Extracting and referencing images

[RichardSieg]

I was wondering whether it is possible to extract all images from a document and reference them at their position in the generated markdown?

As I understand the documentation it should be possible but I could not get any images from PDF documents yet

ai_extraction: Accurately extract clean markdown, cropped images, tables, and equations using a fine-tuned vision model. A 20-page PDF takes ~1 minute. (default is False)