HierarchicalDocumentSplitter

Split documents into different block sizes, building a hierarchical tree structure for advanced retrieval.

Key Features

• Splits documents into multiple levels of chunk sizes in a single pass.
• Builds a parent-child hierarchy where smaller chunks are children of larger parent chunks.
• Enables auto-merging retrieval: retrieve specific small chunks and expand to parent context when needed.
• Configurable overlap between chunks at each level.
• Supports splitting by word, sentence, page, or passage.

Configuration

1. Drag the HierarchicalDocumentSplitter component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. On the General tab:
   1. Set block_sizes — a list of chunk sizes for different hierarchy levels, from largest to smallest (for example, [512, 256, 128]).
4. Go to the Advanced tab to configure the split overlap and split unit (split_overlap_unit, split_by).

Connections

HierarchicalDocumentSplitter accepts a list of documents (documents) as input and outputs a list of hierarchical documents (documents) with parent-child relationships.

Connect converters or DocumentCleaner to the input. Connect the output to document embedders and then DocumentWriter for storage. In query pipelines, use AutoMergingRetriever to merge child documents back to their parent context.

Usage Example

Using the Component in an Index

This example shows an indexing pipeline using hierarchical splitting with block sizes of 512, 256, and 128 words.

components:
  TextFileToDocument:
    type: haystack.components.converters.txt.TextFileToDocument
    init_parameters:
      encoding: utf-8
      store_full_path: false
  DocumentCleaner:
    type: haystack.components.preprocessors.document_cleaner.DocumentCleaner
    init_parameters:
      remove_empty_lines: true
      remove_extra_whitespaces: true
  HierarchicalDocumentSplitter:
    type: deepset_cloud_custom_nodes.preprocessors.hierarchical_document_splitter.HierarchicalDocumentSplitter
    init_parameters:
      block_sizes:
      - 512
      - 256
      - 128
      split_overlap: 0
      split_by: word
  SentenceTransformersDocumentEmbedder:
    type: haystack.components.embedders.sentence_transformers_document_embedder.SentenceTransformersDocumentEmbedder
    init_parameters:
      model: sentence-transformers/all-MiniLM-L6-v2
      batch_size: 32
      progress_bar: true
      normalize_embeddings: false
  DocumentWriter:
    type: haystack.components.writers.document_writer.DocumentWriter
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: hierarchical-documents-index
          max_chunk_bytes: 104857600
          embedding_dim: 384
          return_embedding: false
          create_index: true
          similarity: cosine
      policy: NONE

connections:
- sender: TextFileToDocument.documents
  receiver: DocumentCleaner.documents
- sender: DocumentCleaner.documents
  receiver: HierarchicalDocumentSplitter.documents
- sender: HierarchicalDocumentSplitter.documents
  receiver: SentenceTransformersDocumentEmbedder.documents
- sender: SentenceTransformersDocumentEmbedder.documents
  receiver: DocumentWriter.documents

max_runs_per_component: 100

metadata: {}

inputs:
  files:
  - TextFileToDocument.sources

Parameters

Inputs

Parameter	Type	Default	Description
documents	List[Document]		List of Documents to split into hierarchical blocks.

Outputs

Parameter	Type	Default	Description
documents	List[Document]		List of hierarchical documents with parent-child relationships.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
block_sizes	Set[int]		Set of block sizes to split the document into. The blocks are split in descending order.
split_overlap	int	0	The number of overlapping units for each split.
split_by	Literal['word', 'sentence', 'page', 'passage']	word	The unit for splitting your documents.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
documents	List[Document]		List of Documents to split into hierarchical blocks.