apache_beam.ml.transforms.embeddings.huggingface module

class apache_beam.ml.transforms.embeddings.huggingface.SentenceTransformerEmbeddings(model_name: str, columns: List[str], max_seq_length: Optional[int] = None, **kwargs)

Bases: apache_beam.ml.transforms.base.EmbeddingsManager

Embedding config for sentence-transformers. This config can be used with MLTransform to embed text data. Models are loaded using the RunInference PTransform with the help of ModelHandler.

Parameters:

• model_name – Name of the model to use. The model should be hosted on HuggingFace Hub or compatible with sentence_transformers.
• columns – List of columns to be embedded.
• max_seq_length – Max sequence length to use for the model if applicable.
• min_batch_size – The minimum batch size to be used for inference.
• max_batch_size – The maximum batch size to be used for inference.
• large_model – Whether to share the model across processes.

get_model_handler()

get_ptransform_for_processing(**kwargs) → apache_beam.transforms.ptransform.PTransform

class apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings(hf_token: Optional[str], columns: List[str], model_name: Optional[str] = None, api_url: Optional[str] = None, **kwargs)

Bases: apache_beam.ml.transforms.base.EmbeddingsManager

Feature extraction using HuggingFace’s Inference API. Intended to be used for feature-extraction. For other tasks, please refer to https://huggingface.co/inference-api.

Parameters:

• hf_token – HuggingFace token.
• columns – List of columns to be embedded.
• model_name – Model name used for feature extraction.
• api_url – API url for feature extraction. If specified, model_name will be ignored. If none, the default url for feature extraction will be used.

get_token()

api_url

authorization_token

get_model_handler()

get_ptransform_for_processing(**kwargs) → apache_beam.transforms.ptransform.PTransform