Class MarkdownChunker

Markdown-aware chunking strategy.

Splits markdown documents while respecting document structure:

  • Tries to keep sections under the same header together
  • Preserves code blocks
  • Respects list structures
  • Maintains document hierarchy

The chunker splits on markdown headers (# ## ### etc.) and tries to keep content under each header as a coherent unit.

Example

const chunker = new MarkdownChunker({
  chunkSize: 1000,
  chunkOverlap: 100
});

const result = await chunker.chunk({
  id: 'readme',
  content: markdownContent,
  metadata: { source: 'README.md' }
});

Implements

  • DocumentChunker

Constructors

constructor

Methods

chunk chunkMany estimateChunks

Properties

config

Constructors

constructor

Methods

chunk

  • chunk(document: Document): Promise<ChunkResult>

    Split a document into chunks

    Parameters

    • document: Document

      Document to chunk

    Returns Promise<ChunkResult>

    Chunked documents with metadata

chunkMany

  • chunkMany(documents: Document[]): Promise<ChunkResult[]>

    Split multiple documents into chunks

    Parameters

    • documents: Document[]

      Documents to chunk

    Returns Promise<ChunkResult[]>

    Array of chunk results

estimateChunks

  • estimateChunks(document: Document): number

    Estimate the number of chunks that will be created

    Parameters

    • document: Document

      Document to estimate

    Returns number

    Estimated number of chunks

Properties

Readonlyconfig

config: ChunkerConfig

Configuration for this chunker

Settings

Member Visibility

On This Page

Constructors
Methods
Properties