Support for gpt-4-vision-preview

[jj0hns0n]

Is there intended to be support for the new gpt-4-vision-preview model soon?

[ingvarus-bc]

Hi, @jj0hns0n, thanks for reaching out! ✨
The gpt-4-vision-preview will be added with PR-115, though Swift native support may follow in later releases, as there are a bunch of other more critical features to be covered first.

In the Documentation there are examples of how it had been implemented using Python but no direct API Reference. If you'd like to have this feature available sooner feel free to open Pull Request and contribute to the project, we always appreciate that! ☺️

[thyselius]

Does anyone have an example of uploading an image to the API together with a prompt for that image?

I'm trying to implement uploading an image to the API. However I get the following error when I'm trying this approach:

        ```
        var content = """
                    [
                        {
                          "type": "text",
                          "text": "\(text)"
                        },
                        {
                          "type": "image_url",
                          "image_url": {
                            "url": f"data:image/png;base64,\(base64!)"
                          }
                        }
                    ]
        """

        query = CompletionsQuery(model: .gpt4_vision_preview, prompt: content, temperature: 1, maxTokens: 4000, topP: 1, frequencyPenalty: 0, presencePenalty: 0, stop: ["\\n"])

            ERROR:
    `2 validation errors for Request\nbody -> prompt\n  value is not a valid list (type=type_error.list)\nbody -> prompt\n  value is not a valid list (type=type_error.list)", type: "invalid_request_error"`