- Added CUDA cache clearing after layoutreader prediction to free up GPU memory.
- Modified the bbox sorting logic to sort text and title blocks separately.
- Adjusted drawing colors for better distinction in debug visualizations.

- Added CUDA cache clearing after layoutreader prediction to free up GPU memory.
- Modified the bbox sorting logic to sort text and title blocks separately.
- Adjusted drawing colors for better distinction in debug visualizations.

Implement a new function `draw_layout_sort_bbox` in `draw_bbox.py` to visualize the
layout sorting results using the `LayoutLMv3ForTokenClassification` model. This function
predicts the order of layout elements and draws them in the sorted sequence on the PDF pages.

Implement a new function `draw_layout_sort_bbox` in `draw_bbox.py` to visualize the
layout sorting results using the `LayoutLMv3ForTokenClassification` model. This function
predicts the order of layout elements and draws them in the sorted sequence on the PDF pages.

fix(pdf_extract_kit):change unimernet base -> small

fix(pdf-extract): ensure model is set to evaluation mode before processing

Add model.eval() invocation to pdf_extract_kit initialization sequence to ensure the
model is set to evaluation mode. This is critical for proper inference and performance
metrics when processing PDF content.

refactor(pdf_extract): use Image.crop directly with layout detection

feat(UNIPipe): change default drop_mode to NONE_WITH_REASON

feat(ocr_mkcontent): support drop reason in none_with_reason mode

feat(pipeline): pass language parameter for parsing and markdown conversion

feat(gradio_app): add examples accordion to the PDF conversion interface

feat(ocr_mkcontent): support drop reason in none_with_reason modeEnable the `NONE_WITH_REASON` drop mode in `para_to_standard_format_v2` by updating the
function signature to include the `drop_reason` parameter and handling it within the
function logic. This enhancement allows the function to convey the reason for dropping
content in the output.

fix: remove useless files

fix: solve conflicts

fix: recovert the lang option in tools/cli.py

fix: 1. resolve uncorrect pair relation of figure and footnote, 2. re…

fix: 1. resolve uncorrect pair relation of figure and footnote, 2. resolve uncorrect pair relation of table and caption #590

The pipeline now supports passing the language parameter to parsing functions and
during markdown conversion to optimize processing based on the specified language.
This enhancement allows for more accurate parsing and markdown generation, particularly
when dealing with non-English content.