apache_beam.ml.rag.embeddings.huggingface module

RAG-specific embedding implementations using HuggingFace models.

class apache_beam.ml.rag.embeddings.huggingface.HuggingfaceTextEmbeddings(model_name: str, *, max_seq_length: int | None = None, **kwargs)

Bases: EmbeddingsManager

Utilizes huggingface SentenceTransformer embeddings for RAG pipeline.

Parameters:

• model_name – Name of the sentence-transformers model to use

• max_seq_length – Maximum sequence length for the model

• **kwargs – Additional arguments passed to

:param EmbeddingsManager: :param constructor including ModelHandler arguments:

get_model_handler()

Returns model handler configured with RAG adapter.

get_ptransform_for_processing(**kwargs) → PTransform[PCollection[Chunk], PCollection[Chunk]]

Returns PTransform that uses the RAG adapter.