semantic_router.encoders.huggingface.HFEndpointEncoder#

class semantic_router.encoders.huggingface.HFEndpointEncoder(name: str | None = 'hugging_face_custom_endpoint', huggingface_url: str | None = None, huggingface_api_key: str | None = None, score_threshold: float = 0.8)#

Bases: BaseEncoder

A class to encode documents using a Hugging Face transformer model endpoint.

Attributes:

huggingface_url (str): The URL of the Hugging Face API endpoint. huggingface_api_key (str): The API key for authenticating with the Hugging Face API. score_threshold (float): A threshold value used for filtering or processing the embeddings.

__init__(name: str | None = 'hugging_face_custom_endpoint', huggingface_url: str | None = None, huggingface_api_key: str | None = None, score_threshold: float = 0.8)#

Initializes the HFEndpointEncoder with the specified parameters.

Args:
name (str, optional): The name of the encoder. Defaults to

“hugging_face_custom_endpoint”.

huggingface_url (str, optional): The URL of the Hugging Face API endpoint.

Cannot be None.

huggingface_api_key (str, optional): The API key for the Hugging Face API.

Cannot be None.

score_threshold (float, optional): A threshold for processing the embeddings.

Defaults to 0.8.

Raises:

ValueError: If either huggingface_url or huggingface_api_key is None.

Methods

__init__([name, huggingface_url, ...])

Initializes the HFEndpointEncoder with the specified parameters.

acall(docs)

construct([_fields_set])

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data.

copy(*[, include, exclude, update, deep])

Duplicate a model, optionally choose which fields to include, exclude and change.

dict(*[, include, exclude, by_alias, ...])

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

from_orm(obj)

json(*[, include, exclude, by_alias, ...])

Generate a JSON representation of the model, include and exclude arguments as per dict().

parse_file(path, *[, content_type, ...])

parse_obj(obj)

parse_raw(b, *[, content_type, encoding, ...])

query(payload[, max_retries, retry_interval])

Sends a query to the Hugging Face API and returns the response.

schema([by_alias, ref_template])

schema_json(*[, by_alias, ref_template])

set_score_threshold(v)

update_forward_refs(**localns)

Try to update ForwardRefs on fields based on this Model, globalns and localns.

validate(value)

Attributes

name

huggingface_url

huggingface_api_key

score_threshold

type

classmethod construct(_fields_set: SetStr | None = None, **values: Any) → Model#

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values

copy(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, update: DictStrAny | None = None, deep: bool = False) → Model#

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters:

  • include – fields to include in new model

  • exclude – fields to exclude from new model, as with values this takes precedence over include

  • update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

  • deep – set to True to make a deep copy of the model

Returns:

new model instance

dict(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, by_alias: bool = False, skip_defaults: bool | None = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) → DictStrAny#

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

json(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, by_alias: bool = False, skip_defaults: bool | None = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Callable[[Any], Any] | None = None, models_as_dict: bool = True, **dumps_kwargs: Any) → str#

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

query(payload, max_retries=3, retry_interval=5)#

Sends a query to the Hugging Face API and returns the response.

Args:

payload (dict): The payload to send in the request.

Returns:

dict: The response from the Hugging Face API.

Raises:

ValueError: If the query fails or the response status is not 200.

classmethod update_forward_refs(**localns: Any) → None#

Try to update ForwardRefs on fields based on this Model, globalns and localns.