Commit Graph

2 Commits

Author SHA1 Message Date
120ed89780 fix(proxy): catch markitdown missing-dependency errors with clean hint
When markitdown is installed but a format-specific sub-dependency is
missing (e.g. pdfminer-six for PDF), translate the raw traceback into
a DependencyMissingError with the correct install command.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-13 21:00:51 +01:00
e4fbba8a57 feat(proxy): add markitdown as default proxy backend
Uses markitdown-no-magika (lighter fork without magika/onnxruntime) to
handle PDF, HTML, DOCX, PPTX, XLSX, XLS, CSV, JSON, and XML files.
Specialized extractors (pymupdf4llm, markdownify) remain as fallbacks
when markitdown is not installed.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-13 20:48:47 +01:00