Skip to main content

List of File Types supported

info

All these below file formats are supported in workflow/API deployment/ETL/Task pipelines.In prompt studio, only pdf is supported.

Here is the list of the file formats supported in Unstract:

Word Processing Formats:​

  • DOCX (Microsoft Word Open XML)
  • DOC (Microsoft Word)
  • ODT (OpenDocument Text)

Presentation Formats:​

  • PPTX (Microsoft PowerPoint Open XML)
  • PPT (Microsoft PowerPoint)
  • ODP (OpenDocument Presentation)

Spreadsheet Formats:​

  • XLSX (Microsoft Excel Open XML)
  • XLS (Microsoft Excel)
  • ODS (OpenDocument Spreadsheet)

Document and Plain Text Formats:​

  • PDF (Portable Document Format)
  • TXT (Plain Text)

Image Formats:​

  • BMP (Bitmap Image)
  • GIF (Graphics Interchange Format)
  • JPEG (Joint Photographic Experts Group)
  • JPG (Joint Photographic Experts Group)
  • PNG (Portable Network Graphics)
  • TIF (Tagged Image File Format)
  • TIFF (Tagged Image File Format)
  • WEBP (Web Picture Format)