kb-prepare-batch

To batch convert PDF and DOCX files to Markdown, stage source files into library/raw/ using markitdown. The process converts non-markdown formats and adds provenance frontmatter for traceability.

Yes, you can convert EPUB and TeX documents to Markdown-ready content. The staging process uses pandoc specifically for TeX, EPUB, RST, and ORG formats, while markitdown handles other common types.

Provenance metadata improves knowledge base ingestion by attaching traceability frontmatter to staged items. This records the source file origin and conversion details, supporting auditability and reproducibility for downstream use.

The best way to stage source files into a raw library directory is to provide a list of source paths and optional flags. The process writes converted Markdown to library/raw/ while preserving or moving the original files.

Yes, you need pandoc and markitdown installed to batch convert documents. The staging process relies on markitdown for PDF, DOCX, PPTX, HTML, and CSV formats, and depends on pandoc for TeX, EPUB, RST, and ORG conversions.

Yes, you can use an optional manifest to specify conversion behavior for batch file staging. Providing a manifest allows you to define how source files are processed, copied, or moved into the library/raw/ directory.