PDF
Full text extraction including embedded images, diagrams, and tables.
Available
DOCX / Word
Microsoft Word documents with rich formatting, headers, and inline images.
Available
XLSX / Excel
Spreadsheet data, including multi-sheet workbooks and embedded charts.
Available
PPTX / PowerPoint
Slide decks with text, speaker notes, and embedded diagrams processed together.
Available
Markdown / MDX
Plain-text documentation and MDX files from repos, wikis, and internal docs sites.
Available
HTML
Static HTML pages and internal documentation sites. Main content automatically extracted and parsed.
Available
CSV / TSV
Structured data tables and exports from other systems, ingested and made queryable.
Available
PNG / JPEG
Raster images with OCR text extraction, diagrams, and embedded visual context.
Available
SVG
Scalable vector graphics. Text within SVG files is extracted and indexed for search.
Available
WebP
Modern web image format with efficient compression. Text and visual elements processed.
Available