How to get JSON mode working for Open AI Vision

[mingsterism]

is there any support for JSON mode in vision preview? i've tried to get it working with GPT4Turbo1106 as well but it does not work. below is my example

    resp, err := client.CreateChatCompletion(
        context.Background(),
        openai.ChatCompletionRequest{
            Model:     openai.GPT4Turbo1106,
            MaxTokens: 1000,
            Messages: []openai.ChatCompletionMessage{
                {
                    Role: openai.ChatMessageRoleUser,
                    MultiContent: []openai.ChatMessagePart{
                        {
                            Type: openai.ChatMessagePartTypeText,
                            Text: text,
                        },
                        {
                            Type: openai.ChatMessagePartTypeImageURL,
                            ImageURL: &openai.ChatMessageImageURL{
                                URL:    imgString2,
                                Detail: openai.ImageURLDetailLow,
                            },
                        },
                    },
                },
            },
            Tools: []openai.Tool{t},
            //ResponseFormat: &openai.ChatCompletionResponseFormat{
            //  Type: openai.ChatCompletionResponseFormatTypeJSONObject,
            //},
        },
    )

[HelloTQ]

has the error been fixed?

[rasmusviben]

Working for me with the new GPT4o model and if I specify in the "text" that the output should be json.