← Back to API reference

neuralset.extractors.text.SpacyEmbedding

pydantic model neuralset.extractors.text.SpacyEmbedding

Get word embedding from spacy.

Parameters:

• model_name (str) – Explicit spacy model name (e.g. "en_core_web_sm"). Mutually exclusive with language.

• language (str) – Language name or ISO code (e.g. "english", "fr"). Resolved to a default spacy model via get_spacy_model(). Mutually exclusive with model_name. If neither is set, language is read from events.

Fields:

• event_types (Literal['Word'])

• language (str)

• model_name (str)

field event_types: Literal['Word'] = 'Word'

requirements: ClassVar[tuple[str, ...]] = ('rapidfuzz', 'rapidfuzz', 'spacy>=3.8.2')

field model_name: str = ''

field language: str = ''

get_embedding(text: str, language: str = '') → ndarray

← Back to API reference