Skip to main content
Available from version 1.56
Feature in Alpha
This feature requires a model with vision capabilities. See AI Presets.
Enable vision-based file processing for documents and slides.

​
Modes

ModeDescription
noneDisables vision processing. Files are processed using text extraction only.
liteCombines text and visual extraction to improve understanding of structure, images, charts, and diagrams. Designed to balance quality and efficiency.

​
Configuration

KeyDefaultValuesDescription
transformation.pptx.vision.modenonenone | liteControls vision processing mode for PPTX files (.pptx).
transformation.docling.vision.modenonenone | liteControls vision processing mode for Docling-processed files (.pdf, .docx, .xlsx).

​
Recommendations

  • Use lite when documents include important charts, diagrams, or images.
  • Use lite for PPTX files when slide structure and chart interpretation matter.
Enabling lite increases resource consumption and document processing time.

​
Example

transformation:
    pptx:
      vision:
        mode: lite
    docling:
      vision:
        mode: lite