Skip to content

feat: PPTX ingestion #36

Description

@rajnavakoti

Description

Add support for ingesting .pptx files. Extract text from slides, speaker notes, and tables. Common in enterprise documentation.

Acceptance Criteria

  • .pptx files recognized by document scanner
  • Text extracted from slides and speaker notes
  • Slide titles used as section headings for chunking
  • Tables and charts converted to text descriptions

Out of Scope

  • Image/diagram analysis from slides
  • .ppt (legacy format)

Metadata

Metadata

Assignees

No one assigned

    Labels

    P2-laterPlatform capabilities, post-launchpipelineExtraction pipeline

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions