Skip to content

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Enhance header support text and update extraction tool description for clarity

myhlolie71cbc2fb8aa
diff --git a/mineru/kit/gradio/app.py b/mineru/kit/gradio/app.py
index 519a1872..371bda20 100644
--- a/mineru/kit/gradio/app.py
+++ b/mineru/kit/gradio/app.py
@@ -134,7 +134,6 @@ def _render_header(*, gradio_major_version: int = 5) -> str:
"""渲染复用旧版视觉风格的静态 Header。"""
template = _resource_text("gradio_header.html")
values = {
- "{{HEADER_SUPPORT_TEXT}}": "",
"{{HEADER_MODEL_HUGGINGFACE_LINK}}": "Hugging Face",
"{{HEADER_MODEL_MODELSCOPE_LINK}}": "ModelScope",
"{{HEADER_PAPER_MINERU_REPORT}}": "MinerU · arXiv",
@@ -145,6 +144,7 @@ def _render_header(*, gradio_major_version: int = 5) -> str:
for placeholder, key in {
"HEADER_TITLE": "header_title",
"HEADER_SUBTITLE": "header_subtitle",
+ "HEADER_SUPPORT_TEXT": "header_support_text",
"HEADER_CODE_LINK": "code",
"HEADER_MODEL_LINK": "model",
"HEADER_PAPER_LINK": "paper",
diff --git a/mineru/kit/gradio/i18n.py b/mineru/kit/gradio/i18n.py
index 9f48e32d..48716a76 100644
--- a/mineru/kit/gradio/i18n.py
+++ b/mineru/kit/gradio/i18n.py
@@ -9,8 +9,14 @@ import re
MESSAGES: dict[str, tuple[str, str]] = {
"header_title": ("MinerU 4: Document Extraction", "MinerU 4:文档提取"),
"header_subtitle": (
- "Open-source document extraction for PDF, Office, EPUB, OFD, HTML, CSV and images.",
- "开源文档提取工具,支持 PDF、Office、EPUB、OFD、HTML、CSV 与图片。",
+ "Open-source document extraction for PDF/JPG/PNG, DOC/DOCX, PPT/PPTX, XLS/XLSX, "
+ "RTF, ODT/ODS/ODP, EPUB, HTML, OFD and CSV.",
+ "开源文档提取工具,支持 PDF/JPG/PNG、DOC/DOCX、PPT/PPTX、XLS/XLSX、"
+ "RTF、ODT/ODS/ODP、EPUB、HTML、OFD 和 CSV。",
+ ),
+ "header_support_text": (
+ "If you found our project helpful, please give us a ⭐️ to support us!",
+ "如果我们的项目对你有帮助,请点亮 ⭐️ 支持我们!",
),
"stars": ("GitHub stars", "GitHub 星标"),
"code": ("Code", "代码"),