orkgnlp.clustering.encoders.TransformerKmeansEncoder

class TransformerKmeansEncoder(transformer_path)

Bases: ORKGNLPBaseEncoder

The SciBERTKmeansEncoder encodes the given input to a SciBERT vector needed to execute a Kmeans onnx model.

Parameters:

transformer_path (str) – Path to transformers model. Can be a model name on Huggingface.

Methods

encode	Encodes the raw_input to a model-friendly format.
release_memory	Releases the memory of all available attributes in a pipeline component.

encode(raw_input, **kwargs)

Encodes the raw_input to a model-friendly format.

Parameters:

raw_input (Any) – The user’s input to be encoded.

Return type:

Tuple[Any, Dict[str, Any]]

Returns:

The model-friendly output and kwargs.

release_memory()

Releases the memory of all available attributes in a pipeline component.