vertebrae.extractors.siglip

SigLIP-style image-text extractor.

Classes

SigLIPExtractor

Ergonomic wrapper for SigLIP-style Hugging Face image-text models.

Module Contents

class vertebrae.extractors.siglip.SigLIPExtractor(name, model_id, outputs=None, image_field='image', text_field='text', processor_id=None, batch_size=16, image_mode='auto', alpha_mode='drop', device=None, revision=None, trust_remote_code=False, processor_kwargs=None, model_kwargs=None, checkpoint_paths=None, cache_identity=None)

Ergonomic wrapper for SigLIP-style Hugging Face image-text models.

Parameters:

• name (str)

• model_id (str)

• outputs (Optional[Sequence[Dict[str, Any]]])

• image_field (str)

• text_field (str)

• processor_id (Optional[str])

• batch_size (int)

• image_mode (str)

• alpha_mode (str)

• device (Optional[str])

• revision (Optional[str])

• trust_remote_code (bool)

• processor_kwargs (Optional[Dict[str, Any]])

• model_kwargs (Optional[Dict[str, Any]])

• checkpoint_paths (Optional[Sequence[str]])

• cache_identity (Optional[str])

get_resource_profile_adapter()

Forward resource profiling to the Hugging Face delegate.

Return type:

Any