databricks.labs.dqx.pii.nlp_engine_config
NLPEngineConfig Objects
class NLPEngineConfig(Enum)
Enum class defining various NLP engine configurations for PII detection.
Note that DQX automatically installs the built-in entity recognition models at runtime if they are not already available. However, for better performance and to avoid potential out-of-memory issues, it is recommended to pre-install models using pip install.
Members:
SPACY_SMALL: Uses spaCy's en_core_web_sm for entity recognitionSPACY_SMALL: Uses spaCy's en_core_web_md for entity recognitionSPACY_SMALL: Uses spaCy's en_core_web_lg for entity recognition