> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/annotate/annotate-multimodal-data.md).

# Annotate Multimodal Data

If you are labeling a dataset that is part of a Multimodal project, prefixes are used to annotate your images.

A prefix can either be:

* An identifier like `<PREFIX>`, that is used to prompt a [VLM](https://blog.roboflow.com/what-is-a-vision-language-model/) like Florence-2, or;
* A question like "What is in this image?", ideal for use with general VQA models like GPT-4o.

For Florence-2 fine-tuning, for example, the prefix chosen will correspond to the prefix prompt you give to the model. For Florence-2, prefixes should be in the format `<PREFIX>`, like `<TOTAL>`.

For GPT-4o, your prefix may be: "What is the total in this receipt?".

You may want to add different prefixes different features in an object that we want to identify, like total, subtotal, and tax.

### Add Prefixes

To add prefixes, click "Classes & Tags" in the Roboflow sidebar, then click the "Add " button:

<figure><img src="/files/RnnDuRWo0d5uv87CSjgV" alt=""><figcaption></figcaption></figure>

Then, enter the prefix. This may be a question like "What is in the image?" or a unique ID like "\<RECEIPT>", depending on the model you want to train.

You can add multiple prefixes with the "+" button.

Click “Add Prefixes” to add your prefixes.

Once you have set prefixes, they will be available as questions in your annotation editor:

<figure><img src="/files/o5KW9jxKM74bk4AoQlkA" alt=""><figcaption></figcaption></figure>