DOCXToDocument

Convert DOCX files to documents your pipeline can query, with configurable formatting for tables and links.

DOCXToDocument uses the python-docx library to extract text from DOCX files. Note that it doesn't preserve page breaks from the original document.

Key Features

• Configurable table output format: CSV (default) or Markdown.
• Configurable link output format: plain text, Markdown, or no links.
• Optional metadata attachment to resulting documents.

Configuration

1. Drag the DOCXToDocument component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. Configure the component settings:
   • Set the Table Format to control how tables are extracted: csv (default) or markdown.
   • Set the Link Format to control how hyperlinks appear in the extracted text: none (default, text only), markdown (for [text](url)), or plain (for text (url)).
   • Set Store Full Path to control whether the full file path or just the file name is stored in document metadata.

Connections

DOCXToDocument accepts a list of file paths or ByteStream objects through its sources input. It outputs a list of Document objects.

It typically connects with:

• FileTypeRouter: receives DOCX files routed by MIME type.
• DocumentJoiner: sends converted documents to join with output from other converters before further processing.

Source Code

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

Usage Examples

Basic Configuration

  docx_converter:
    type: haystack.components.converters.docx.DOCXToDocument
    init_parameters:
      link_format: markdown

Using the Component in an Index

In this index, DOCXToDocument receives DOCX files from FileTypeRouter and sends them to DocumentJoiner.

# haystack-pipeline
components:
  file_classifier:
    type: haystack.components.routers.file_type_router.FileTypeRouter
    init_parameters:
      mime_types:
      - text/plain
      - application/pdf
      - text/markdown
      - application/vnd.openxmlformats-officedocument.wordprocessingml.document
  text_converter:
    type: haystack.components.converters.txt.TextFileToDocument
    init_parameters:
      encoding: utf-8

  pdf_converter:
    type: haystack.components.converters.pdfminer.PDFMinerToDocument
    init_parameters:
      line_overlap: 0.5
      char_margin: 2
      line_margin: 0.5
      word_margin: 0.1
      boxes_flow: 0.5
      detect_vertical: true
      all_texts: false
      store_full_path: false

  markdown_converter:
    type: haystack.components.converters.txt.TextFileToDocument
    init_parameters:
      encoding: utf-8

  docx_converter:
    type: haystack.components.converters.docx.DOCXToDocument
    init_parameters:
      link_format: markdown

  joiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate
      sort_by_score: false

  splitter:
    type: haystack.components.preprocessors.document_splitter.DocumentSplitter
    init_parameters:
      split_by: word
      split_length: 250
      split_overlap: 30
      respect_sentence_boundary: true
      language: en

  document_embedder:
    type: haystack.components.embedders.sentence_transformers_document_embedder.SentenceTransformersDocumentEmbedder
    init_parameters:
      normalize_embeddings: true
      model: intfloat/e5-base-v2

  writer:
    type: haystack.components.writers.document_writer.DocumentWriter
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: ''
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
      policy: OVERWRITE

connections:  # Defines how the components are connected
- sender: file_classifier.text/plain
  receiver: text_converter.sources
- sender: file_classifier.application/pdf
  receiver: pdf_converter.sources
- sender: file_classifier.text/markdown
  receiver: markdown_converter.sources
- sender: file_classifier.application/vnd.openxmlformats-officedocument.wordprocessingml.document
  receiver: docx_converter.sources
- sender: text_converter.documents
  receiver: joiner.documents
- sender: pdf_converter.documents
  receiver: joiner.documents
- sender: markdown_converter.documents
  receiver: joiner.documents
- sender: docx_converter.documents
  receiver: joiner.documents
- sender: joiner.documents
  receiver: splitter.documents
- sender: document_embedder.documents
  receiver: writer.documents
- sender: splitter.documents
  receiver: document_embedder.documents

inputs:  # Define the inputs for your pipeline
  files:                            # This component will receive the files to index as input
  - file_classifier.sources

max_runs_per_component: 100

metadata: {}

Parameters

Inputs

Parameter	Type	Default	Description
sources	List[Union[str, Path, ByteStream]]		List of file paths or ByteStream objects.
meta	Optional[Union[Dict[str, Any], List[Dict[str, Any]]]]	None	Optional metadata to attach to the converted documents. This value can be either a list of dictionaries or a single dictionary. If it's a single dictionary, its content is added to the metadata of all produced Documents. If it's a list, the length of the list must match the number of sources, because the two lists will be zipped. If sources contains ByteStream objects, their meta will be added to the output Documents.

Outputs

Parameter	Type	Description
documents	List[Document]	Created documents.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
table_format	Union[str, DOCXTableFormat]	DOCXTableFormat.CSV	The format for table output. Can be either DOCXTableFormat.MARKDOWN, DOCXTableFormat.CSV, "markdown", or "csv".
link_format	Union[str, DOCXLinkFormat]	DOCXLinkFormat.NONE	The format for link output. Can be either: DOCXLinkFormat.MARKDOWN or "markdown" to get [text](url), DOCXLinkFormat.PLAIN or "plain" to get text (url), DOCXLinkFormat.NONE or "none" to get text without links.
store_full_path	bool	False	If True, the full file path is stored in the metadata of the document. If False, only the file name is stored.

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
sources	List[Union[str, Path, ByteStream]]		List of file paths or ByteStream objects.
meta	Optional[Union[Dict[str, Any], List[Dict[str, Any]]]]	None	Optional metadata to attach to the Documents. This value can be either a list of dictionaries or a single dictionary. If it's a single dictionary, its content is added to the metadata of all produced Documents. If it's a list, the length of the list must match the number of sources, because the two lists are zipped. If sources contains ByteStream objects, their meta is added to the output Documents.