Explain Image functionality

[leventmolla]

OpenAI has a new model gp4-1106-vision-preview which can explain a collection of images. I think it could be done with the general chat completions endpoint, but the documentation is not very clear about the message structure. There should be a text prompt initially describing the task and follow-up messages that contain the images. I tried this and passed base64-encoded images, got errors (for some reason the number of tokens requested is a very large number and the query fails). I then tried to pass the URLs of the files for the images, which failed as well. So I am at a loss about how to use this functionality.

[kalafus]

please see issue report 174 for an example. support was just added, and is being fixed by this pull

[nezhyborets]

There seems to have been a progress in this since the issues was created, specifically #175
Will close until someone has more relevant issues