lazyslide.tl.slide_caption

slide_caption(wsi, prompt, feature_key, *, agg_key=None, agg_by=None, max_length=100, model='prism', device=None)

Generate captions for the slide.

Parameters:

wsiWSIData

The WSIData object to work on.

promptlist of str

The text instruction to generate the caption.

feature_keystr

The slide features to be used.

agg_keystr, default: None

The aggregation key.

agg_bystr or list of str, default: None

The aggregation keys that were used to create the slide features.

max_lengthint, default: 100

The maximum length of the generated caption.

model{“prism”}, default: “prism”

The caption generation model to use.

devicestr, default: None

The device to use for inference. If None, the default device will be used.

Returns:

DataFrame

The generated captions. Contains a ‘caption’ column, plus any annotation columns if aggregation groups were used.