Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-ragpdf-parserpptxpythonxlsx
fix(webui): use declared PDFium guard API
myhloli3dacabcc401b
diff --git a/mineru/kit/gradio/page_range.py b/mineru/kit/gradio/page_range.pyindex 265ccf47..223a73b2 100644--- a/mineru/kit/gradio/page_range.py+++ b/mineru/kit/gradio/page_range.py@@ -25,13 +25,14 @@ def validate_max_pages(max_pages: int | None) -> None:def read_pdf_page_count(path: str | Path) -> int:"""在共享 PDFium 锁内读取页数,并在成功或异常时及时释放文档。"""- # 先取得公共 PDF 包,再读取其运行时;与图片准备的首次导入保持同一锁顺序。- from docvortex.document.pdf import pdfium as pdfium_runtime+ # 先加载公共 PDF 包,再导入公开锁函数;与图片准备的首次导入保持同一锁顺序。+ import docvortex.document.pdf # noqa: F401+ from docvortex.document.pdf.pdfium import pdfium_guardimport pypdfium2 as pdfiumtry:- with pdfium_runtime.pdfium_guard():+ with pdfium_guard():document = pdfium.PdfDocument(str(path))try:page_count = len(document)