MCPcopy Create free account
hub / github.com/Paper2Poster/Paper2Poster / chunk_elements

Method chunk_elements

camel/loaders/unstructured_io.py:444–472  ·  view source on GitHub ↗

r"""Chunks elements by titles. Args: elements (List[Element]): List of Element objects to be chunked. chunk_type (str): Type chunk going to apply. Supported types: 'chunk_by_title'. **kwargs: Additional keyword arguments for chunking.

(
        elements: List["Element"], chunk_type: str, **kwargs
    )

Source from the content-addressed store, hash-verified

442
443 @staticmethod
444 def chunk_elements(
445 elements: List["Element"], chunk_type: str, **kwargs
446 ) -> List["Element"]:
447 r"""Chunks elements by titles.
448
449 Args:
450 elements (List[Element]): List of Element objects to be chunked.
451 chunk_type (str): Type chunk going to apply. Supported types:
452 'chunk_by_title'.
453 **kwargs: Additional keyword arguments for chunking.
454
455 Returns:
456 List[Dict]: List of chunked sections.
457
458 References:
459 https://unstructured-io.github.io/unstructured/
460 """
461
462 from unstructured.chunking.title import chunk_by_title
463
464 chunking_functions = {
465 "chunk_by_title": chunk_by_title,
466 }
467
468 if chunk_type not in chunking_functions:
469 raise ValueError(f"Unsupported chunk type: {chunk_type}")
470
471 # Format chunks into a list of dictionaries (or your preferred format)
472 return chunking_functions[chunk_type](elements, **kwargs)

Callers 2

processMethod · 0.45
processMethod · 0.45

Calls

no outgoing calls

Tested by

no test coverage detected