lazyslide.tl.slide_caption

slide_caption(wsi, prompt, feature_key, *, agg_key=None, agg_by=None, max_length=100, model='prism', device=None, amp=None, autocast_dtype=None, compile=None, compile_kws=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.

modelstr or ModelBaseProtocol, default: “prism”

The caption generation model to use: a model registry key (see Models) or a model instance with a caption method.

devicestr, default: None

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

ampbool, optional

Whether to use automatic mixed precision.

autocast_dtypetorch.dtype, optional

The dtype for automatic mixed precision.

compilebool, optional

Whether to compile the model with torch.compile(). Compilation is best-effort and is silently skipped for models that do not support it.

compile_kwsdict, optional

Keyword arguments passed to torch.compile().

Returns:

DataFrame

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