myhloli commited on
Commit
919ceab
·
1 Parent(s): b361723

iframe (#14)

Browse files

- Switch Space to static embedded demo (108d2572fa717b1f640e8cb29ee872ff5b654351)

Files changed (6) hide show
  1. .gitattributes +1 -1
  2. README.md +6 -9
  3. app.py +0 -42
  4. index.html +49 -0
  5. packages.txt +0 -2
  6. requirements.txt +0 -2
.gitattributes CHANGED
@@ -32,7 +32,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.xz filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -textexamples/demo1.docx filter=lfs diff=lfs merge=lfs -text
36
  examples/demo1.docx filter=lfs diff=lfs merge=lfs -text
37
  examples/demo1.pdf filter=lfs diff=lfs merge=lfs -text
38
  examples/demo2.pdf filter=lfs diff=lfs merge=lfs -text
 
32
  *.xz filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  examples/demo1.docx filter=lfs diff=lfs merge=lfs -text
37
  examples/demo1.pdf filter=lfs diff=lfs merge=lfs -text
38
  examples/demo2.pdf filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -3,20 +3,17 @@ title: MinerU Document Extraction Tools
3
  emoji: 📚
4
  colorFrom: purple
5
  colorTo: blue
6
- sdk: gradio
7
- sdk_version: 6.8.0
8
- app_file: app.py
9
  pinned: true
10
  license: apache-2.0
11
- python_version: 3.12
12
- models:
13
- - opendatalab/PDF-Extract-Kit-1.0
14
- - opendatalab/MinerU2.5-Pro-2605-1.2B
15
  thumbnail: >-
16
  https://cdn-uploads.huggingface.co/production/uploads/668f77a3b3991ac0c308a441/dsQTqtqf8SiM5oDe1FKFY.png
17
- short_description: Easy converting PDF and Office docs into Markdown and JSON
 
 
18
  ---
19
 
20
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
21
 
22
- Paper: https://huggingface.co/papers/2409.18839
 
3
  emoji: 📚
4
  colorFrom: purple
5
  colorTo: blue
6
+ sdk: static
7
+ app_file: index.html
 
8
  pinned: true
9
  license: apache-2.0
 
 
 
 
10
  thumbnail: >-
11
  https://cdn-uploads.huggingface.co/production/uploads/668f77a3b3991ac0c308a441/dsQTqtqf8SiM5oDe1FKFY.png
12
+ short_description: Embedded MinerU document extraction demo
13
+ fullWidth: true
14
+ header: mini
15
  ---
16
 
17
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
18
 
19
+ Paper: https://huggingface.co/papers/2409.18839
app.py DELETED
@@ -1,42 +0,0 @@
1
- # Copyright (c) Opendatalab. All rights reserved.
2
-
3
- import os
4
- import json
5
- from loguru import logger
6
-
7
-
8
- if __name__ == '__main__':
9
- os.system('pip uninstall -y mineru')
10
- os.system('pip install git+https://github.com/myhloli/Magic-PDF.git@dev')
11
- os.system('pip install -U mineru_vl_utils')
12
- os.system('pip uninstall -y onnxruntime')
13
- os.system('pip install onnxruntime-gpu==1.23.2')
14
- os.system('mineru-models-download -s huggingface -m all')
15
- # os.system('mineru-models-download -s modelscope -m all')
16
- os.environ['MINERU_MODEL_SOURCE'] = "local"
17
- os.environ['GRADIO_SSR_MODE'] = "false"
18
- os.environ['MINERU_PDF_RENDER_TIMEOUT'] = "10"
19
- try:
20
- home_dir = os.path.expanduser('~')
21
- config_file = os.path.join(home_dir, 'mineru.json')
22
- with open(config_file, 'r+') as file:
23
- config = json.load(file)
24
-
25
- delimiters = {
26
- 'display': {'left': '\\[', 'right': '\\]'},
27
- 'inline': {'left': '\\(', 'right': '\\)'}
28
- }
29
-
30
- config['latex-delimiter-config'] = delimiters
31
-
32
- if os.getenv('apikey'):
33
- config['llm-aided-config']['title_aided']['api_key'] = os.getenv('apikey')
34
- config['llm-aided-config']['title_aided']['enable'] = True
35
- config['llm-aided-config']['title_aided']['model'] = "qwen3.5-flash"
36
-
37
- file.seek(0) # 将文件指针移回文件开始位置
38
- file.truncate() # 截断文件,清除原有内容
39
- json.dump(config, file, indent=4) # 写入新内容
40
- except Exception as e:
41
- logger.exception(e)
42
- os.system('mineru-gradio --enable-api false --max-convert-pages 20 --latex-delimiters-type b --gpu-memory-utilization 0.5 --enable-vlm-preload true --client-side-output-generation true')
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
index.html ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!doctype html>
2
+ <html lang="zh-CN">
3
+ <head>
4
+ <meta charset="utf-8">
5
+ <meta name="viewport" content="width=device-width, initial-scale=1">
6
+ <meta name="color-scheme" content="light dark">
7
+ <title>MinerU Document Extraction Tools</title>
8
+ <style>
9
+ html,
10
+ body {
11
+ width: 100%;
12
+ height: 100%;
13
+ margin: 0;
14
+ overflow: hidden;
15
+ background: #ffffff;
16
+ }
17
+
18
+ iframe {
19
+ width: 100%;
20
+ height: 100vh;
21
+ min-height: 100vh;
22
+ border: 0;
23
+ display: block;
24
+ }
25
+
26
+ noscript {
27
+ position: fixed;
28
+ inset: 0;
29
+ display: grid;
30
+ place-items: center;
31
+ padding: 24px;
32
+ font: 16px/1.5 system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
33
+ color: #1f2937;
34
+ background: #ffffff;
35
+ }
36
+ </style>
37
+ </head>
38
+ <body>
39
+ <iframe
40
+ src="https://opendatalab-mineru.ms.show"
41
+ title="MinerU Document Extraction Tools"
42
+ allow="clipboard-read; clipboard-write; fullscreen"
43
+ referrerpolicy="strict-origin-when-cross-origin"
44
+ ></iframe>
45
+ <noscript>
46
+ 当前页面需要启用 JavaScript 才能加载 MinerU 文档提取演示。
47
+ </noscript>
48
+ </body>
49
+ </html>
packages.txt DELETED
@@ -1,2 +0,0 @@
1
- fonts-noto-core
2
- fonts-noto-cjk
 
 
 
requirements.txt DELETED
@@ -1,2 +0,0 @@
1
- mineru[core]>=3.2.0
2
- vllm==0.21.0