Support gpt-4-vision-preview

[sloganking]

https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo

I imagine gpt-4 vision is going to have some API differences compared to normal language models that just take text instead of files. Supporting it would probably be desirable to many people however.

[64bit]

Hey, just published DevDay released on v0.16.0. Please give it a try, if you find any issues PRs are welcome!

[ludberg]

How would we add something like this?

I think I've found the corresponding code - do you have an example on how to use it?

[tiderjian]

How would we add something like this?

I think I've found the corresponding code - do you have an example on how to use it?

let request = CreateChatCompletionRequestArgs::default()
    .max_tokens(4096u16)
    .model("gpt-4")
    .messages([
        ChatCompletionRequestSystemMessageArgs::default()
            .content("You are a helpful assistant.")
            .build().unwrap()
            .into(),
        ChatCompletionRequestUserMessageArgs::default()
            .content(vec!(
                ChatCompletionRequestMessageContentPartTextArgs::default().text(payload.prompt).build().unwrap().into(),
ChatCompletionRequestMessageContentPartImageArgs::default().image_url(payload.image).build().unwrap().into(),
            ))
            .build().unwrap()
            .into(),
        
    ])
    .build().unwrap();

[64bit]

This was addressed in #203 hence closing