search

zhu327 / gemini-openai-proxy

A proxy for converting the OpenAI API protocol to the Google Gemini Pro protocol.
MIT License
504 stars 92 forks source link

pro vision cannot use text #8

Closed kokojacket closed 6 months ago

kokojacket commented 6 months ago

I just found out that the update supports vision, but after using it, I found that using vision with plain text is not supported and must be accompanied by pictures. image

zhu327 commented 6 months ago

https://platform.openai.com/docs/guides/vision

I implemented the protocol according to the above documents. I am not sure if the original gpt-4-vision-preview supports plain text directly

kokojacket commented 6 months ago

Well, thanks