OpenVINOEmbeddings

OpenVINO model object.

Tokenizer for embedding model.

HuggingFace model id.

Keyword arguments to pass to the model.

Keyword arguments to pass when calling the encode method of the model.

Whether to show a progress bar.

Computes sentence embeddings.

:param sentences: the sentences to embed. :param batch_size: the batch size used for the computation. :param show_progress_bar: Whether to output a progress bar. :param convert_to_numpy: Whether the output should be a list of numpy vectors. :param convert_to_tensor: Whether the output should be one large tensor. :param mean_pooling: Whether to pool returned vectors. :param normalize_embeddings: Whether to normalize returned vectors.

:return: By default, a 2d numpy array with shape [num_inputs, output_dimension].

Compute doc embeddings using a HuggingFace transformer model.

Compute query embeddings using a HuggingFace transformer model.