From 8902d1e2087a3e9b195d33e996767d3e1256e0ad Mon Sep 17 00:00:00 2001 From: Michele Dolfi Date: Sat, 2 Nov 2024 09:44:34 +0100 Subject: [PATCH] update CLI docs Signed-off-by: Michele Dolfi --- docs/usage.md | 45 ++++++++++++++++++++++++++------------------- 1 file changed, 26 insertions(+), 19 deletions(-) diff --git a/docs/usage.md b/docs/usage.md index 5493c2ee..a5be4299 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -32,30 +32,37 @@ Here are the available options as of this writing (for an up-to-date listing, ru ```console $ docling --help - Usage: docling [OPTIONS] source - + Usage: docling [OPTIONS] source + ╭─ Arguments ───────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ * input_sources source PDF files to convert. Can be local file / directory paths or URL. [default: None] │ │ [required] │ ╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ ╭─ Options ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮ -│ --from [docx|pptx|html|image|pdf] Specify input formats to convert from. │ -│ Defaults to all formats. │ -│ [default: None] │ -│ --to [md|json|text|doctags] Specify output formats. Defaults to │ -│ Markdown. │ -│ [default: None] │ -│ --ocr --no-ocr If enabled, the bitmap content will be │ -│ processed using OCR. │ -│ [default: ocr] │ -│ --ocr-engine [easyocr|tesseract_cli|tesseract] The OCR engine to use. [default: easyocr] │ -│ --abort-on-error --no-abort-on-error If enabled, the bitmap content will be │ -│ processed using OCR. │ -│ [default: no-abort-on-error] │ -│ --output PATH Output directory where results are saved. │ -│ [default: .] │ -│ --version Show version information. │ -│ --help Show this message and exit. │ +│ --from [docx|pptx|html|image|pdf|asciidoc|md] Specify input formats to convert from. │ +│ Defaults to all formats. │ +│ [default: None] │ +│ --to [md|json|text|doctags] Specify output formats. Defaults to │ +│ Markdown. │ +│ [default: None] │ +│ --ocr --no-ocr If enabled, the bitmap content will be │ +│ processed using OCR. │ +│ [default: ocr] │ +│ --ocr-engine [easyocr|tesseract_cli|tesseract] The OCR engine to use. │ +│ [default: easyocr] │ +│ --pdf-backend [pypdfium2|dlparse_v1|dlparse_v2] The PDF backend to use. │ +│ [default: dlparse_v1] │ +│ --table-mode [fast|accurate] The mode to use in the table structure │ +│ model. │ +│ [default: fast] │ +│ --abort-on-error --no-abort-on-error If enabled, the bitmap content will be │ +│ processed using OCR. │ +│ [default: no-abort-on-error] │ +│ --output PATH Output directory where results are │ +│ saved. │ +│ [default: .] │ +│ --version Show version information. │ +│ --help Show this message and exit. │ ╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ ```