Huggingface
clip_image(image: Batch[Image], *, model_id: str) -> Batch[ndarray]
Runs the specified CLIP model on images.
clip_text(text: Batch[str], *, model_id: str) -> Batch[ndarray]
Runs the specified CLIP model on text.
cross_encoder(
sentences1: Batch[str], sentences2: Batch[str], *, model_id: str
) -> Batch[float]
Runs the specified cross-encoder model.
detr_for_object_detection(
image: Batch[Image], *, model_id: str, threshold: float = 0.5
) -> Batch[dict]
Runs the specified DETR model.
sentence_transformer(
sentences: Batch[str], *, model_id: str, normalize_embeddings: bool = False
) -> Batch[ndarray]
Runs the specified sentence transformer model.