Multimodal cookbook prompts don't scroll sideways and are hard to read

[simonw]

https://github.com/anthropics/anthropic-cookbook/blob/main/multimodal/how_to_transcribe_text.ipynb

This is even worse on mobile, where the screen is narrower so often most of the code is impossible to view.

I just reported this bug to GitHub here:

• https://github.com/orgs/community/discussions/131730

For the moment there are two things you could do:

1. Publish these notebooks elsewhere - maybe via GitHub Pages - such that they can be read
2. (Easier) Edit these notebooks so the prompts are readable despite this GitHub bug

An example of option 2, adapted from https://github.com/anthropics/anthropic-cookbook/blob/main/multimodal/best_practices_for_vision.ipynb

message_list = [
    {
        "role": 'user',
        "content": [
            {
                "type": "image",
                "source": {
                    "type": "base64",
                    "media_type": "image/jpeg",
                    "data": get_base64_encoded_image(
                        "../images/best_practices/"
                        "nine_dogs.jpg"
                    )
                }
            },
            {
                "type": "text",
                "text": "You have perfect vision "
                        "and pay great attention to "
                        "detail which makes you an "
                        "expert at counting objects "
                        "in images. How many dogs "
                        "are in this picture? "
                        "Before providing the "
                        "answer in <answer> tags, "
                        "think step by step in "
                        "<thinking> tags and "
                        "analyze every part of the "
                        "image."
            }
        ]
    }
]