XLSXToDocument

Turn XLSX worksheets or rows into documents. This component uses pandas and openpyxl to read spreadsheets.

Key Features

• Two conversion modes: one document per worksheet (default) or one document per row.
• Configurable content column for row mode — remaining columns become document metadata.
• Sheet selection to limit conversion to specific worksheets.
• Passes additional arguments to pandas.read_excel for advanced control.

Configuration

1. Drag the XLSXToDocument component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. Configure the component settings:
   • Set Document Per to sheet (default) to create one document per worksheet, or row to create one document per row.
   • If using row mode, set Content Column to specify which column becomes the document content. The default is content.
   • Optionally, set Sheet Name to limit conversion to specific sheets by name or index. If not set, all sheets are converted.
   • Set kwargs to pass additional arguments to pandas.read_excel, such as engine, skiprows, or nrows.

Connections

XLSXToDocument 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 XLSX files routed by MIME type.
• DocumentJoiner: sends converted documents to join with output from other converters before further processing.
• DocumentSplitter or embedding components: sends documents for further processing.

Usage Examples

Basic Configuration

  xlsx_converter:
    type: deepset_cloud_custom_nodes.converters.xlsx.XLSXToDocument
    init_parameters:
      document_per: row
      content_column: summary

Using the Component in an Index

# haystack-pipeline
components:
  file_router:
    type: haystack.components.routers.file_type_router.FileTypeRouter
    init_parameters:
      mime_types:
      - application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
      - text/csv
  xlsx_converter:
    type: haystack.components.converters.xlsx.XLSXToDocument
    init_parameters:
      table_format: csv
      sheet_name:
  csv_converter:
    type: deepset_cloud_custom_nodes.converters.csv_rows_to_documents.DeepsetCSVRowsToDocumentsConverter
    init_parameters: {}
  joiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate

  DocumentWriter:
    type: haystack.components.writers.document_writer.DocumentWriter
    init_parameters:
      policy: NONE
      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:

connections:
- sender: file_router.application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
  receiver: xlsx_converter.sources
- sender: file_router.text/csv
  receiver: csv_converter.sources
- sender: xlsx_converter.documents
  receiver: joiner.documents
- sender: csv_converter.documents
  receiver: joiner.documents

- sender: joiner.documents
  receiver: DocumentWriter.documents

inputs:
  files:
  - file_router.sources

max_runs_per_component: 100

metadata: {}

Parameters

Inputs

Parameter	Type	Default	Description
sources	List[Union[str, Path, ByteStream]]		Paths or ByteStreams that point to XLSX files.
meta	Optional[Union[Dict[str, Any], List[Dict[str, Any]]]]	None	Metadata forwarded to every document or aligned per source.

Outputs

Parameter	Type	Description
documents	List[Document]	Documents that contain CSV content or the selected row content plus merged metadata.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
document_per	Literal["sheet", "row"]	"sheet"	Create a document per worksheet or per row.
content_column	str	"content"	Column that holds the content when document_per is set to row.
sheet_name	Union[str, int, List[Union[str, int]], None]	None	Limit conversion to one sheet, several sheets, or leave None to read all sheets.
kwargs	Dict[str, Any]		Arguments forwarded to pandas.read_excel, such as engine, skiprows, or nrows.

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]]		XLSX file paths or ByteStreams.
meta	Optional[Union[Dict[str, Any], List[Dict[str, Any]]]]	None	Metadata applied to every generated document or aligned per source entry.