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>
This commit is contained in:
@@ -34,7 +34,8 @@ development = [
|
||||
]
|
||||
proxy-pdf = ["pymupdf4llm>=0.0.10"]
|
||||
proxy-html = ["markdownify>=0.13.1"]
|
||||
proxy = ["pymupdf4llm>=0.0.10", "markdownify>=0.13.1"]
|
||||
proxy-markitdown = ["markitdown-no-magika[pdf]"]
|
||||
proxy = ["markitdown-no-magika[pdf]"]
|
||||
|
||||
[project.scripts]
|
||||
markitect = "markitect.cli:main"
|
||||
|
||||
Reference in New Issue
Block a user