Expand description
Text chunking functionality for processing large documents.
This module provides comprehensive text chunking capabilities to handle documents that exceed the language model’s context window. It supports multiple chunking strategies and overlap management to ensure no information is lost during processing.
Structs§
- Chunk
Iterator - Token-based chunk iterator that mimics Python’s ChunkIterator behavior
- Chunk
Result - Result from processing a single chunk
- Chunking
Config - Configuration for text chunking
- Result
Aggregator - Result aggregator for combining extractions from multiple chunks
- Text
Chunk - A chunk of text with metadata
- Text
Chunker - Text chunker for processing large documents
- Token
Chunk - A token-based chunk with sophisticated linguistic boundaries
Enums§
- Chunking
Strategy - Different strategies for chunking text