Merge pull request #838 from opendatalab/release-0.9.0

Release 0.9.0

.github/workflows/cla.yml

@@ -29,7 +29,7 @@ jobs:
           path-to-document: 'https://github.com/opendatalab/MinerU/blob/master/MinerU_CLA.md' # e.g. a CLA or a DCO document
           # branch should not be protected
           branch: 'master'
-          allowlist: myhloli,dt-yy,Focusshang,renpengli01,icecraft,drunkpig,wangbinDL,qiangqiang199,GDDGCZ518,papayalove,conghui,quyuan
+          allowlist: myhloli,dt-yy,Focusshang,renpengli01,icecraft,drunkpig,wangbinDL,qiangqiang199,GDDGCZ518,papayalove,conghui,quyuan,LollipopsAndWine
 
          # the followings are the optional inputs - If the optional inputs are not given, then default values will be taken
           #remote-organization-name: enter the remote organization name where the signatures should be stored (Default is storing the signatures in the same repository)

.github/workflows/cli.yml

@@ -10,7 +10,6 @@ on:
     paths-ignore:
       - "cmds/**"
       - "**.md"
-      - "**.yml"
   pull_request:
     branches:
       - "master"
@@ -18,12 +17,11 @@ on:
     paths-ignore:
       - "cmds/**"
       - "**.md"
-      - "**.yml"
   workflow_dispatch:
 jobs:
   cli-test:
     runs-on: pdf
-    timeout-minutes: 120
+    timeout-minutes: 240
     strategy:
       fail-fast: true
 
@@ -33,16 +31,16 @@ jobs:
       with:
         fetch-depth: 2
 
-    - name: install
+    - name: install&test
       run: |
-        echo $GITHUB_WORKSPACE && sh tests/retry_env.sh
-    - name: unit test
-      run: |        
-        cd $GITHUB_WORKSPACE && export PYTHONPATH=. && coverage run -m  pytest  tests/test_unit.py --cov=magic_pdf/ --cov-report term-missing --cov-report html
+        source activate mineru
+        conda env list
+        pip show coverage
+        # cd $GITHUB_WORKSPACE && sh tests/retry_env.sh
+        cd $GITHUB_WORKSPACE && python tests/clean_coverage.py      
+        cd $GITHUB_WORKSPACE && coverage run -m pytest tests/unittest/ --cov=magic_pdf/  --cov-report html --cov-report term-missing
         cd $GITHUB_WORKSPACE && python tests/get_coverage.py
-    - name: cli test
-      run: |
-        cd $GITHUB_WORKSPACE &&  pytest -s -v tests/test_cli/test_cli_sdk.py
+        cd $GITHUB_WORKSPACE && pytest -m P0 -s -v tests/test_cli/test_cli_sdk.py
 
   notify_to_feishu:
     if: ${{ always() && !cancelled() && contains(needs.*.result, 'failure') && (github.ref_name == 'master') }}

.github/workflows/daily.yml

+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: mineru
+on:
+  schedule:
+    - cron: '0 22 * * *'  # 每天晚上 10 点执行
+jobs:
+  cli-test:
+    runs-on: pdf
+    timeout-minutes: 240
+    strategy:
+      fail-fast: true
+
+    steps:
+    - name: PDF cli
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: install&test
+      run: |
+        source activate mineru
+        conda env list
+        pip show coverage
+        # cd $GITHUB_WORKSPACE && sh tests/retry_env.sh
+        cd $GITHUB_WORKSPACE && python tests/clean_coverage.py      
+        cd $GITHUB_WORKSPACE && coverage run -m pytest tests/unittest/ --cov=magic_pdf/  --cov-report html --cov-report term-missing
+        cd $GITHUB_WORKSPACE && python tests/get_coverage.py
+        cd $GITHUB_WORKSPACE && pytest -s -v tests/test_cli/test_cli_sdk.py
+
+  notify_to_feishu:
+    if: ${{ always() && !cancelled() && contains(needs.*.result, 'failure') && (github.ref_name == 'master') }}
+    needs: cli-test
+    runs-on: pdf
+    steps:
+    - name: get_actor
+      run: |
+          metion_list="dt-yy"
+          echo $GITHUB_ACTOR
+          if [[ $GITHUB_ACTOR == "drunkpig" ]]; then
+            metion_list="xuchao"
+          elif [[ $GITHUB_ACTOR == "myhloli" ]]; then
+            metion_list="zhaoxiaomeng"
+          elif [[ $GITHUB_ACTOR == "icecraft" ]]; then
+            metion_list="xurui1"
+          fi
+          echo $metion_list
+          echo "METIONS=$metion_list" >> "$GITHUB_ENV"
+          echo ${{ env.METIONS }}
+
+    - name: notify
+      run: |
+        echo ${{ secrets.USER_ID }}
+        curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"'${{ github.repository }}' GitHubAction Failed","content":[[{"tag":"text","text":""},{"tag":"a","text":"Please click here for details ","href":"https://github.com/'${{ github.repository }}'/actions/runs/'${GITHUB_RUN_ID}'"},{"tag":"at","user_id":"'${{ secrets.USER_ID }}'"}]]}}}}'  ${{ secrets.WEBHOOK_URL }}

.github/workflows/huigui.yml

+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: mineru
+on:
+  push:
+    branches:
+      - "master"
+      - "dev"
+    paths-ignore:
+      - "cmds/**"
+      - "**.md"
+  workflow_dispatch:
+jobs:
+  cli-test:
+    runs-on: pdf
+    timeout-minutes: 240
+    strategy:
+      fail-fast: true
+
+    steps:
+    - name: PDF cli
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: install&test
+      run: |
+        source activate mineru
+        conda env list
+        pip show coverage
+        # cd $GITHUB_WORKSPACE && sh tests/retry_env.sh
+        cd $GITHUB_WORKSPACE && python tests/clean_coverage.py      
+        cd $GITHUB_WORKSPACE && coverage run -m pytest tests/unittest/ --cov=magic_pdf/  --cov-report html --cov-report term-missing
+        cd $GITHUB_WORKSPACE && python tests/get_coverage.py
+        cd $GITHUB_WORKSPACE && pytest -s -v tests/test_cli/test_cli_sdk.py
+
+  notify_to_feishu:
+    if: ${{ always() && !cancelled() && contains(needs.*.result, 'failure') && (github.ref_name == 'master') }}
+    needs: cli-test
+    runs-on: pdf
+    steps:
+    - name: get_actor
+      run: |
+          metion_list="dt-yy"
+          echo $GITHUB_ACTOR
+          if [[ $GITHUB_ACTOR == "drunkpig" ]]; then
+            metion_list="xuchao"
+          elif [[ $GITHUB_ACTOR == "myhloli" ]]; then
+            metion_list="zhaoxiaomeng"
+          elif [[ $GITHUB_ACTOR == "icecraft" ]]; then
+            metion_list="xurui1"
+          fi
+          echo $metion_list
+          echo "METIONS=$metion_list" >> "$GITHUB_ENV"
+          echo ${{ env.METIONS }}
+
+    - name: notify
+      run: |
+        echo ${{ secrets.USER_ID }}
+        curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"'${{ github.repository }}' GitHubAction Failed","content":[[{"tag":"text","text":""},{"tag":"a","text":"Please click here for details ","href":"https://github.com/'${{ github.repository }}'/actions/runs/'${GITHUB_RUN_ID}'"},{"tag":"at","user_id":"'${{ secrets.USER_ID }}'"}]]}}}}'  ${{ secrets.WEBHOOK_URL }}

.github/workflows/update_base.yml

-# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
-# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
-
-name: update-base
-on:
-  push:
-    tags:
-      - '*released'
-  workflow_dispatch:
-jobs:
-  pdf-test:
-    runs-on: pdf
-    timeout-minutes: 40
-
-
-    steps:
-    - name: update-base
-      uses: actions/checkout@v3
-    - name: start-update
-      run: |
-        echo "start test"
-  

.gitignore

-*.tar
-*.tar.gz
-venv*/
-envs/
-slurm_logs/
-
-sync1.sh
-data_preprocess_pj1
-data-preparation1
-__pycache__
-*.log
-*.pyc
-.vscode
-debug/
-*.ipynb
-.idea
-
-# vscode history
-.history
-
-.DS_Store
-.env
-
-bad_words/
-bak/
-
-app/tests/*
-temp/
-tmp/
-tmp
-.vscode
-.vscode/
-ocr_demo
-
-/app/common/__init__.py
-/magic_pdf/config/__init__.py
-source.dev.env
-
-tmp
+*.tar
+*.tar.gz
+*.zip
+venv*/
+envs/
+slurm_logs/
+
+sync1.sh
+data_preprocess_pj1
+data-preparation1
+__pycache__
+*.log
+*.pyc
+.vscode
+debug/
+*.ipynb
+.idea
+
+# vscode history
+.history
+
+.DS_Store
+.env
+
+bad_words/
+bak/
+
+app/tests/*
+temp/
+tmp/
+tmp
+.vscode
+.vscode/
+ocr_demo
+.coveragerc
+/app/common/__init__.py
+/magic_pdf/config/__init__.py
+source.dev.env
+
+tmp
+
+projects/web/node_modules
+projects/web/dist
+
+projects/web_demo/web_demo/static/
+cli_debug/
+debug_utils/
+
+# sphinx docs
+_build/

.pre-commit-config.yaml

@@ -3,7 +3,7 @@ repos:
     rev: 5.0.4
     hooks:
       - id: flake8
-        args: ["--max-line-length=120", "--ignore=E131,E125,W503,W504,E203"]
+        args: ["--max-line-length=150", "--ignore=E131,E125,W503,W504,E203"]
   - repo: https://github.com/PyCQA/isort
     rev: 5.11.5
     hooks:
@@ -12,11 +12,12 @@ repos:
     rev: v0.32.0
     hooks:
       - id: yapf
-        args: ["--style={based_on_style: google, column_limit: 120, indent_width: 4}"]
+        args: ["--style={based_on_style: google, column_limit: 150, indent_width: 4}"]
   - repo: https://github.com/codespell-project/codespell
     rev: v2.2.1
     hooks:
       - id: codespell
+        args: ['--skip', '*.json']
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.3.0
     hooks:

.readthedocs.yaml

+version: 2
+
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.10"
+
+formats:
+  - epub
+
+python:
+  install:
+    - requirements: docs/zh_cn/requirements.txt
+
+sphinx:
+  configuration: docs/zh_cn/conf.py

Dockerfile

@@ -31,7 +31,7 @@ RUN python3 -m venv /opt/mineru_venv
 RUN /bin/bash -c "source /opt/mineru_venv/bin/activate && \
     pip3 install --upgrade pip && \
     wget https://gitee.com/myhloli/MinerU/raw/master/requirements-docker.txt && \
-    pip3 install -r requirements-docker.txt --extra-index-url https://wheels.myhloli.com -i https://pypi.tuna.tsinghua.edu.cn/simple && \
+    pip3 install -r requirements-docker.txt --extra-index-url https://wheels.myhloli.com -i https://mirrors.aliyun.com/pypi/simple && \
     pip3 install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/"
 
 # Copy the configuration file template and install magic-pdf latest

LICENSE.md

@@ -659,3 +659,4 @@ specific requirements.
 if any, to sign a "copyright disclaimer" for the program, if necessary.
 For more information on this, and how to apply and follow the GNU AGPL, see
 <https://www.gnu.org/licenses/>.
+

README.md

@@ -18,8 +18,10 @@
 [![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/papayalove/b5f4913389e7ff9883c6b687de156e78/mineru_demo.ipynb)
+
 [![Paper](https://img.shields.io/badge/Paper-arXiv-green)](https://arxiv.org/abs/2409.18839)
 
+
 <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>
 
 <!-- language -->
@@ -41,6 +43,19 @@
 </div>
 
 # Changelog
+- 2024/10/31 0.9.0 released. This is a major new version with extensive code refactoring, addressing numerous issues, improving performance, reducing hardware requirements, and enhancing usability:
+  - Refactored the sorting module code to use [layoutreader](https://github.com/ppaanngggg/layoutreader) for reading order sorting, ensuring high accuracy in various layouts.
+  - Refactored the paragraph concatenation module to achieve good results in cross-column, cross-page, cross-figure, and cross-table scenarios.
+  - Refactored the list and table of contents recognition functions, significantly improving the accuracy of list blocks and table of contents blocks, as well as the parsing of corresponding text paragraphs.
+  - Refactored the matching logic for figures, tables, and descriptive text, greatly enhancing the accuracy of matching captions and footnotes to figures and tables, and reducing the loss rate of descriptive text to near zero.
+  - Added multi-language support for OCR, supporting detection and recognition of 84 languages.For the list of supported languages, see [OCR Language Support List](https://paddlepaddle.github.io/PaddleOCR/latest/en/ppocr/blog/multi_languages.html#5-support-languages-and-abbreviations).
+  - Added memory recycling logic and other memory optimization measures, significantly reducing memory usage. The memory requirement for enabling all acceleration features except table acceleration (layout/formula/OCR) has been reduced from 16GB to 8GB, and the memory requirement for enabling all acceleration features has been reduced from 24GB to 10GB.
+  - Optimized configuration file feature switches, adding an independent formula detection switch to significantly improve speed and parsing results when formula detection is not needed.
+  - Integrated [PDF-Extract-Kit 1.0](https://github.com/opendatalab/PDF-Extract-Kit):
+    - Added the self-developed `doclayout_yolo` model, which speeds up processing by more than 10 times compared to the original solution while maintaining similar parsing effects, and can be freely switched with `layoutlmv3` via the configuration file.
+    - Upgraded formula parsing to `unimernet 0.2.1`, improving formula parsing accuracy while significantly reducing memory usage.
+    - Due to the repository change for `PDF-Extract-Kit 1.0`, you need to re-download the model. Please refer to [How to Download Models](docs/how_to_download_models_en.md) for detailed steps.
+- 2024/09/27 Version 0.8.1 released, Fixed some bugs, and providing a [localized deployment version](projects/web_demo/README.md) of the [online demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/) and the [front-end interface](projects/web/README.md).
 - 2024/09/09: Version 0.8.0 released, supporting fast deployment with Dockerfile, and launching demos on Huggingface and Modelscope.
 - 2024/08/30: Version 0.7.1 released, add paddle tablemaster table recognition option
 - 2024/08/09: Version 0.7.0b1 released, simplified installation process, added table recognition functionality
@@ -68,6 +83,7 @@
             <ul>
             <li><a href="#command-line">Command Line</a></li>
             <li><a href="#api">API</a></li>
+            <li><a href="#deploy-derived-projects">Deploy Derived Projects</a></li>
             <li><a href="#development-guide">Development Guide</a></li>
             </ul>
         </li>
@@ -99,15 +115,18 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
 
 ## Key Features
 
-- Removes elements such as headers, footers, footnotes, and page numbers while maintaining semantic continuity
-- Outputs text in a human-readable order from multi-column documents
-- Retains the original structure of the document, including titles, paragraphs, and lists
-- Extracts images, image captions, tables, and table captions
-- Automatically recognizes formulas in the document and converts them to LaTeX
-- Automatically recognizes tables in the document and converts them to LaTeX
-- Automatically detects and enables OCR for corrupted PDFs
-- Supports both CPU and GPU environments
-- Supports Windows, Linux, and Mac platforms
+- Remove headers, footers, footnotes, page numbers, etc., to ensure semantic coherence.
+- Output text in human-readable order, suitable for single-column, multi-column, and complex layouts.
+- Preserve the structure of the original document, including headings, paragraphs, lists, etc.
+- Extract images, image descriptions, tables, table titles, and footnotes.
+- Automatically recognize and convert formulas in the document to LaTeX format.
+- Automatically recognize and convert tables in the document to LaTeX or HTML format.
+- Automatically detect scanned PDFs and garbled PDFs and enable OCR functionality.
+- OCR supports detection and recognition of 84 languages.
+- Supports multiple output formats, such as multimodal and NLP Markdown, JSON sorted by reading order, and rich intermediate formats.
+- Supports various visualization results, including layout visualization and span visualization, for efficient confirmation of output quality.
+- Supports both CPU and GPU environments.
+- Compatible with Windows, Linux, and Mac platforms.
 
 ## Quick Start
 
@@ -138,8 +157,8 @@ In non-mainline environments, due to the diversity of hardware and software conf
     </tr>
     <tr>
         <td colspan="3">CPU</td>
-        <td>x86_64</td>
-        <td>x86_64</td>
+        <td>x86_64(unsupported ARM Linux)</td>
+        <td>x86_64(unsupported ARM Windows)</td>
         <td>x86_64 / arm64</td>
     </tr>
     <tr>
@@ -148,7 +167,7 @@ In non-mainline environments, due to the diversity of hardware and software conf
     </tr>
     <tr>
         <td colspan="3">Python Version</td>
-        <td colspan="3">3.10</td>
+        <td colspan="3">3.10(Please make sure to create a Python 3.10 virtual environment using conda)</td>
     </tr>
     <tr>
         <td colspan="3">Nvidia Driver Version</td>
@@ -165,22 +184,24 @@ In non-mainline environments, due to the diversity of hardware and software conf
     <tr>
         <td rowspan="2">GPU Hardware Support List</td>
         <td colspan="2">Minimum Requirement 8G+ VRAM</td>
-        <td colspan="2">3060ti/3070/3080/3080ti/4060/4070/4070ti<br>
-        8G VRAM only enables layout and formula recognition acceleration</td>
+        <td colspan="2">3060ti/3070/4060<br>
+        8G VRAM enables layout, formula recognition acceleration and OCR acceleration</td>
         <td rowspan="2">None</td>
     </tr>
     <tr>
-        <td colspan="2">Recommended Configuration 16G+ VRAM</td>
-        <td colspan="2">3090/3090ti/4070ti super/4080/4090<br>
-        16G or more can enable layout, formula recognition, and OCR acceleration simultaneously<br>
-        24G or more can enable layout, formula recognition, OCR acceleration and table recognition simultaneously
+        <td colspan="2">Recommended Configuration 10G+ VRAM</td>
+        <td colspan="2">3080/3080ti/3090/3090ti/4070/4070ti/4070tisuper/4080/4090<br>
+        10G VRAM or more can enable layout, formula recognition, OCR acceleration and table recognition acceleration simultaneously
         </td>
     </tr>
 </table>
 
 ### Online Demo
 
+Stable Version (Stable version verified by QA):  
 [![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
+
+Test Version (Synced with dev branch updates, testing new features):  
 [![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)
 
@@ -207,14 +228,23 @@ You can find the `magic-pdf.json` file in your 【user directory】.
 
 You can modify certain configurations in this file to enable or disable features, such as table recognition:
 
+
 > If the following items are not present in the JSON, please manually add the required items and remove the comment content (standard JSON does not support comments).
 
 ```json
 {
-  // other config
-  "table-config": {
-        "model": "TableMaster", // Another option of this value is 'struct_eqtable'
-        "is_table_recog_enable": false, // Table recognition is disabled by default, modify this value to enable it
+    // other config
+    "layout-config": {
+        "model": "layoutlmv3" // Please change to "doclayout_yolo" when using doclayout_yolo.
+    },
+    "formula-config": {
+        "mfd_model": "yolo_v8_mfd",
+        "mfr_model": "unimernet_small",
+        "enable": true  // The formula recognition feature is enabled by default. If you need to disable it, please change the value here to "false".
+    },
+    "table-config": {
+        "model": "tablemaster",  // When using structEqTable, please change to "struct_eqtable".
+        "enable": false, // The table recognition feature is disabled by default. If you need to enable it, please change the value here to "true".
         "max_time": 400
     }
 }
@@ -252,13 +282,26 @@ Usage: magic-pdf [OPTIONS]
 Options:
   -v, --version                display the version and exit
   -p, --path PATH              local pdf filepath or directory  [required]
-  -o, --output-dir TEXT        output local directory
-  -m, --method [ocr|txt|auto]  the method for parsing pdf.
-                               ocr: using ocr technique to extract information from pdf,
-                               txt: suitable for the text-based pdf only and outperform ocr,
-                               auto: automatically choose the best method for parsing pdf
-                                  from ocr and txt.
-                               without method specified, auto will be used by default.
+  -o, --output-dir PATH        output local directory  [required]
+  -m, --method [ocr|txt|auto]  the method for parsing pdf. ocr: using ocr
+                               technique to extract information from pdf. txt:
+                               suitable for the text-based pdf only and
+                               outperform ocr. auto: automatically choose the
+                               best method for parsing pdf from ocr and txt.
+                               without method specified, auto will be used by
+                               default.
+  -l, --lang TEXT              Input the languages in the pdf (if known) to
+                               improve OCR accuracy.  Optional. You should
+                               input "Abbreviation" with language form url: ht
+                               tps://paddlepaddle.github.io/PaddleOCR/latest/en
+                               /ppocr/blog/multi_languages.html#5-support-languages-
+                               and-abbreviations
+  -d, --debug BOOLEAN          Enables detailed debugging information during
+                               the execution of the CLI commands.
+  -s, --start INTEGER          The starting page for PDF parsing, beginning
+                               from 0.
+  -e, --end INTEGER            The ending page for PDF parsing, beginning from
+                               0.
   --help                       Show this message and exit.
 
 
@@ -275,11 +318,12 @@ The results will be saved in the `{some_output_dir}` directory. The output file
 ```text
 ├── some_pdf.md                          # markdown file
 ├── images                               # directory for storing images
-├── some_pdf_layout.pdf                  # layout diagram
+├── some_pdf_layout.pdf                  # layout diagram (Include layout reading order)
 ├── some_pdf_middle.json                 # MinerU intermediate processing result
 ├── some_pdf_model.json                  # model inference result
 ├── some_pdf_origin.pdf                  # original PDF file
-└── some_pdf_spans.pdf                   # smallest granularity bbox position information diagram
+├── some_pdf_spans.pdf                   # smallest granularity bbox position information diagram
+└── some_pdf_content_list.json           # Rich text JSON arranged in reading order
 ```
 
 For more information about the output files, please refer to the [Output File Description](docs/output_file_en_us.md).
@@ -319,29 +363,38 @@ For detailed implementation, refer to:
 - [demo.py Simplest Processing Method](demo/demo.py)
 - [magic_pdf_parse_main.py More Detailed Processing Workflow](demo/magic_pdf_parse_main.py)
 
+### Deploy Derived Projects
+
+Derived projects include secondary development projects based on MinerU by project developers and community developers,  
+such as application interfaces based on Gradio, RAG based on llama, web demos similar to the official website, lightweight multi-GPU load balancing client/server ends, etc.
+These projects may offer more features and a better user experience.  
+For specific deployment methods, please refer to the [Derived Project README](projects/README.md)
+
+
 ### Development Guide
 
 TODO
 
 # TODO
 
-- [ ] Semantic-based reading order
-- [ ] List recognition within the text
-- [ ] Code block recognition within the text
-- [ ] Table of contents recognition
-- [x] Table recognition
-- [ ] [Chemical formula recognition](docs/chemical_knowledge_introduction/introduction.pdf)
-- [ ] Geometric shape recognition
+- 🗹 Reading order based on the model  
+- 🗹 Recognition of `index` and `list` in the main text  
+- 🗹 Table recognition
+- ☐ Code block recognition in the main text
+- ☐ [Chemical formula recognition](docs/chemical_knowledge_introduction/introduction.pdf)
+- ☐ Geometric shape recognition
 
 # Known Issues
 
-- Reading order is segmented based on rules, which can cause disordered sequences in some cases
-- Vertical text is not supported
-- Lists, code blocks, and table of contents are not yet supported in the layout model
-- Comic books, art books, elementary school textbooks, and exercise books are not well-parsed yet
-- Enabling OCR may produce better results in PDFs with a high density of formulas
-- If you are processing PDFs with a large number of formulas, it is strongly recommended to enable the OCR function. When using PyMuPDF to extract text, overlapping text lines can occur, leading to inaccurate formula insertion positions.
-
+- Reading order is determined by the model based on the spatial distribution of readable content, and may be out of order in some areas under extremely complex layouts.
+- Vertical text is not supported.
+- Tables of contents and lists are recognized through rules, and some uncommon list formats may not be recognized.
+- Only one level of headings is supported; hierarchical headings are not currently supported.
+- Code blocks are not yet supported in the layout model.
+- Comic books, art albums, primary school textbooks, and exercises cannot be parsed well.
+- Table recognition may result in row/column recognition errors in complex tables.
+- OCR recognition may produce inaccurate characters in PDFs of lesser-known languages (e.g., diacritical marks in Latin script, easily confused characters in Arabic script).
+- Some formulas may not render correctly in Markdown.
 
 # FAQ
 
@@ -367,6 +420,7 @@ This project currently uses PyMuPDF to achieve advanced functionality. However,
 - [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy)
 - [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
 - [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
+- [layoutreader](https://github.com/ppaanngggg/layoutreader)
 - [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
 - [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
 

README_ja-JP.md

@@ -290,14 +290,23 @@ https://github.com/opendatalab/MinerU/assets/11393164/20438a02-ce6c-4af8-9dde-d7
 # 引用
 
 ```bibtex
-@misc{2024mineru,
-    title={MinerU: A One-stop, Open-source, High-quality Data Extraction Tool},
-    author={MinerU Contributors},
-    howpublished = {\url{https://github.com/opendatalab/MinerU}},
-    year={2024}
+@misc{wang2024mineruopensourcesolutionprecise,
+      title={MinerU: An Open-Source Solution for Precise Document Content Extraction}, 
+      author={Bin Wang and Chao Xu and Xiaomeng Zhao and Linke Ouyang and Fan Wu and Zhiyuan Zhao and Rui Xu and Kaiwen Liu and Yuan Qu and Fukai Shang and Bo Zhang and Liqun Wei and Zhihao Sui and Wei Li and Botian Shi and Yu Qiao and Dahua Lin and Conghui He},
+      year={2024},
+      eprint={2409.18839},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2409.18839}, 
 }
-```
 
+@article{he2024opendatalab,
+  title={Opendatalab: Empowering general artificial intelligence with open datasets},
+  author={He, Conghui and Li, Wei and Jin, Zhenjiang and Xu, Chao and Wang, Bin and Lin, Dahua},
+  journal={arXiv preprint arXiv:2407.13773},
+  year={2024}
+}
+```
 
 # スター履歴
 

README_zh-CN.md

@@ -20,6 +20,7 @@
 [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/papayalove/b5f4913389e7ff9883c6b687de156e78/mineru_demo.ipynb)
 [![Paper](https://img.shields.io/badge/Paper-arXiv-green)](https://arxiv.org/abs/2409.18839)
 
+
 <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>
 
 <!-- language -->
@@ -41,6 +42,20 @@
 </div>
 
 # 更新记录
+
+- 2024/10/31 0.9.0发布，这是我们进行了大量代码重构的全新版本，解决了众多问题，提升了性能，降低了硬件需求，并提供了更丰富的易用性：
+  - 重构排序模块代码，使用 [layoutreader](https://github.com/ppaanngggg/layoutreader) 进行阅读顺序排序，确保在各种排版下都能实现极高准确率
+  - 重构段落拼接模块，在跨栏、跨页、跨图、跨表情况下均能实现良好的段落拼接效果
+  - 重构列表和目录识别功能，极大提升列表块和目录块识别的准确率及对应文本段落的解析效果
+  - 重构图、表与描述性文本的匹配逻辑，大幅提升 caption 和 footnote 与图表的匹配准确率，并将描述性文本的丢失率降至接近0
+  - 增加 OCR 的多语言支持，支持 84 种语言的检测与识别，语言支持列表详见 [OCR 语言支持列表](https://paddlepaddle.github.io/PaddleOCR/latest/ppocr/blog/multi_languages.html#5)
+  - 增加显存回收逻辑及其他显存优化措施，大幅降低显存使用需求。开启除表格加速外的全部加速功能(layout/公式/OCR)的显存需求从16GB降至8GB，开启全部加速功能的显存需求从24GB降至10GB
+  - 优化配置文件的功能开关，增加独立的公式检测开关，无需公式检测时可大幅提升速度和解析效果
+  - 集成 [PDF-Extract-Kit 1.0](https://github.com/opendatalab/PDF-Extract-Kit)
+    - 加入自研的 `doclayout_yolo` 模型，在相近解析效果情况下比原方案提速10倍以上，可通过配置文件与 `layoutlmv3` 自由切换
+    - 公式解析升级至 `unimernet 0.2.1`，在提升公式解析准确率的同时，大幅降低显存需求
+    - 因 `PDF-Extract-Kit 1.0` 更换仓库，需要重新下载模型，步骤详见 [如何下载模型](docs/how_to_download_models_zh_cn.md)
+- 2024/09/27 0.8.1发布，修复了一些bug，同时提供了[在线demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/)的[本地化部署版本](projects/web_demo/README_zh-CN.md)和[前端界面](projects/web/README_zh-CN.md)
 - 2024/09/09 0.8.0发布，支持Dockerfile快速部署，同时上线了huggingface、modelscope demo
 - 2024/08/30 0.7.1发布，集成了paddle tablemaster表格识别功能
 - 2024/08/09 0.7.0b1发布，简化安装步骤提升易用性，加入表格识别功能
@@ -68,6 +83,7 @@
             <ul>
             <li><a href="#命令行">命令行</a></li>
             <li><a href="#api">API</a></li>
+            <li><a href="#部署衍生项目">部署衍生项目</a></li>
             <li><a href="#二次开发">二次开发</a></li>
             </ul>
         </li>
@@ -99,15 +115,18 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
 
 ## 主要功能
 
-- 删除页眉、页脚、脚注、页码等元素，保持语义连贯
-- 对多栏输出符合人类阅读顺序的文本
+- 删除页眉、页脚、脚注、页码等元素，确保语义连贯
+- 输出符合人类阅读顺序的文本，适用于单栏、多栏及复杂排版
 - 保留原文档的结构，包括标题、段落、列表等
-- 提取图像、图片标题、表格、表格标题
-- 自动识别文档中的公式并将公式转换成latex
-- 自动识别文档中的表格并将表格转换成latex
-- 乱码PDF自动检测并启用OCR
+- 提取图像、图片描述、表格、表格标题及脚注
+- 自动识别并转换文档中的公式为LaTeX格式
+- 自动识别并转换文档中的表格为LaTeX或HTML格式
+- 自动检测扫描版PDF和乱码PDF，并启用OCR功能
+- OCR支持84种语言的检测与识别
+- 支持多种输出格式，如多模态与NLP的Markdown、按阅读顺序排序的JSON、含有丰富信息的中间格式等
+- 支持多种可视化结果，包括layout可视化、span可视化等，便于高效确认输出效果与质检
 - 支持CPU和GPU环境
-- 支持windows/linux/mac平台
+- 兼容Windows、Linux和Mac平台
 
 ## 快速开始
 
@@ -138,8 +157,8 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
     </tr>
     <tr>
         <td colspan="3">CPU</td>
-        <td>x86_64</td>
-        <td>x86_64</td>
+        <td>x86_64(暂不支持ARM Linux)</td>
+        <td>x86_64(暂不支持ARM Windows)</td>
         <td>x86_64 / arm64</td>
     </tr>
     <tr>
@@ -148,7 +167,7 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
     </tr>
     <tr>
         <td colspan="3">python版本</td>
-        <td colspan="3">3.10</td>
+        <td colspan="3">3.10 (请务必通过conda创建3.10虚拟环境)</td>
     </tr>
     <tr>
         <td colspan="3">Nvidia Driver 版本</td>
@@ -165,24 +184,27 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
     <tr>
         <td rowspan="2">GPU硬件支持列表</td>
         <td colspan="2">最低要求 8G+显存</td>
-        <td colspan="2">3060ti/3070/3080/3080ti/4060/4070/4070ti<br>
-        8G显存仅可开启lavout和公式识别加速</td>
+        <td colspan="2">3060ti/3070/4060<br>
+        8G显存可开启layout、公式识别和ocr加速</td>
         <td rowspan="2">None</td>
     </tr>
     <tr>
-        <td colspan="2">推荐配置 16G+显存</td>
-        <td colspan="2">3090/3090ti/4070tisuper/4080/4090<br>
-        16G及以上可以同时开启layout，公式识别和ocr加速<br>
-        24G及以上可以同时开启layout，公式识别，ocr加速和表格识别
+        <td colspan="2">推荐配置 10G+显存</td>
+        <td colspan="2">3080/3080ti/3090/3090ti/4070/4070ti/4070tisuper/4080/4090<br>
+        10G显存及以上可以同时开启layout、公式识别和ocr加速和表格识别加速<br>
         </td>
     </tr>
 </table>
 
 ### 在线体验
+稳定版(经过QA验证的稳定版本)：
 
 [![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
-[![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)
+
+测试版(同步dev分支更新，测试新特性)：
+
 [![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAF8AAABYCAMAAACkl9t/AAAAk1BMVEVHcEz/nQv/nQv/nQr/nQv/nQr/nQv/nQv/nQr/wRf/txT/pg7/yRr/rBD/zRz/ngv/oAz/zhz/nwv/txT/ngv/0B3+zBz/nQv/0h7/wxn/vRb/thXkuiT/rxH/pxD/ogzcqyf/nQvTlSz/czCxky7/SjifdjT/Mj3+Mj3wMj15aTnDNz+DSD9RTUBsP0FRO0Q6O0WyIxEIAAAAGHRSTlMADB8zSWF3krDDw8TJ1NbX5efv8ff9/fxKDJ9uAAAGKklEQVR42u2Z63qjOAyGC4RwCOfB2JAGqrSb2WnTw/1f3UaWcSGYNKTdf/P+mOkTrE+yJBulvfvLT2A5ruenaVHyIks33npl/6C4s/ZLAM45SOi/1FtZPyFur1OYofBX3w7d54Bxm+E8db+nDr12ttmESZ4zludJEG5S7TO72YPlKZFyE+YCYUJTBZsMiNS5Sd7NlDmKM2Eg2JQg8awbglfqgbhArjxkS7dgp2RH6hc9AMLdZYUtZN5DJr4molC8BfKrEkPKEnEVjLbgW1fLy77ZVOJagoIcLIl+IxaQZGjiX597HopF5CkaXVMDO9Pyix3AFV3kw4lQLCbHuMovz8FallbcQIJ5Ta0vks9RnolbCK84BtjKRS5uA43hYoZcOBGIG2Epbv6CvFVQ8m8loh66WNySsnN7htL58LNp+NXT8/PhXiBXPMjLSxtwp8W9f/1AngRierBkA+kk/IpUSOeKByzn8y3kAAAfh//0oXgV4roHm/kz4E2z//zRc3/lgwBzbM2mJxQEa5pqgX7d1L0htrhx7LKxOZlKbwcAWyEOWqYSI8YPtgDQVjpB5nvaHaSnBaQSD6hweDi8PosxD6/PT09YY3xQA7LTCTKfYX+QHpA0GCcqmEHvr/cyfKQTEuwgbs2kPxJEB0iNjfJcCTPyocx+A0griHSmADiC91oNGVwJ69RudYe65vJmoqfpul0lrqXadW0jFKH5BKwAeCq+Den7s+3zfRJzA61/Uj/9H/VzLKTx9jFPPdXeeP+L7WEvDLAKAIoF8bPTKT0+TM7W8ePj3Rz/Yn3kOAp2f1Kf0Weony7pn/cPydvhQYV+eFOfmOu7VB/ViPe34/EN3RFHY/yRuT8ddCtMPH/McBAT5s+vRde/gf2c/sPsjLK+m5IBQF5tO+h2tTlBGnP6693JdsvofjOPnnEHkh2TnV/X1fBl9S5zrwuwF8NFrAVJVwCAPTe8gaJlomqlp0pv4Pjn98tJ/t/fL++6unpR1YGC2n/KCoa0tTLoKiEeUPDl94nj+5/Tv3/eT5vBQ60X1S0oZr+IWRR8Ldhu7AlLjPISlJcO9vrFotky9SpzDequlwEir5beYAc0R7D9KS1DXva0jhYRDXoExPdc6yw5GShkZXe9QdO/uOvHofxjrV/TNS6iMJS+4TcSTgk9n5agJdBQbB//IfF/HpvPt3Tbi7b6I6K0R72p6ajryEJrENW2bbeVUGjfgoals4L443c7BEE4mJO2SpbRngxQrAKRudRzGQ8jVOL2qDVjjI8K1gc3TIJ5KiFZ1q+gdsARPB4NQS4AjwVSt72DSoXNyOWUrU5mQ9nRYyjp89Xo7oRI6Bga9QNT1mQ/ptaJq5T/7WcgAZywR/XlPGAUDdet3LE+qS0TI+g+aJU8MIqjo0Kx8Ly+maxLjJmjQ18rA0YCkxLQbUZP1WqdmyQGJLUm7VnQFqodmXSqmRrdVpqdzk5LvmvgtEcW8PMGdaS23EOWyDVbACZzUJPaqMbjDxpA3Qrgl0AikimGDbqmyT8P8NOYiqrldF8rX+YN7TopX4UoHuSCYY7cgX4gHwclQKl1zhx0THf+tCAUValzjI7Wg9EhptrkIcfIJjA94evOn8B2eHaVzvBrnl2ig0So6hvPaz0IGcOvTHvUIlE2+prqAxLSQxZlU2stql1NqCCLdIiIN/i1DBEHUoElM9dBravbiAnKqgpi4IBkw+utSPIoBijDXJipSVV7MpOEJUAc5Qmm3BnUN+w3hteEieYKfRZSIUcXKMVf0u5wD4EwsUNVvZOtUT7A2GkffHjByWpHqvRBYrTV72a6j8zZ6W0DTE86Hn04bmyWX3Ri9WH7ZU6Q7h+ZHo0nHUAcsQvVhXRDZHChwiyi/hnPuOsSEF6Exk3o6Y9DT1eZ+6cASXk2Y9k+6EOQMDGm6WBK10wOQJCBwren86cPPWUcRAnTVjGcU1LBgs9FURiX/e6479yZcLwCBmTxiawEwrOcleuu12t3tbLv/N4RLYIBhYexm7Fcn4OJcn0+zc+s8/VfPeddZHAGN6TT8eGczHdR/Gts1/MzDkThr23zqrVfAMFT33Nx1RJsx1k5zuWILLnG/vsH+Fv5D4NTVcp1Gzo8AAAAAElFTkSuQmCC&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)
 
 ### 使用CPU快速体验
 
@@ -193,7 +215,7 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
 ```bash
 conda create -n MinerU python=3.10
 conda activate MinerU
-pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com -i https://pypi.tuna.tsinghua.edu.cn/simple
+pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com -i https://mirrors.aliyun.com/pypi/simple
 ```
 
 #### 2. 下载模型权重文件
@@ -212,10 +234,18 @@ pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com -i h
 
 ```json
 {
-  // other config
-  "table-config": {
-        "model": "TableMaster", // 使用structEqTable请修改为'struct_eqtable'
-        "is_table_recog_enable": false, // 表格识别功能默认是关闭的，如果需要修改此处的值
+    // other config
+    "layout-config": {
+        "model": "layoutlmv3" // 使用doclayout_yolo请修改为“doclayout_yolo"
+    },
+    "formula-config": {
+        "mfd_model": "yolo_v8_mfd",
+        "mfr_model": "unimernet_small",
+        "enable": true  // 公式识别功能默认是开启的，如果需要关闭请修改此处的值为"false"
+    },
+    "table-config": {
+        "model": "tablemaster",  // 使用structEqTable请修改为"struct_eqtable"
+        "enable": false, // 表格识别功能默认是关闭的，如果需要开启请修改此处的值为"true"
         "max_time": 400
     }
 }
@@ -254,13 +284,26 @@ Usage: magic-pdf [OPTIONS]
 Options:
   -v, --version                display the version and exit
   -p, --path PATH              local pdf filepath or directory  [required]
-  -o, --output-dir TEXT        output local directory
-  -m, --method [ocr|txt|auto]  the method for parsing pdf.
-                               ocr: using ocr technique to extract information from pdf,
-                               txt: suitable for the text-based pdf only and outperform ocr,
-                               auto: automatically choose the best method for parsing pdf
-                                  from ocr and txt.
-                               without method specified, auto will be used by default.
+  -o, --output-dir PATH        output local directory  [required]
+  -m, --method [ocr|txt|auto]  the method for parsing pdf. ocr: using ocr
+                               technique to extract information from pdf. txt:
+                               suitable for the text-based pdf only and
+                               outperform ocr. auto: automatically choose the
+                               best method for parsing pdf from ocr and txt.
+                               without method specified, auto will be used by
+                               default.
+  -l, --lang TEXT              Input the languages in the pdf (if known) to
+                               improve OCR accuracy.  Optional. You should
+                               input "Abbreviation" with language form url: ht
+                               tps://paddlepaddle.github.io/PaddleOCR/latest/en
+                               /ppocr/blog/multi_languages.html#5-support-languages-
+                               and-abbreviations
+  -d, --debug BOOLEAN          Enables detailed debugging information during
+                               the execution of the CLI commands.
+  -s, --start INTEGER          The starting page for PDF parsing, beginning
+                               from 0.
+  -e, --end INTEGER            The ending page for PDF parsing, beginning from
+                               0.
   --help                       Show this message and exit.
 
 
@@ -277,11 +320,12 @@ magic-pdf -p {some_pdf} -o {some_output_dir} -m auto
 ```text
 ├── some_pdf.md                          # markdown 文件
 ├── images                               # 存放图片目录
-├── some_pdf_layout.pdf                  # layout 绘图
+├── some_pdf_layout.pdf                  # layout 绘图 （包含layout阅读顺序）
 ├── some_pdf_middle.json                 # minerU 中间处理结果
 ├── some_pdf_model.json                  # 模型推理结果
 ├── some_pdf_origin.pdf                  # 原 pdf 文件
-└── some_pdf_spans.pdf                   # 最小粒度的bbox位置信息绘图
+├── some_pdf_spans.pdf                   # 最小粒度的bbox位置信息绘图
+└── some_pdf_content_list.json           # 按阅读顺序排列的富文本json
 ```
 
 更多有关输出文件的信息，请参考[输出文件说明](docs/output_file_zh_cn.md)
@@ -321,29 +365,38 @@ md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
 - [demo.py 最简单的处理方式](demo/demo.py)
 - [magic_pdf_parse_main.py 能够更清晰看到处理流程](demo/magic_pdf_parse_main.py)
 
+### 部署衍生项目
+
+衍生项目包含项目开发者和社群开发者们基于MinerU的二次开发项目，
+例如基于Gradio的应用界面、基于llama的RAG、官网同款web demo、轻量级的多卡负载均衡c/s端等，
+这些项目可能会提供更多的功能和更好的用户体验。
+具体部署方式请参考 [衍生项目readme](projects/README_zh-CN.md)
+
+
 ### 二次开发
 
 TODO
 
 # TODO
 
-- [ ] 基于语义的阅读顺序
-- [ ] 正文中列表识别
-- [ ] 正文中代码块识别
-- [ ] 目录识别
-- [x] 表格识别
-- [ ] [化学式识别](docs/chemical_knowledge_introduction/introduction.pdf)
-- [ ] 几何图形识别
+- 🗹 基于模型的阅读顺序  
+- 🗹 正文中目录、列表识别  
+- 🗹 表格识别
+- ☐  正文中代码块识别
+- ☐  [化学式识别](docs/chemical_knowledge_introduction/introduction.pdf)
+- ☐  几何图形识别
 
 # Known Issues
 
-- 阅读顺序基于规则的分割，在一些情况下会乱序
+- 阅读顺序基于模型对可阅读内容在空间中的分布进行排序，在极端复杂的排版下可能会部分区域乱序
 - 不支持竖排文字
-- 列表、代码块、目录在layout模型里还没有支持
+- 目录和列表通过规则进行识别，少部分不常见的列表形式可能无法识别
+- 标题只有一级，目前不支持标题分级
+- 代码块在layout模型里还没有支持
 - 漫画书、艺术图册、小学教材、习题尚不能很好解析
-- 在一些公式密集的PDF上强制启用OCR效果会更好
-- 如果您要处理包含大量公式的pdf,强烈建议开启OCR功能。使用pymuPDF提取文字的时候会出现文本行互相重叠的情况导致公式插入位置不准确。
-
+- 表格识别在复杂表格上可能会出现行/列识别错误
+- 在小语种PDF上，OCR识别可能会出现字符不准确的情况（如拉丁文的重音符号、阿拉伯文易混淆字符等）
+- 部分公式可能会无法在markdown中渲染
 
 # FAQ
 
@@ -370,6 +423,7 @@ TODO
 - [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy)
 - [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
 - [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
+- [layoutreader](https://github.com/ppaanngggg/layoutreader)
 - [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
 - [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
 

demo/demo.py

 import os
-import json
 
 from loguru import logger
-
 from magic_pdf.pipe.UNIPipe import UNIPipe
 from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter
 
-import magic_pdf.model as model_config 
-model_config.__use_inside_model__ = True
 
 try:
     current_script_dir = os.path.dirname(os.path.abspath(__file__))
     demo_name = "demo1"
     pdf_path = os.path.join(current_script_dir, f"{demo_name}.pdf")
-    model_path = os.path.join(current_script_dir, f"{demo_name}.json")
     pdf_bytes = open(pdf_path, "rb").read()
-    # model_json = json.loads(open(model_path, "r", encoding="utf-8").read())
-    model_json = []  # model_json传空list使用内置模型解析
-    jso_useful_key = {"_pdf_type": "", "model_list": model_json}
+    jso_useful_key = {"_pdf_type": "", "model_list": []}
     local_image_dir = os.path.join(current_script_dir, 'images')
     image_dir = str(os.path.basename(local_image_dir))
     image_writer = DiskReaderWriter(local_image_dir)
     pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
     pipe.pipe_classify()
-    """如果没有传入有效的模型数据，则使用内置model解析"""
-    if len(model_json) == 0:
-        if model_config.__use_inside_model__:
-            pipe.pipe_analyze()
-        else:
-            logger.error("need model list input")
-            exit(1)
+    pipe.pipe_analyze()
     pipe.pipe_parse()
     md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
     with open(f"{demo_name}.md", "w", encoding="utf-8") as f:

demo/magic_pdf_parse_main.py

@@ -4,13 +4,12 @@ import copy
 
 from loguru import logger
 
+from magic_pdf.libs.draw_bbox import draw_layout_bbox, draw_span_bbox
 from magic_pdf.pipe.UNIPipe import UNIPipe
 from magic_pdf.pipe.OCRPipe import OCRPipe
 from magic_pdf.pipe.TXTPipe import TXTPipe
 from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter
-import magic_pdf.model as model_config
 
-model_config.__use_inside_model__ = True
 
 # todo: 设备类型选择 （？）
 
@@ -47,11 +46,20 @@ def json_md_dump(
     )
 
 
+# 可视化
+def draw_visualization_bbox(pdf_info, pdf_bytes, local_md_dir, pdf_file_name):
+    # 画布局框，附带排序结果
+    draw_layout_bbox(pdf_info, pdf_bytes, local_md_dir, pdf_file_name)
+    # 画 span 框
+    draw_span_bbox(pdf_info, pdf_bytes, local_md_dir, pdf_file_name)
+
+
 def pdf_parse_main(
         pdf_path: str,
         parse_method: str = 'auto',
         model_json_path: str = None,
         is_json_md_dump: bool = True,
+        is_draw_visualization_bbox: bool = True,
         output_dir: str = None
 ):
     """
@@ -108,11 +116,7 @@ def pdf_parse_main(
 
         # 如果没有传入模型数据，则使用内置模型解析
         if not model_json:
-            if model_config.__use_inside_model__:
-                pipe.pipe_analyze()  # 解析
-            else:
-                logger.error("need model list input")
-                exit(1)
+            pipe.pipe_analyze()  # 解析
 
         # 执行解析
         pipe.pipe_parse()
@@ -121,10 +125,11 @@ def pdf_parse_main(
         content_list = pipe.pipe_mk_uni_format(image_path_parent, drop_mode="none")
         md_content = pipe.pipe_mk_markdown(image_path_parent, drop_mode="none")
 
-
         if is_json_md_dump:
             json_md_dump(pipe, md_writer, pdf_name, content_list, md_content)
 
+        if is_draw_visualization_bbox:
+            draw_visualization_bbox(pipe.pdf_mid_data['pdf_info'], pdf_bytes, output_path, pdf_name)
 
     except Exception as e:
         logger.exception(e)
@@ -132,5 +137,5 @@ def pdf_parse_main(
 
 # 测试
 if __name__ == '__main__':
-    pdf_path = r"C:\Users\XYTK2\Desktop\2024-2016-gb-cd-300.pdf"
+    pdf_path = r"D:\project\20240617magicpdf\Magic-PDF\demo\demo1.pdf"
     pdf_parse_main(pdf_path)

docs/FAQ_en_us.md

@@ -11,7 +11,7 @@ pip install magic-pdf[full]
 
 ### 2. Encountering the error `pickle.UnpicklingError: invalid load key, 'v'.` during use
 
-This might be due to an incomplete download of the model file. You can try re-downloading the model file and then try again.  
+This might be due to an incomplete download of the model file. You can try re-downloading the model file and then try again.
 Reference: https://github.com/opendatalab/MinerU/issues/143
 
 ### 3. Where should the model files be downloaded and how should the `/models-dir` configuration be set?
@@ -24,7 +24,7 @@ The path for the model files is configured in "magic-pdf.json". just like:
 }
 ```
 
-This path is an absolute path, not a relative path. You can obtain the absolute path in the models directory using the "pwd" command.  
+This path is an absolute path, not a relative path. You can obtain the absolute path in the models directory using the "pwd" command.
 Reference: https://github.com/opendatalab/MinerU/issues/155#issuecomment-2230216874
 
 ### 4. Encountered the error `ImportError: libGL.so.1: cannot open shared object file: No such file or directory` in Ubuntu 22.04 on WSL2
@@ -38,17 +38,22 @@ sudo apt-get install libgl1-mesa-glx
 Reference: https://github.com/opendatalab/MinerU/issues/388
 
 ### 5. Encountered error `ModuleNotFoundError: No module named 'fairscale'`
+
 You need to uninstall the module and reinstall it:
+
 ```bash
 pip uninstall fairscale
 pip install fairscale
 ```
+
 Reference: https://github.com/opendatalab/MinerU/issues/411
 
 ### 6. On some newer devices like the H100, the text parsed during OCR using CUDA acceleration is garbled.
 
 The compatibility of cuda11 with new graphics cards is poor, and the CUDA version used by Paddle needs to be upgraded.
+
 ```bash
 pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu123/
 ```
+
 Reference: https://github.com/opendatalab/MinerU/issues/558

docs/FAQ_zh_cn.md

 # 常见问题解答
 
-### 1.在较新版本的mac上使用命令安装pip install magic-pdf[full] zsh: no matches found: magic-pdf[full]
+### 1.在较新版本的mac上使用命令安装pip install magic-pdf\[full\] zsh: no matches found: magic-pdf\[full\]
 
 在 macOS 上，默认的 shell 从 Bash 切换到了 Z shell，而 Z shell 对于某些类型的字符串匹配有特殊的处理逻辑，这可能导致no matches found错误。
 可以通过在命令行禁用globbing特性，再尝试运行安装命令
+
 ```bash
 setopt no_nomatch
 pip install magic-pdf[full]
@@ -11,41 +12,50 @@ pip install magic-pdf[full]
 
 ### 2.使用过程中遇到_pickle.UnpicklingError: invalid load key, 'v'.错误
 
-可能是由于模型文件未下载完整导致，可尝试重新下载模型文件后再试  
+可能是由于模型文件未下载完整导致，可尝试重新下载模型文件后再试
 参考：https://github.com/opendatalab/MinerU/issues/143
 
 ### 3.模型文件应该下载到哪里/models-dir的配置应该怎么填
 
 模型文件的路径输入是在"magic-pdf.json"中通过
+
 ```json
 {
   "models-dir": "/tmp/models"
 }
 ```
+
 进行配置的。
-这个路径是绝对路径而不是相对路径，绝对路径的获取可在models目录中通过命令 "pwd" 获取。  
+这个路径是绝对路径而不是相对路径，绝对路径的获取可在models目录中通过命令 "pwd" 获取。
 参考：https://github.com/opendatalab/MinerU/issues/155#issuecomment-2230216874
 
 ### 4.在WSL2的Ubuntu22.04中遇到报错`ImportError: libGL.so.1: cannot open shared object file: No such file or directory`
 
 WSL2的Ubuntu22.04中缺少`libgl`库，可通过以下命令安装`libgl`库解决：
+
 ```bash
 sudo apt-get install libgl1-mesa-glx
 ```
+
 参考：https://github.com/opendatalab/MinerU/issues/388
 
 ### 5.遇到报错 `ModuleNotFoundError : Nomodulenamed 'fairscale'`
+
 需要卸载该模块并重新安装
+
 ```bash
 pip uninstall fairscale
 pip install fairscale
 ```
+
 参考：https://github.com/opendatalab/MinerU/issues/411
 
 ### 6.在部分较新的设备如H100上，使用CUDA加速OCR时解析出的文字乱码。
 
 cuda11对新显卡的兼容性不好，需要升级paddle使用的cuda版本
+
 ```bash
 pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu123/
 ```
+
 参考：https://github.com/opendatalab/MinerU/issues/558

docs/README_Ubuntu_CUDA_Acceleration_en_US.md

-
 # Ubuntu 22.04 LTS
 
 ### 1. Check if NVIDIA Drivers Are Installed
-   ```sh
-   nvidia-smi
-   ```
-   If you see information similar to the following, it means that the NVIDIA drivers are already installed, and you can skip Step 2.
-   ```plaintext
-   +---------------------------------------------------------------------------------------+
-   | NVIDIA-SMI 537.34                 Driver Version: 537.34       CUDA Version: 12.2     |
-   |-----------------------------------------+----------------------+----------------------+
-   | GPU  Name                     TCC/WDDM  | Bus-Id        Disp.A | Volatile Uncorr. ECC |
-   | Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
-   |                                         |                      |               MIG M. |
-   |=========================================+======================+======================|
-   |   0  NVIDIA GeForce RTX 3060 Ti   WDDM  | 00000000:01:00.0  On |                  N/A |
-   |  0%   51C    P8              12W / 200W |   1489MiB /  8192MiB |      5%      Default |
-   |                                         |                      |                  N/A |
-   +-----------------------------------------+----------------------+----------------------+
-   ```
+
+```sh
+nvidia-smi
+```
+
+If you see information similar to the following, it means that the NVIDIA drivers are already installed, and you can skip Step 2.
+
+Notice:`CUDA Version` should be >= 12.1, If the displayed version number is less than 12.1, please upgrade the driver.
+
+```plaintext
++---------------------------------------------------------------------------------------+
+| NVIDIA-SMI 537.34                 Driver Version: 537.34       CUDA Version: 12.2     |
+|-----------------------------------------+----------------------+----------------------+
+| GPU  Name                     TCC/WDDM  | Bus-Id        Disp.A | Volatile Uncorr. ECC |
+| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
+|                                         |                      |               MIG M. |
+|=========================================+======================+======================|
+|   0  NVIDIA GeForce RTX 3060 Ti   WDDM  | 00000000:01:00.0  On |                  N/A |
+|  0%   51C    P8              12W / 200W |   1489MiB /  8192MiB |      5%      Default |
+|                                         |                      |                  N/A |
++-----------------------------------------+----------------------+----------------------+
+```
 
 ### 2. Install the Driver
-   If no driver is installed, use the following command:
-   ```sh
-   sudo apt-get update
-   sudo apt-get install nvidia-driver-545
-   ```
-   Install the proprietary driver and restart your computer after installation.
-   ```sh
-   reboot
-   ```
+
+If no driver is installed, use the following command:
+
+```sh
+sudo apt-get update
+sudo apt-get install nvidia-driver-545
+```
+
+Install the proprietary driver and restart your computer after installation.
+
+```sh
+reboot
+```
 
 ### 3. Install Anaconda
-   If Anaconda is already installed, skip this step.
-   ```sh
-   wget https://repo.anaconda.com/archive/Anaconda3-2024.06-1-Linux-x86_64.sh
-   bash Anaconda3-2024.06-1-Linux-x86_64.sh
-   ```
-   In the final step, enter `yes`, close the terminal, and reopen it.
+
+If Anaconda is already installed, skip this step.
+
+```sh
+wget https://repo.anaconda.com/archive/Anaconda3-2024.06-1-Linux-x86_64.sh
+bash Anaconda3-2024.06-1-Linux-x86_64.sh
+```
+
+In the final step, enter `yes`, close the terminal, and reopen it.
 
 ### 4. Create an Environment Using Conda
-   Specify Python version 3.10.
-   ```sh
-   conda create -n MinerU python=3.10
-   conda activate MinerU
-   ```
+
+Specify Python version 3.10.
+
+```sh
+conda create -n MinerU python=3.10
+conda activate MinerU
+```
 
 ### 5. Install Applications
-   ```sh
-   pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com
-   ```
+
+```sh
+pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com
+```
+
 ❗ After installation, make sure to check the version of `magic-pdf` using the following command:
-   ```sh
-   magic-pdf --version
-   ```
-   If the version number is less than 0.7.0, please report the issue.
+
+```sh
+magic-pdf --version
+```
+
+If the version number is less than 0.7.0, please report the issue.
 
 ### 6. Download Models
-   Refer to detailed instructions on [how to download model files](how_to_download_models_en.md).
+
+
+Refer to detailed instructions on [how to download model files](how_to_download_models_en.md).
+
 
 ## 7. Understand the Location of the Configuration File
 
 After completing the [6. Download Models](#6-download-models) step, the script will automatically generate a `magic-pdf.json` file in the user directory and configure the default model path.
 You can find the `magic-pdf.json` file in your user directory.
+
 > The user directory for Linux is "/home/username".
 
+
 ### 8. First Run
-   Download a sample file from the repository and test it.
-   ```sh
-   wget https://github.com/opendatalab/MinerU/raw/master/demo/small_ocr.pdf
-   magic-pdf -p small_ocr.pdf
-   ```
+
+Download a sample file from the repository and test it.
+
+```sh
+wget https://github.com/opendatalab/MinerU/raw/master/demo/small_ocr.pdf
+magic-pdf -p small_ocr.pdf
+```
 
 ### 9. Test CUDA Acceleration
 
-If your graphics card has at least 8GB of VRAM, follow these steps to test CUDA acceleration:
+If your graphics card has at least **8GB** of VRAM, follow these steps to test CUDA acceleration:
 
 1. Modify the value of `"device-mode"` in the `magic-pdf.json` configuration file located in your home directory.
    ```json
@@ -89,8 +113,6 @@ If your graphics card has at least 8GB of VRAM, follow these steps to test CUDA
 
 ### 10. Enable CUDA Acceleration for OCR
 
-❗ The following operations require a graphics card with at least 16GB of VRAM; otherwise, the program may crash or experience reduced performance.
-    
 1. Download `paddlepaddle-gpu`. Installation will automatically enable OCR acceleration.
    ```sh
    python -m pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/

docs/README_Ubuntu_CUDA_Acceleration_zh_CN.md

 # Ubuntu 22.04 LTS
 
 ## 1. 检测是否已安装nvidia驱动
+
 ```bash
-nvidia-smi 
+nvidia-smi
 ```
+
 如果看到类似如下的信息，说明已经安装了nvidia驱动，可以跳过步骤2
+
+注意:`CUDA Version` 显示的版本号应 >= 12.1，如显示的版本号小于12.1，请升级驱动
+
+```plaintext
 ```
 +---------------------------------------------------------------------------------------+
 | NVIDIA-SMI 537.34                 Driver Version: 537.34       CUDA Version: 12.2     |
@@ -18,78 +24,110 @@ nvidia-smi
 |                                         |                      |                  N/A |
 +-----------------------------------------+----------------------+----------------------+
 ```
+
 ## 2. 安装驱动
+
 如没有驱动，则通过如下命令
+
 ```bash
 sudo apt-get update
 sudo apt-get install nvidia-driver-545
 ```
+
 安装专有驱动，安装完成后，重启电脑
+
 ```bash
 reboot
 ```
+
 ## 3. 安装anacoda
+
 如果已安装conda，可以跳过本步骤
+
 ```bash
 wget -U NoSuchBrowser/1.0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/archive/Anaconda3-2024.06-1-Linux-x86_64.sh
 bash Anaconda3-2024.06-1-Linux-x86_64.sh
 ```
+
 最后一步输入yes，关闭终端重新打开
+
 ## 4. 使用conda 创建环境
+
 需指定python版本为3.10
+
 ```bash
 conda create -n MinerU python=3.10
 conda activate MinerU
 ```
+
 ## 5. 安装应用
+
 ```bash
-pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com -i https://pypi.tuna.tsinghua.edu.cn/simple
+pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com -i https://mirrors.aliyun.com/pypi/simple
 ```
+
 > ❗️下载完成后，务必通过以下命令确认magic-pdf的版本是否正确
-> 
+>
 > ```bash
 > magic-pdf --version
->```
+> ```
+>
 > 如果版本号小于0.7.0，请到issue中向我们反馈
 
 ## 6. 下载模型
+
+
 详细参考 [如何下载模型文件](how_to_download_models_zh_cn.md)
 
 ## 7. 了解配置文件存放的位置
+
 完成[6.下载模型](#6-下载模型)步骤后，脚本会自动生成用户目录下的magic-pdf.json文件，并自动配置默认模型路径。
-您可在【用户目录】下找到magic-pdf.json文件。 
+您可在【用户目录】下找到magic-pdf.json文件。
+
+
 > linux用户目录为 "/home/用户名"
 
 ## 8. 第一次运行
+
 从仓库中下载样本文件，并测试
+
 ```bash
 wget https://gitee.com/myhloli/MinerU/raw/master/demo/small_ocr.pdf
 magic-pdf -p small_ocr.pdf
 ```
+
 ## 9. 测试CUDA加速
-如果您的显卡显存大于等于8G，可以进行以下流程，测试CUDA解析加速效果
+
+如果您的显卡显存大于等于 **8GB** ，可以进行以下流程，测试CUDA解析加速效果
 
 **1.修改【用户目录】中配置文件magic-pdf.json中"device-mode"的值**
+
 ```json
 {
   "device-mode":"cuda"
 }
 ```
+
 **2.运行以下命令测试cuda加速效果**
+
 ```bash
 magic-pdf -p small_ocr.pdf
 ```
+
 > 提示：CUDA加速是否生效可以根据log中输出的各个阶段cost耗时来简单判断，通常情况下，`layout detection cost` 和 `mfr time` 应提速10倍以上。
 
 ## 10. 为ocr开启cuda加速
-> ❗️以下操作需显卡显存大于等于16G才可进行，否则会因为显存不足导致程序崩溃或运行速度下降
 
 **1.下载paddlepaddle-gpu, 安装完成后会自动开启ocr加速**
+
 ```bash
 python -m pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
 ```
+
 **2.运行以下命令测试ocr加速效果**
+
 ```bash
 magic-pdf -p small_ocr.pdf
 ```
+
 > 提示：CUDA加速是否生效可以根据log中输出的各个阶段cost耗时来简单判断，通常情况下，`ocr cost`应提速10倍以上。

docs/README_Windows_CUDA_Acceleration_en_US.md

 # Windows 10/11
 
 ### 1. Install CUDA and cuDNN
+
 Required versions: CUDA 11.8 + cuDNN 8.7.0
-   - CUDA 11.8: https://developer.nvidia.com/cuda-11-8-0-download-archive
-   - cuDNN v8.7.0 (November 28th, 2022), for CUDA 11.x: https://developer.nvidia.com/rdp/cudnn-archive
-   
+
+- CUDA 11.8: https://developer.nvidia.com/cuda-11-8-0-download-archive
+- cuDNN v8.7.0 (November 28th, 2022), for CUDA 11.x: https://developer.nvidia.com/rdp/cudnn-archive
+
 ### 2. Install Anaconda
-   If Anaconda is already installed, you can skip this step.
-   
+
+If Anaconda is already installed, you can skip this step.
+
 Download link: https://repo.anaconda.com/archive/Anaconda3-2024.06-1-Windows-x86_64.exe
 
 ### 3. Create an Environment Using Conda
-   Python version must be 3.10.
-   ```
-   conda create -n MinerU python=3.10
-   conda activate MinerU
-   ```
+
+Python version must be 3.10.
+
+```
+conda create -n MinerU python=3.10
+conda activate MinerU
+```
 
 ### 4. Install Applications
-   ```
-   pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com
-   ```
-   >❗️After installation, verify the version of `magic-pdf`:
-   >  ```bash
-   >  magic-pdf --version
-   >  ```
-   > If the version number is less than 0.7.0, please report it in the issues section.
-   
+
+```
+pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com
+```
+
+> ❗️After installation, verify the version of `magic-pdf`:
+>
+> ```bash
+> magic-pdf --version
+> ```
+>
+> If the version number is less than 0.7.0, please report it in the issues section.
+
 ### 5. Download Models
-   Refer to detailed instructions on [how to download model files](how_to_download_models_en.md).
+
+Refer to detailed instructions on [how to download model files](how_to_download_models_en.md).
 
 ### 6. Understand the Location of the Configuration File
 
 After completing the [5. Download Models](#5-download-models) step, the script will automatically generate a `magic-pdf.json` file in the user directory and configure the default model path.
 You can find the `magic-pdf.json` file in your 【user directory】 .
+
 > The user directory for Windows is "C:/Users/username".
 
 ### 7. First Run
-   Download a sample file from the repository and test it.
-   ```powershell
-     (New-Object System.Net.WebClient).DownloadFile('https://github.com/opendatalab/MinerU/raw/master/demo/small_ocr.pdf', 'small_ocr.pdf')
-     magic-pdf -p small_ocr.pdf
-   ```
+
+Download a sample file from the repository and test it.
+
+```powershell
+  wget https://github.com/opendatalab/MinerU/raw/master/demo/small_ocr.pdf -O small_ocr.pdf
+  magic-pdf -p small_ocr.pdf
+```
 
 ### 8. Test CUDA Acceleration
-   If your graphics card has at least 8GB of VRAM, follow these steps to test CUDA-accelerated parsing performance.
-   1. **Overwrite the installation of torch and torchvision** supporting CUDA.
-      ```
-      pip install --force-reinstall torch==2.3.1 torchvision==0.18.1 --index-url https://download.pytorch.org/whl/cu118
-      ```
-      >❗️Ensure the following versions are specified in the command:
-      >```
-      > torch==2.3.1 torchvision==0.18.1
-      >```
-      >These are the highest versions we support. Installing higher versions without specifying them will cause the program to fail.
-   2. **Modify the value of `"device-mode"`** in the `magic-pdf.json` configuration file located in your user directory.
-     
-      ```json
-      {
-        "device-mode": "cuda"
-      }
-      ```
-   3. **Run the following command to test CUDA acceleration**:
-
-      ```
-      magic-pdf -p small_ocr.pdf
-      ```
+
+If your graphics card has at least 8GB of VRAM, follow these steps to test CUDA-accelerated parsing performance.
+
+1. **Overwrite the installation of torch and torchvision** supporting CUDA.
+
+   ```
+   pip install --force-reinstall torch==2.3.1 torchvision==0.18.1 --index-url https://download.pytorch.org/whl/cu118
+   ```
+
+   > ❗️Ensure the following versions are specified in the command:
+   >
+   > ```
+   > torch==2.3.1 torchvision==0.18.1
+   > ```
+   >
+   > These are the highest versions we support. Installing higher versions without specifying them will cause the program to fail.
+
+2. **Modify the value of `"device-mode"`** in the `magic-pdf.json` configuration file located in your user directory.
+
+   ```json
+   {
+     "device-mode": "cuda"
+   }
+   ```
+
+
+3. **Run the following command to test CUDA acceleration**:
+
+   ```
+   magic-pdf -p small_ocr.pdf
+   ```
 
 ### 9. Enable CUDA Acceleration for OCR
-   >❗️This operation requires at least 16GB of VRAM on your graphics card, otherwise it will cause the program to crash or slow down.
-   1. **Download paddlepaddle-gpu**, which will automatically enable OCR acceleration upon installation.
-      ```
-      pip install paddlepaddle-gpu==2.6.1
-      ```
-   2. **Run the following command to test OCR acceleration**:
-      ```
-      magic-pdf -p small_ocr.pdf
-      ```
+
+1. **Download paddlepaddle-gpu**, which will automatically enable OCR acceleration upon installation.
+   ```
+   pip install paddlepaddle-gpu==2.6.1
+   ```
+2. **Run the following command to test OCR acceleration**:
+   ```
+   magic-pdf -p small_ocr.pdf
+   ```