Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.camel-ai.org/llms.txt

Use this file to discover all available pages before exploring further.

​
UnstructuredIOChunker

class UnstructuredIOChunker(BaseChunker):
A class for chunking text while respecting structure and character limits. This class ensures that structured elements, such as document sections and titles, are not arbitrarily split across chunks. It utilizes the UnstructuredIO class to process and segment elements while maintaining readability and coherence. The chunking method can be adjusted based on the provided chunk_type parameter. Parameters:
  • chunk_type (str, optional): The method used for chunking text. (default: :obj:"chunk_by_title")
  • max_characters (int, optional): The maximum number of characters allowed per chunk. (default: :obj:500)
  • metadata_filename (Optional[str], optional): An optional filename for storing metadata related to chunking. (default: :obj:None)

​
init

def __init__(
    self,
    chunk_type: str = 'chunk_by_title',
    max_characters: int = 500,
    metadata_filename: Optional[str] = None
):

​
chunk

def chunk(self, content: List['Element']):
Splits the content into smaller chunks while preserving structure and adhering to token constraints. Parameters:
  • content (List[Element]): The content to be chunked.
Returns: List[Element]: A list of chunked text segments.