaestrini closed 4 months ago

mmaestrini commented 11 months ago

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 11 months ago

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

jobpassion commented 10 months ago

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

assassinliujie commented 9 months ago

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 9 months ago

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 4 months ago

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The chatgpt package is pretty outdated at this point.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.