rag.splitters.hierarchical
Split text into hierarchical parent-child chunks for context-aware retrieval.
Split text into hierarchical parent-child chunks for context-aware retrieval.
- class HierarchicalChunker(chunk_size=400, chunk_overlap=100, metadata=None, parent_chunk_size=1500, max_levels=2)[source]
Bases:
ChunkerBaseHierarchical chunking with parent-child relationships.
- Parameters:
- chunk(text, metadata=None)[source]
Split text into hierarchical chunks with parent-child relationships.
- get_parent_chunks(chunks)[source]
Filter to return only parent chunks.
- Parameters:
chunks (list[HierarchicalTextChunk])
- Return type:
- get_child_chunks(chunks)[source]
Filter to return only child chunks.
- Parameters:
chunks (list[HierarchicalTextChunk])
- Return type:
- get_chunks_with_parent_context(child_chunks, all_chunks)[source]
Get child chunks with their parent context for retrieval.
- Parameters:
child_chunks (list[HierarchicalTextChunk]) – Child chunks retrieved from search.
all_chunks (list[HierarchicalTextChunk]) – All chunks (to look up parents).
- Returns:
List of dicts with child content and parent context.
- Return type:
Classes
- class HierarchicalChunker(chunk_size=400, chunk_overlap=100, metadata=None, parent_chunk_size=1500, max_levels=2)[source]
Bases:
ChunkerBaseHierarchical chunking with parent-child relationships.
- Parameters:
- chunk(text, metadata=None)[source]
Split text into hierarchical chunks with parent-child relationships.
- get_parent_chunks(chunks)[source]
Filter to return only parent chunks.
- Parameters:
chunks (list[HierarchicalTextChunk])
- Return type:
- get_child_chunks(chunks)[source]
Filter to return only child chunks.
- Parameters:
chunks (list[HierarchicalTextChunk])
- Return type:
- get_chunks_with_parent_context(child_chunks, all_chunks)[source]
Get child chunks with their parent context for retrieval.
- Parameters:
child_chunks (list[HierarchicalTextChunk]) – Child chunks retrieved from search.
all_chunks (list[HierarchicalTextChunk]) – All chunks (to look up parents).
- Returns:
List of dicts with child content and parent context.
- Return type: