operators.candidates.extractor.ParagraphSpanExtractor

class operators.candidates.extractor.ParagraphSpanExtractor(field, col_suffix=None)

Extracts spans (slices of documents) that contain paragraphs (using regex)

This operator uses a regex pattern to extract all paragraphs as spans from the parent document. Trailing newline characters are preserved for each paragraph

Parameters:

• field (str) – The dataframe column to extract paragraph spans from

• col_suffix (Optional[str], default: None) – An optional suffix for the column containing the extracted spans