nemo_curator.stages.deduplication.fuzzy.utils

View as Markdown

Module Contents

Data

CURATOR_DEFAULT_MINHASH_FIELD

CURATOR_FUZZY_DUPLICATE_GROUP_FIELD

CURATOR_LSH_BUCKET_FIELD

API

nemo_curator.stages.deduplication.fuzzy.utils.CURATOR_DEFAULT_MINHASH_FIELD = '_minhash_signature'
nemo_curator.stages.deduplication.fuzzy.utils.CURATOR_FUZZY_DUPLICATE_GROUP_FIELD = '_duplicate_group_id'
nemo_curator.stages.deduplication.fuzzy.utils.CURATOR_LSH_BUCKET_FIELD = '_bucket_id'