pyseekdb.utils.embedding_functions.OnnxEmbeddingFunction

class pyseekdb.utils.embedding_functions.OnnxEmbeddingFunction(model_name: str, hf_model_id: str, dimension: int, download_path: Path | None = None, preferred_providers: list[str] | None = None)[source]

Bases: object

Generic ONNX runtime embedding function.

This class handles model download, tokenizer/model loading, and embedding generation using onnxruntime.

__init__(model_name: str, hf_model_id: str, dimension: int, download_path: Path | None = None, preferred_providers: list[str] | None = None)[source]

Initialize an ONNX embedding function.

Parameters:

model_name – Name of the model (used for cache directory naming).
hf_model_id – Hugging Face model ID.
dimension – Output embedding dimension.
download_path – Optional cache path override.
preferred_providers – Preferred ONNX runtime providers.

Methods

`__init__`(model_name, hf_model_id, dimension)	Initialize an ONNX embedding function.
`max_tokens`()	Get the maximum number of tokens supported by the model.

Attributes

`ARCHIVE_FILENAME`
`EXTRACTED_FOLDER_NAME`
`dimension`	Get the dimension of embeddings produced by this function.
`model`	Get the model.
`tokenizer`	Get the tokenizer for the model.

property dimension: int: Get the dimension of embeddings produced by this function.

max_tokens() → int[source]: Get the maximum number of tokens supported by the model.

property model: Any

Get the model.

Returns:: The model.

property tokenizer: Any

Get the tokenizer for the model.

Returns:: The tokenizer for the model.