`DocumentToImageContent` component

[anakin87]

We should make an additional component to FileToImageContent called DocumentToImageContent which allows passing of Document objects directly along with specifying the meta field where you'll find the image path.

An additional requirement here is that we should also support looking for a meta field called page_number. In the situation of supporting PDFs we rarely want to send the whole PDF to the vision LLM, but rather a single page (or even maybe a few pages).

Depends on #9258.

@sjrl has background on this.

[sjrl]

Here are the analogous components that we use in deepset

• DeepsetPDFDocumentToBase64Image for PDF based Documents
• DeepsetFiletoBase64Image for PNG, JPG, JPEG, GIF based Documents

These could probably be combined so we don't need separate components for the different file types.