Skip to main content
For the complete documentation index for agents and LLMs, see llms.txt.

MarkItDownConverter

Convert PDF, Word, PowerPoint, Excel, HTML, and many other file formats to Markdown Documents using Microsoft MarkItDown.

Key Features​

  • Converts PDF, DOCX, PPTX, XLSX, HTML, images, audio, and more to Markdown.
  • Runs entirely locally with no external API calls.
  • Accepts file paths, Path objects, and ByteStream inputs.
  • Supports per-file or per-batch metadata attached to output Documents.
  • Simple setup with a single optional init parameter.

Configuration​

  1. Install the markitdown-haystack integration.
  2. Configure MarkItDownConverter in your pipeline YAML.

Connections​

MarkItDownConverter accepts file paths, Path objects, or ByteStream inputs as sources, and optional metadata as meta. It outputs a list of Document objects (documents) containing Markdown content.

Connect the pipeline's file input to the sources input. Connect the documents output to DocumentSplitter, DocumentJoiner, or DocumentWriter for further processing.

Source Code​

To check this component's source code, open markitdown_converter.py in the Haystack Core Integrations repository.

Usage Examples​

Basic Configuration​

  markitdown_converter:
    type: haystack_integrations.components.converters.markitdown.markitdown_converter.MarkItDownConverter
    init_parameters:
      store_full_path: false

Using the Component in a Pipeline​

# haystack-pipeline
components:
  markitdown_converter:
    type: haystack_integrations.components.converters.markitdown.markitdown_converter.MarkItDownConverter
    init_parameters:
      store_full_path: false
  splitter:
    type: haystack.components.preprocessors.document_splitter.DocumentSplitter
    init_parameters:
      split_by: word
      split_length: 250
      split_overlap: 30
  writer:
    type: haystack.components.writers.document_writer.DocumentWriter
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          - ${OPENSEARCH_HOST}
          index: markitdown-demo
          embedding_dim: 768
          create_index: true

connections:
- sender: markitdown_converter.documents
  receiver: splitter.documents
- sender: splitter.documents
  receiver: writer.documents

inputs:
  files:
  - markitdown_converter.sources

max_runs_per_component: 100

metadata: {}

Parameters​

Init Parameters​

These are the parameters you can configure in Pipeline Builder:

ParameterTypeDefaultDescription
store_full_pathboolFalseIf True, stores the full file path in Document metadata. If False, stores only the file name.