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

LibreOfficeFileConverter

Convert Office documents, spreadsheets, and presentations to other formats using the LibreOffice command-line utility (soffice).

Key Features​

  • Converts DOC, DOCX, ODT, XLS, XLSX, PPT, PPTX, and other Office formats to PDF, DOCX, TXT, HTML, and more.
  • Outputs ByteStream objects that you can pass directly to Haystack document converters such as PyPDFToDocument.
  • Supports both synchronous and asynchronous execution.
  • Accepts file paths, Path objects, and ByteStream inputs.
  • Requires LibreOffice to be installed on the system where the pipeline runs.

Configuration​

  1. Install LibreOffice on your system. For instructions, see the LibreOffice installation guide.
  2. Make sure the soffice executable is available in your system PATH.
  3. Configure LibreOfficeFileConverter in your pipeline YAML with the desired output_file_type.

Connections​

LibreOfficeFileConverter accepts file paths, Path objects, or ByteStream inputs as sources and returns a list of ByteStream objects as output. The output typically connects to a Haystack document converter such as PyPDFToDocument or DOCXToDocument to produce Document objects for downstream processing.

Source Code​

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

Usage Examples​

Basic Configuration​

  libreoffice_converter:
    type: haystack_integrations.components.converters.libreoffice.converter.LibreOfficeFileConverter
    init_parameters:
      output_file_type: pdf

Using the Component in a Pipeline​

# haystack-pipeline
components:
  libreoffice_converter:
    type: haystack_integrations.components.converters.libreoffice.converter.LibreOfficeFileConverter
    init_parameters:
      output_file_type: pdf
  pdf_converter:
    type: haystack.components.converters.pypdf.PyPDFToDocument
    init_parameters: {}
  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: libreoffice-demo
          embedding_dim: 768
          create_index: true

connections:
- sender: libreoffice_converter.output
  receiver: pdf_converter.sources
- sender: pdf_converter.documents
  receiver: splitter.documents
- sender: splitter.documents
  receiver: writer.documents

inputs:
  files:
  - libreoffice_converter.sources

max_runs_per_component: 100

metadata: {}

Parameters​

Init Parameters​

These are the parameters you can configure in Pipeline Builder:

ParameterTypeDefaultDescription
output_file_typestr | NoneNoneTarget file format for conversion. Supported values: pdf, doc, docx, odt, rtf, txt, html, xlsx, xls, ods, csv, pptx, ppt, odp, epub, png, jpg. Must be a valid conversion target for the source file type. Can also be set at run time.