INNER CODE UNIT · Python

split_document

Azure/logicapps · LogicApps-AI-RAG-Demo/TokenizeDocFunction/function_app.py:187

def split_document(json_data, document):
    splitter = json_data.get("splittingStrategy").upper()
    secondary_splitter = json_data.get(
        "secondarySplittingStrategy").upper()
    headers_to_split_on = json_data.get("headersToSplitOn", None)
    chunk_size = json_data.get("chunkSize")
    chunk_overlap = json_data.get("chunkOverlap")
    document_type = json_data["documentType"].upper()
    return split_document_by_splitter_type(
        document,
        document_type,
        splitter=splitter,
        secondary_splitter=secondary_splitter,
        headers_to_split_on=headers_to_split_on,
        chunk_size=chunk_size,
        chunk_overlap=chunk_overlap,
    )

View source record →