pyseekdb.utils.embedding_functions.SentenceTransformerEmbeddingFunction

class pyseekdb.utils.embedding_functions.SentenceTransformerEmbeddingFunction(model_name: str = 'all-MiniLM-L6-v2', device: str = 'cpu', normalize_embeddings: bool = False, **kwargs: Any)

Bases: EmbeddingFunction[str | list[str]]

An embedding function using sentence-transformers with a specific model.

Example

pip install pyseekdb sentence-transformers

__init__(model_name: str = 'all-MiniLM-L6-v2', device: str = 'cpu', normalize_embeddings: bool = False, **kwargs: Any)

Initialize SentenceTransformerEmbeddingFunction.

Parameters:

• model_name (str, optional) – Identifier of the SentenceTransformer model, defaults to “all-MiniLM-L6-v2”

• device (str, optional) – Device used for computation, defaults to “cpu”

• normalize_embeddings (bool, optional) – Whether to normalize returned vectors, defaults to False

• **kwargs – Additional arguments to pass to the SentenceTransformer model.

Methods

__init__([model_name, device, ...])	Initialize SentenceTransformerEmbeddingFunction.
build_from_config(config)
get_config()	Get the configuration dictionary for the embedding function.
name()
support_persistence(embedding_function)	Check if the embedding function supports persistence.

Attributes

models

get_config() → dict[str, Any]

Get the configuration dictionary for the embedding function.

This method should return a dictionary that contains all the information needed to restore the embedding function after restart.

Returns:

Dictionary containing the embedding function’s configuration. Note: The ‘name’ field is not included as it’s handled by the upper layer for routing.