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:
-
chunk_file–Read and chunk a file.
-
chunk_files–Process multiple files.
-
chunk_text–Extract chunks from text.
-
chunk_texts–Process multiple texts.
Source code in src/chunklet/base_chunker.py
chunk_file
abstractmethod
Read and chunk a file.
Returns:
-
list[Box]–list[Box]: List of chunks with content and metadata.
chunk_files
abstractmethod
Process multiple files.
Yields:
-
Box(Box) –Boxobject, representing a chunk with its content and metadata.
chunk_text
abstractmethod
Extract chunks from text.
Returns:
-
list[Box]–list[Box]: List of chunks with content and metadata.
chunk_texts
abstractmethod
Process multiple texts.
Returns:
-
list[list[Box]]–list[list[Box]]: List of chunks for each input text.