Skip to main content

​
Parameters

ParameterTypeDefaultDescription
configOptional[RecursiveChunkingConfig]NoneA specialized configuration model for the Recursive Chunker strategy. This configuration extends the base settings with parameters that control the recursive splitting behavior, such as the prioritized list of separators to use.

​
Functions

​
__init__

Initializes the chunker with a specific or default configuration. Parameters:
  • config (Optional[RecursiveChunkingConfig]): Configuration object with all settings.

​
_chunk_document

The core implementation for recursively chunking a single document. Parameters:
  • document (Document): The document to be chunked.
Returns:
  • List[Chunk]: A list of Chunk objects derived from the document.

​
_recursive_split

Recursively splits text using a prioritized list of separators. Parameters:
  • text (str): The text to split.
  • separators (List[str]): List of separators to try in order.
  • offset (int): Character offset for position tracking.
Returns:
  • List[Tuple[str, int, int]]: List of tuples containing (text, start_index, end_index).

​
from_language

Create a RecursiveChunker configured for a specific programming language. Parameters:
  • language (Language): The programming language to configure for.
  • config (Optional[RecursiveChunkingConfig]): Optional configuration to use.
Returns:
  • RecursiveChunker: A chunker configured for the specified language.
⌘I