chunklet.base_chunker
Base Chunker Abstract Class
Defines the interface for chunkers.
Classes:
-
BaseChunker–Abstract base class for chunkers.
BaseChunker
Bases: ABC
Abstract base class for chunkers.
Defines the standard interface for chunking content into units.
Methods:
-
batch_chunk–Process multiple items in parallel.
-
chunk–Extract chunks.
-
log_info–Log an info message if verbose is enabled.
Source code in src/chunklet/base_chunker.py
batch_chunk
abstractmethod
Process multiple items in parallel.
Yields:
-
Box(Box) –Boxobject, representing a chunk with its content and metadata.
chunk
abstractmethod
Extract chunks.
Returns:
-
list[Box]–list[Box]: List of chunks with content and metadata.