Expand description
Document chunking strategies for RAG pipelines
Structs§
- Chunk
- A chunk of text from a document
- ChunkId
- Unique chunk identifier
- Chunk
Metadata - Metadata associated with a chunk
- Fixed
Size Chunker - Fixed-size chunker implementation
- Paragraph
Chunker - Paragraph-based chunker
- Recursive
Chunker - Recursive chunker implementation
- Semantic
Chunker - Semantic chunker that groups sentences by embedding similarity
- Sentence
Chunker - Sentence-based chunker
- Structural
Chunker - Structural chunker that respects document structure (headers, sections)
- Timestamp
Chunker - Timestamp-aware chunker for subtitle/transcript content.
Enums§
- Chunking
Strategy - Chunking strategy configuration
Traits§
- Chunker
- Trait for document chunkers