Merge pull request #2842 from myhloli/dev

Dev

README.md

@@ -18,7 +18,8 @@
 [![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
 [![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
 [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/myhloli/3b3a00a4a0a61577b6c30f989092d20d/mineru_demo.ipynb)
-[![Paper](https://img.shields.io/badge/Paper-arXiv-green)](https://arxiv.org/abs/2409.18839)
+[![arXiv](https://img.shields.io/badge/arXiv-2409.18839-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2409.18839)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/opendatalab/MinerU)
 
 
 <a href="https://trendshift.io/repositories/11174" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11174" alt="opendatalab%2FMinerU | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
@@ -433,7 +434,7 @@ There are three different ways to experience MinerU:
 >
 > In non-mainline environments, due to the diversity of hardware and software configurations, as well as third-party dependency compatibility issues, we cannot guarantee 100% project availability. Therefore, for users who wish to use this project in non-recommended environments, we suggest carefully reading the documentation and FAQ first. Most issues already have corresponding solutions in the FAQ. We also encourage community feedback to help us gradually expand support.
 
-<table border="1">
+<table>
     <tr>
         <td>Parsing Backend</td>
         <td>pipeline</td>
@@ -446,6 +447,16 @@ There are three different ways to experience MinerU:
         <td>windows/linux</td>
         <td>windows(wsl2)/linux</td>
     </tr>
+    <tr>
+        <td>CPU Inference Support</td>
+        <td>✅</td>
+        <td colspan="2">❌</td>
+    </tr>
+    <tr>
+        <td>GPU Requirements</td>
+        <td>Turing architecture or later, 6GB+ VRAM or Apple Silicon</td>
+        <td colspan="2">Ampere architecture or later, 8GB+ VRAM</td>
+    </tr>
     <tr>
         <td>Memory Requirements</td>
         <td colspan="3">Minimum 16GB+, 32GB+ recommended</td>
@@ -458,18 +469,6 @@ There are three different ways to experience MinerU:
         <td>Python Version</td>
         <td colspan="3">3.10-3.13</td>
     </tr>
-    <tr>
-        <td>CPU Inference Support</td>
-        <td>✅</td>
-        <td>❌</td>
-        <td>❌</td>
-    </tr>
-    <tr>
-        <td>GPU Requirements</td>
-        <td>Turing architecture or later, 6GB+ VRAM or Apple Silicon</td>
-        <td>Ampere architecture or later, 8GB+ VRAM</td>
-        <td>Ampere architecture or later, 24GB+ VRAM</td>
-    </tr>
 </table>
 
 ## Online Demo
@@ -535,7 +534,7 @@ If you need to use **sglang to accelerate VLM model inference**, you can choose
   ```
   
 > [!TIP]
-> The Dockerfile uses `lmsysorg/sglang:v0.4.7-cu124` as the default base image. If necessary, you can modify it to another platform version.
+> The Dockerfile uses `lmsysorg/sglang:v0.4.8.post1-cu126` as the default base image. If necessary, you can modify it to another platform version.
 
 
 #### 1.4 Install client  (for connecting to sglang-server on edge devices that require only CPU and network connectivity)

README_zh-CN.md

@@ -18,7 +18,8 @@
 [![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
 [![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
 [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/myhloli/3b3a00a4a0a61577b6c30f989092d20d/mineru_demo.ipynb)
-[![Paper](https://img.shields.io/badge/Paper-arXiv-green)](https://arxiv.org/abs/2409.18839)
+[![arXiv](https://img.shields.io/badge/arXiv-2409.18839-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2409.18839)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/opendatalab/MinerU)
 
 
 <a href="https://trendshift.io/repositories/11174" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11174" alt="opendatalab%2FMinerU | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
@@ -423,7 +424,7 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
 >
 > 在非主线环境中，由于硬件、软件配置的多样性，以及第三方依赖项的兼容性问题，我们无法100%保证项目的完全可用性。因此，对于希望在非推荐环境中使用本项目的用户，我们建议先仔细阅读文档以及FAQ，大多数问题已经在FAQ中有对应的解决方案，除此之外我们鼓励社区反馈问题，以便我们能够逐步扩大支持范围。
 
-<table border="1">
+<table>
     <tr>
         <td>解析后端</td>
         <td>pipeline</td>
@@ -436,6 +437,16 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
         <td>windows/linux</td>
         <td>windows(wsl2)/linux</td>
     </tr>
+    <tr>
+        <td>CPU推理支持</td>
+        <td>✅</td>
+        <td colspan="2">❌</td>
+    </tr>
+    <tr>
+        <td>GPU要求</td>
+        <td>Turing及以后架构，6G显存以上或Apple Silicon</td>
+        <td colspan="2">Ampere及以后架构，8G显存以上</td>
+    </tr>
     <tr>
         <td>内存要求</td>
         <td colspan="3">最低16G以上，推荐32G以上</td>
@@ -448,18 +459,6 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
         <td>python版本</td>
         <td colspan="3">3.10-3.13</td>
     </tr>
-    <tr>
-        <td>CPU推理支持</td>
-        <td>✅</td>
-        <td>❌</td>
-        <td>❌</td>
-    </tr>
-    <tr>
-        <td>GPU要求</td>
-        <td>Turing及以后架构，6G显存以上或Apple Silicon</td>
-        <td>Ampere及以后架构，8G显存以上</td>
-        <td>Ampere及以后架构，24G显存及以上</td>
-    </tr>
 </table>
 
 ## 在线体验
@@ -525,7 +524,7 @@ uv pip install -e .[core] -i https://mirrors.aliyun.com/pypi/simple
   ```
   
 > [!TIP]
-> Dockerfile默认使用`lmsysorg/sglang:v0.4.7-cu124`作为基础镜像，如有需要，您可以自行修改为其他平台版本。
+> Dockerfile默认使用`lmsysorg/sglang:v0.4.8.post1-cu126`作为基础镜像，如有需要，您可以自行修改为其他平台版本。
   
 #### 1.4 安装client（用于在仅需 CPU 和网络连接的边缘设备上连接 sglang-server）
 

docker/china/Dockerfile

 # Use the official sglang image
-FROM lmsysorg/sglang:v0.4.8-cu124
+FROM lmsysorg/sglang:v0.4.8.post1-cu126
 
 # install mineru latest
 RUN python3 -m pip install -U 'mineru[core]' -i https://mirrors.aliyun.com/pypi/simple --break-system-packages

docker/global/Dockerfile

 # Use the official sglang image
-FROM lmsysorg/sglang:v0.4.8-cu124
+FROM lmsysorg/sglang:v0.4.8.post1-cu126
 
 # install mineru latest
 RUN python3 -m pip install -U 'mineru[core]' --break-system-packages

mineru/backend/vlm/predictor.py

@@ -77,7 +77,7 @@ def get_predictor(
             raise ImportError(
                 "sglang is not installed, so sglang-engine backend cannot be used. "
                 "If you need to use sglang-engine backend for inference, "
-                "please install sglang[all]==0.4.7 or a newer version."
+                "please install sglang[all]==0.4.8 or a newer version."
             )
         predictor = SglangEnginePredictor(
             server_args=ServerArgs(model_path, **kwargs),

mineru/cli/common.py

@@ -17,7 +17,7 @@ from mineru.backend.vlm.vlm_analyze import doc_analyze as vlm_doc_analyze
 from mineru.backend.vlm.vlm_analyze import aio_doc_analyze as aio_vlm_doc_analyze
 
 pdf_suffixes = [".pdf"]
-image_suffixes = [".png", ".jpeg", ".jpg"]
+image_suffixes = [".png", ".jpeg", ".jpg", ".webp", ".gif"]
 
 
 def read_fn(path):

mineru/cli/gradio_app.py

@@ -7,11 +7,12 @@ import time
 import zipfile
 from pathlib import Path
 
+import click
 import gradio as gr
 from gradio_pdf import PDF
 from loguru import logger
 
-from mineru.cli.common import prepare_env, read_fn, aio_do_parse
+from mineru.cli.common import prepare_env, read_fn, aio_do_parse, pdf_suffixes, image_suffixes
 from mineru.utils.hash_utils import str_sha256
 
 
@@ -28,8 +29,7 @@ async def parse_pdf(doc_path, output_dir, end_page_id, is_ocr, formula_enable, t
 
         if backend.startswith("vlm"):
             parse_method = "vlm"
-        if not backend.endswith("client"):
-            url = None
+
         local_image_dir, local_md_dir = prepare_env(output_dir, file_name, parse_method)
         await aio_do_parse(
             output_dir=output_dir,
@@ -100,9 +100,9 @@ async def to_markdown(file_path, end_pages=10, is_ocr=False, formula_enable=True
     archive_zip_path = os.path.join('./output', str_sha256(local_md_dir) + '.zip')
     zip_archive_success = compress_directory_to_zip(local_md_dir, archive_zip_path)
     if zip_archive_success == 0:
-        logger.info('压缩成功')
+        logger.info('Compression successful')
     else:
-        logger.error('压缩失败')
+        logger.error('Compression failed')
     md_path = os.path.join(local_md_dir, file_name + '.md')
     with open(md_path, 'r', encoding='utf-8') as f:
         txt_content = f.read()
@@ -121,8 +121,8 @@ latex_delimiters = [
 ]
 
 header_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'resources', 'header.html')
-with open(header_path, 'r') as file:
-    header = file.read()
+with open(header_path, 'r') as header_file:
+    header = header_file.read()
 
 
 latin_lang = [
@@ -175,40 +175,75 @@ def to_pdf(file_path):
 
     return tmp_file_path
 
-
-def main():
-    example_enable = False
-
-    # try:
-    #     print("Start init SgLang engine...")
-    #     from mineru.backend.vlm.vlm_analyze import ModelSingleton
-    #     modelsingleton = ModelSingleton()
-    #     predictor = modelsingleton.get_model(
-    #         "sglang-engine",
-    #         None,
-    #         None,
-    #         mem_fraction_static=0.5,
-    #         enable_torch_compile=True,
-    #     )
-    #     print("SgLang engine init successfully.")
-    # except Exception as e:
-    #     logger.exception(e)
-
+@click.command()
+@click.option(
+    '--enable-example',
+    'example_enable',
+    type=bool,
+    help="Enable example files for input."
+         "The example files to be input need to be placed in the `example` folder within the directory where the command is currently executed.",
+    default=True,
+)
+@click.option(
+    '--enable-sglang-engine',
+    'sglang_engine_enable',
+    type=bool,
+    help="Enable SgLang engine backend for faster processing.",
+    default=False,
+)
+@click.option(
+    '--mem-fraction-static',
+    'mem_fraction_static',
+    type=float,
+    help="Set the static memory fraction for SgLang engine. ",
+    default=0.5,
+)
+@click.option(
+    '--enable-torch-compile',
+    'enable_torch_compile',
+    type=bool,
+    help="Enable torch compile for SgLang engine. ",
+    default=True,
+)
+def main(example_enable, sglang_engine_enable, mem_fraction_static, enable_torch_compile):
+    if sglang_engine_enable:
+        try:
+            print("Start init SgLang engine...")
+            from mineru.backend.vlm.vlm_analyze import ModelSingleton
+            modelsingleton = ModelSingleton()
+            predictor = modelsingleton.get_model(
+                "sglang-engine",
+                None,
+                None,
+                mem_fraction_static=mem_fraction_static,
+                enable_torch_compile=enable_torch_compile,
+            )
+            print("SgLang engine init successfully.")
+        except Exception as e:
+            logger.exception(e)
+
+    suffixes = pdf_suffixes + image_suffixes
     with gr.Blocks() as demo:
         gr.HTML(header)
         with gr.Row():
             with gr.Column(variant='panel', scale=5):
                 with gr.Row():
-                    file = gr.File(label='Please upload a PDF or image', file_types=['.pdf', '.png', '.jpeg', '.jpg'])
+                    input_file = gr.File(label='Please upload a PDF or image', file_types=suffixes)
                 with gr.Row():
                     max_pages = gr.Slider(1, 20, 10, step=1, label='Max convert pages')
                 with gr.Row():
-                    backend = gr.Dropdown(["pipeline", "vlm-transformers", "vlm-sglang-client"], label="Backend", value="pipeline")
-                with gr.Row(visible=True) as ocr_options:
+                    if sglang_engine_enable:
+                        drop_list = ["pipeline", "vlm-sglang-engine"]
+                        preferred_option = "vlm-sglang-engine"
+                    else:
+                        drop_list = ["pipeline", "vlm-transformers", "vlm-sglang-client"]
+                        preferred_option = "pipeline"
+                    backend = gr.Dropdown(drop_list, label="Backend", value=preferred_option)
+                with gr.Row(visible=False) as ocr_options:
                     language = gr.Dropdown(all_lang, label='Language', value='ch')
                 with gr.Row(visible=False) as client_options:
                     url = gr.Textbox(label='Server URL', value='http://localhost:30000', placeholder='http://localhost:30000')
-                with gr.Row(visible=True) as pipeline_options:
+                with gr.Row(visible=False) as pipeline_options:
                     is_ocr = gr.Checkbox(label='Force enable OCR', value=False)
                     formula_enable = gr.Checkbox(label='Enable formula recognition', value=True)
                     table_enable = gr.Checkbox(label='Enable table recognition(test)', value=True)
@@ -217,13 +252,13 @@ def main():
                     clear_bu = gr.ClearButton(value='Clear')
                 pdf_show = PDF(label='PDF preview', interactive=False, visible=True, height=800)
                 if example_enable:
-                    example_root = os.path.join(os.path.dirname(__file__), 'examples')
+                    example_root = os.path.join(os.getcwd(), 'examples')
                     if os.path.exists(example_root):
                         with gr.Accordion('Examples:'):
                             gr.Examples(
                                 examples=[os.path.join(example_root, _) for _ in os.listdir(example_root) if
-                                          _.endswith('pdf')],
-                                inputs=file
+                                          _.endswith(tuple(suffixes))],
+                                inputs=input_file
                             )
 
             with gr.Column(variant='panel', scale=5):
@@ -255,13 +290,19 @@ def main():
             inputs=[backend],
             outputs=[client_options, ocr_options, pipeline_options]
         )
+        # 添加demo.load事件，在页面加载时触发一次界面更新
+        demo.load(
+            fn=update_interface,
+            inputs=[backend],
+            outputs=[client_options, ocr_options, pipeline_options]
+        )
 
-        file.change(fn=to_pdf, inputs=file, outputs=pdf_show)
-        change_bu.click(fn=to_markdown, inputs=[file, max_pages, is_ocr, formula_enable, table_enable, language, backend, url],
+        input_file.change(fn=to_pdf, inputs=input_file, outputs=pdf_show)
+        change_bu.click(fn=to_markdown, inputs=[input_file, max_pages, is_ocr, formula_enable, table_enable, language, backend, url],
                         outputs=[md, md_text, output_file, pdf_show])
-        clear_bu.add([file, md, pdf_show, md_text, output_file, is_ocr])
+        clear_bu.add([input_file, md, pdf_show, md_text, output_file, is_ocr])
 
-    demo.launch(server_name='localhost')
+    demo.launch()
 
 
 if __name__ == '__main__':

projects/README.md

@@ -2,10 +2,6 @@
 
 ## Project List
 
-- Projects compatible with version 2.0:
-  - [gradio_app](./gradio_app/README.md): Web application based on Gradio
-
 - Projects not yet compatible with version 2.0:
-  - [web_api](./web_api/README.md): Web API based on FastAPI
   - [multi_gpu](./multi_gpu/README.md): Multi-GPU parallel processing based on LitServe
   - [mcp](./mcp/README.md): MCP server based on the official API

projects/README_zh-CN.md

@@ -2,10 +2,6 @@
 
 ## 项目列表
 
-- 已兼容2.0版本的项目列表
-  - [gradio_app](./gradio_app/README_zh-CN.md): 基于 Gradio 的 Web 应用
-
 - 未兼容2.0版本的项目列表
-  - [web_api](./web_api/README.md): 基于 FastAPI 的 Web API 
   - [multi_gpu](./multi_gpu/README.md): 基于 LitServe 的多 GPU 并行处理
   - [mcp](./mcp/README.md): 基于官方api的mcp server

projects/gradio_app/README.md

-## Installation
-
-MinerU(>=0.8.0)
- > If you already have a functioning MinerU environment, you can skip this step.
- > 
-[Deploy in CPU environment](https://github.com/opendatalab/MinerU?tab=readme-ov-file#quick-cpu-demo)
-
-[Deploy in GPU environment](https://github.com/opendatalab/MinerU?tab=readme-ov-file#using-gpu)
-
-Third-party Software
-
-```bash
-pip install gradio gradio-pdf
-```
-
-## Start Gradio App
-
-```bash
-python app.py
-```
-
-## Use Gradio App
-
-Access http://127.0.0.1:7860 in your web browser
\ No newline at end of file

projects/gradio_app/README_zh-CN.md

-## 安装
-
-MinerU(>=0.8.0)
- >如已有正常运行的MinerU环境则可以跳过此步骤
-> 
-[在CPU环境部署](https://github.com/opendatalab/MinerU/blob/master/README_zh-CN.md#%E4%BD%BF%E7%94%A8cpu%E5%BF%AB%E9%80%9F%E4%BD%93%E9%AA%8C)
-
-[在GPU环境部署](https://github.com/opendatalab/MinerU/blob/master/README_zh-CN.md#%E4%BD%BF%E7%94%A8gpu)
-
-第三方软件
-
-```bash
-pip install gradio gradio-pdf
-```
-
-## 启动gradio应用
-
-```bash
-python app.py
-```
-
-## 使用gradio应用
-
-在浏览器中访问 http://127.0.0.1:7860
\ No newline at end of file

projects/gradio_app/app.py

-# Copyright (c) Opendatalab. All rights reserved.
-
-import base64
-import os
-import re
-import time
-import zipfile
-from pathlib import Path
-
-import gradio as gr
-from gradio_pdf import PDF
-from loguru import logger
-
-from mineru.cli.common import prepare_env, do_parse, read_fn
-from mineru.utils.hash_utils import str_sha256
-
-
-def parse_pdf(doc_path, output_dir, end_page_id, is_ocr, formula_enable, table_enable, language):
-    os.makedirs(output_dir, exist_ok=True)
-
-    try:
-        file_name = f'{str(Path(doc_path).stem)}_{time.strftime("%y%m%d_%H%M%S")}'
-        pdf_data = read_fn(doc_path)
-        if is_ocr:
-            parse_method = 'ocr'
-        else:
-            parse_method = 'auto'
-        local_image_dir, local_md_dir = prepare_env(output_dir, file_name, parse_method)
-        do_parse(
-            output_dir=output_dir,
-            pdf_file_names=[file_name],
-            pdf_bytes_list=[pdf_data],
-            p_lang_list=[language],
-            parse_method=parse_method,
-            end_page_id=end_page_id,
-            p_formula_enable=formula_enable,
-            p_table_enable=table_enable,
-        )
-        return local_md_dir, file_name
-    except Exception as e:
-        logger.exception(e)
-
-
-def compress_directory_to_zip(directory_path, output_zip_path):
-    """压缩指定目录到一个 ZIP 文件。
-
-    :param directory_path: 要压缩的目录路径
-    :param output_zip_path: 输出的 ZIP 文件路径
-    """
-    try:
-        with zipfile.ZipFile(output_zip_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
-
-            # 遍历目录中的所有文件和子目录
-            for root, dirs, files in os.walk(directory_path):
-                for file in files:
-                    # 构建完整的文件路径
-                    file_path = os.path.join(root, file)
-                    # 计算相对路径
-                    arcname = os.path.relpath(file_path, directory_path)
-                    # 添加文件到 ZIP 文件
-                    zipf.write(file_path, arcname)
-        return 0
-    except Exception as e:
-        logger.exception(e)
-        return -1
-
-
-def image_to_base64(image_path):
-    with open(image_path, 'rb') as image_file:
-        return base64.b64encode(image_file.read()).decode('utf-8')
-
-
-def replace_image_with_base64(markdown_text, image_dir_path):
-    # 匹配Markdown中的图片标签
-    pattern = r'\!\[(?:[^\]]*)\]\(([^)]+)\)'
-
-    # 替换图片链接
-    def replace(match):
-        relative_path = match.group(1)
-        full_path = os.path.join(image_dir_path, relative_path)
-        base64_image = image_to_base64(full_path)
-        return f'![{relative_path}](data:image/jpeg;base64,{base64_image})'
-
-    # 应用替换
-    return re.sub(pattern, replace, markdown_text)
-
-
-def to_markdown(file_path, end_pages, is_ocr, formula_enable, table_enable, language):
-    file_path = to_pdf(file_path)
-    # 获取识别的md文件以及压缩包文件路径
-    local_md_dir, file_name = parse_pdf(file_path, './output', end_pages - 1, is_ocr, formula_enable, table_enable, language)
-    archive_zip_path = os.path.join('./output', str_sha256(local_md_dir) + '.zip')
-    zip_archive_success = compress_directory_to_zip(local_md_dir, archive_zip_path)
-    if zip_archive_success == 0:
-        logger.info('压缩成功')
-    else:
-        logger.error('压缩失败')
-    md_path = os.path.join(local_md_dir, file_name + '.md')
-    with open(md_path, 'r', encoding='utf-8') as f:
-        txt_content = f.read()
-    md_content = replace_image_with_base64(txt_content, local_md_dir)
-    # 返回转换后的PDF路径
-    new_pdf_path = os.path.join(local_md_dir, file_name + '_layout.pdf')
-
-    return md_content, txt_content, archive_zip_path, new_pdf_path
-
-
-latex_delimiters = [
-    {'left': '$$', 'right': '$$', 'display': True},
-    {'left': '$', 'right': '$', 'display': False},
-    {'left': '\\(', 'right': '\\)', 'display': False},
-    {'left': '\\[', 'right': '\\]', 'display': True},
-]
-
-
-with open('header.html', 'r') as file:
-    header = file.read()
-
-
-latin_lang = [
-        'af', 'az', 'bs', 'cs', 'cy', 'da', 'de', 'es', 'et', 'fr', 'ga', 'hr',  # noqa: E126
-        'hu', 'id', 'is', 'it', 'ku', 'la', 'lt', 'lv', 'mi', 'ms', 'mt', 'nl',
-        'no', 'oc', 'pi', 'pl', 'pt', 'ro', 'rs_latin', 'sk', 'sl', 'sq', 'sv',
-        'sw', 'tl', 'tr', 'uz', 'vi', 'french', 'german'
-]
-arabic_lang = ['ar', 'fa', 'ug', 'ur']
-cyrillic_lang = [
-        'ru', 'rs_cyrillic', 'be', 'bg', 'uk', 'mn', 'abq', 'ady', 'kbd', 'ava',  # noqa: E126
-        'dar', 'inh', 'che', 'lbe', 'lez', 'tab'
-]
-devanagari_lang = [
-        'hi', 'mr', 'ne', 'bh', 'mai', 'ang', 'bho', 'mah', 'sck', 'new', 'gom',  # noqa: E126
-        'sa', 'bgc'
-]
-other_lang = ['ch', 'ch_lite', 'ch_server', 'en', 'korean', 'japan', 'chinese_cht', 'ta', 'te', 'ka']
-add_lang = ['latin', 'arabic', 'cyrillic', 'devanagari']
-
-# all_lang = ['', 'auto']
-all_lang = []
-# all_lang.extend([*other_lang, *latin_lang, *arabic_lang, *cyrillic_lang, *devanagari_lang])
-all_lang.extend([*other_lang, *add_lang])
-
-
-def safe_stem(file_path):
-    stem = Path(file_path).stem
-    # 只保留字母、数字、下划线和点，其他字符替换为下划线
-    return re.sub(r'[^\w.]', '_', stem)
-
-
-def to_pdf(file_path):
-
-    if file_path is None:
-        return None
-
-    pdf_bytes = read_fn(file_path)
-
-    # unique_filename = f'{uuid.uuid4()}.pdf'
-    unique_filename = f'{safe_stem(file_path)}.pdf'
-
-    # 构建完整的文件路径
-    tmp_file_path = os.path.join(os.path.dirname(file_path), unique_filename)
-
-    # 将字节数据写入文件
-    with open(tmp_file_path, 'wb') as tmp_pdf_file:
-        tmp_pdf_file.write(pdf_bytes)
-
-    return tmp_file_path
-
-
-if __name__ == '__main__':
-    with gr.Blocks() as demo:
-        gr.HTML(header)
-        with gr.Row():
-            with gr.Column(variant='panel', scale=5):
-                with gr.Row():
-                    file = gr.File(label='Please upload a PDF or image', file_types=['.pdf', '.png', '.jpeg', '.jpg'])
-                with gr.Row(equal_height=True):
-                    with gr.Column(scale=4):
-                        max_pages = gr.Slider(1, 20, 10, step=1, label='Max convert pages')
-                    with gr.Column(scale=1):
-                        language = gr.Dropdown(all_lang, label='Language', value='ch')
-                with gr.Row():
-                    is_ocr = gr.Checkbox(label='Force enable OCR', value=False)
-                    formula_enable = gr.Checkbox(label='Enable formula recognition', value=True)
-                    table_enable = gr.Checkbox(label='Enable table recognition(test)', value=True)
-                with gr.Row():
-                    change_bu = gr.Button('Convert')
-                    clear_bu = gr.ClearButton(value='Clear')
-                pdf_show = PDF(label='PDF preview', interactive=False, visible=True, height=800)
-                with gr.Accordion('Examples:'):
-                    example_root = os.path.join(os.path.dirname(__file__), 'examples')
-                    gr.Examples(
-                        examples=[os.path.join(example_root, _) for _ in os.listdir(example_root) if
-                                  _.endswith('pdf')],
-                        inputs=file
-                    )
-
-            with gr.Column(variant='panel', scale=5):
-                output_file = gr.File(label='convert result', interactive=False)
-                with gr.Tabs():
-                    with gr.Tab('Markdown rendering'):
-                        md = gr.Markdown(label='Markdown rendering', height=1100, show_copy_button=True,
-                                         latex_delimiters=latex_delimiters,
-                                         line_breaks=True)
-                    with gr.Tab('Markdown text'):
-                        md_text = gr.TextArea(lines=45, show_copy_button=True)
-        file.change(fn=to_pdf, inputs=file, outputs=pdf_show)
-        change_bu.click(fn=to_markdown, inputs=[file, max_pages, is_ocr, formula_enable, table_enable, language],
-                        outputs=[md, md_text, output_file, pdf_show])
-        clear_bu.add([file, md, pdf_show, md_text, output_file, is_ocr])
-
-    demo.launch(server_name='0.0.0.0')