udfPreprocess/paramconfig.cfg

[lexical_search]
TOP_K = 10
THRESHOLD = 0.1

[semantic_search]
TOP_K = 10
MAX_SEQ_LENGTH = 64
MODEL_NAME = msmarco-distilbert-cos-v5
THRESHOLD = 0.1

[sdg]
THRESHOLD = 0.85

[preprocessor]
SPLIT_OVERLAP_WORD = 20
SPLIT_OVERLAP_SENTENCE = 1