@UaRuairc has signed the CLA in opendatalab/MinerU#4654

Dev

.github/workflows/cli.yml

@@ -1,16 +1,15 @@
 # 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
+name: mineru-cli-test
 on:
-  pull_request:
+  push:
     branches:
       - "master"
       - "dev"
     paths-ignore:
       - "cmds/**"
       - "**.md"
-  workflow_dispatch:
 jobs:
   cli-test:
     if: github.repository == 'opendatalab/MinerU'
@@ -20,31 +19,30 @@ jobs:
       fail-fast: true
 
     steps:
-    - name: PDF cli
-      uses: actions/checkout@v4
-      with:
-        ref: dev
-        fetch-depth: 2
+      - name: PDF cli
+        uses: actions/checkout@v4
+        with:
+          ref: dev
+          fetch-depth: 2
 
-    - name: install uv
-      uses: astral-sh/setup-uv@v5
-
-    - name: install&test
-      run: |
-        uv --version
-        uv venv --python 3.12
-        source .venv/bin/activate
-        uv pip install .[test]
-        cd $GITHUB_WORKSPACE && python tests/clean_coverage.py      
-        cd $GITHUB_WORKSPACE && coverage run
-        cd $GITHUB_WORKSPACE && python tests/get_coverage.py
+      - name: install uv
+        uses: astral-sh/setup-uv@v5
 
+      - name: install&test
+        run: |
+          uv --version
+          uv venv --python 3.12
+          source .venv/bin/activate
+          uv pip install .[test]
+          cd $GITHUB_WORKSPACE && python tests/clean_coverage.py      
+          cd $GITHUB_WORKSPACE && coverage run
+          cd $GITHUB_WORKSPACE && python tests/get_coverage.py
 
   notify_to_feishu:
     if: ${{ always() && !cancelled() && contains(needs.*.result, 'failure')}}
     needs: cli-test
     runs-on: ubuntu-latest
     steps:
-    - name: notify
-      run: |
-        curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"'${{ 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}'"}]]}}}}'  ${{ secrets.FEISHU_WEBHOOK_URL }}
+      - name: notify
+        run: |
+          curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"'${{ 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}'"}]]}}}}'  ${{ secrets.FEISHU_WEBHOOK_URL }}

.github/workflows/huigui.yml

@@ -1,48 +0,0 @@
-# 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"
-jobs:
-  cli-test:
-    if: github.repository == 'opendatalab/MinerU'
-    runs-on: ubuntu-latest
-    timeout-minutes: 240
-    strategy:
-      fail-fast: true
-
-    steps:
-    - name: PDF cli
-      uses: actions/checkout@v4
-      with:
-        ref: dev
-        fetch-depth: 2
-
-    - name: install uv
-      uses: astral-sh/setup-uv@v5
-
-    - name: install&test
-      run: |
-        uv --version
-        uv venv --python 3.12
-        source .venv/bin/activate
-        uv pip install .[test]
-        cd $GITHUB_WORKSPACE && python tests/clean_coverage.py      
-        cd $GITHUB_WORKSPACE && coverage run
-        cd $GITHUB_WORKSPACE && python tests/get_coverage.py
-
-  notify_to_feishu:
-    if: ${{ always() && !cancelled() && contains(needs.*.result, 'failure')}}
-    needs: cli-test
-    runs-on: ubuntu-latest
-    steps:
-    - name: notify
-      run: |
-        curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"'${{ 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}'"}]]}}}}'  ${{ secrets.FEISHU_WEBHOOK_URL }}

README.md

@@ -59,10 +59,10 @@
     - Greatly enhanced post-processing speed when the `pipeline` backend handles batch processing of documents with fewer pages (<10 pages).
     - Layout analysis speed of the `pipeline` backend has been increased by approximately 20%.
   - **Experience Enhancements:**
-    - Built-in ready-to-use `fastapi service` and `gradio webui`. For detailed usage instructions, please refer to [Documentation](#3-api-calls-or-visual-invocation).
+    - Built-in ready-to-use `fastapi service` and `gradio webui`. For detailed usage instructions, please refer to [Documentation](https://opendatalab.github.io/MinerU/usage/quick_usage/#advanced-usage-via-api-webui-sglang-clientserver).
     - Adapted to `sglang` version `0.4.8`, significantly reducing the GPU memory requirements for the `vlm-sglang` backend. It can now run on graphics cards with as little as `8GB GPU memory` (Turing architecture or newer).
     - Added transparent parameter passing for all commands related to `sglang`, allowing the `sglang-engine` backend to receive all `sglang` parameters consistently with the `sglang-server`.
-    - Supports feature extensions based on configuration files, including `custom formula delimiters`, `enabling heading classification`, and `customizing local model directories`. For detailed usage instructions, please refer to [Documentation](#4-extending-mineru-functionality-through-configuration-files).
+    - Supports feature extensions based on configuration files, including `custom formula delimiters`, `enabling heading classification`, and `customizing local model directories`. For detailed usage instructions, please refer to [Documentation](https://opendatalab.github.io/MinerU/usage/quick_usage/#extending-mineru-functionality-with-configuration-files).
   - **New Features:**
     - Updated the `pipeline` backend with the PP-OCRv5 multilingual text recognition model, supporting text recognition in 37 languages such as French, Spanish, Portuguese, Russian, and Korean, with an average accuracy improvement of over 30%. [Details](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/algorithm/PP-OCRv5/PP-OCRv5_multi_languages.html)
     - Introduced limited support for vertical text layout in the `pipeline` backend.

README_zh-CN.md

@@ -56,12 +56,12 @@
   - 性能优化： 
     - 大幅提升某些特定分辨率（长边2000像素左右）文档的预处理速度
     - 大幅提升`pipeline`后端批量处理大量页数较少（<10）文档时的后处理速度
-    - `pipline`后端的layout分析速度提升约20%
+    - `pipeline`后端的layout分析速度提升约20%
   - 体验优化：
-    - 内置开箱即用的`fastapi服务`和`gradio webui`，详细使用方法请参考[文档](#3-api-调用-或-可视化调用)
+    - 内置开箱即用的`fastapi服务`和`gradio webui`，详细使用方法请参考[文档](https://opendatalab.github.io/MinerU/zh/usage/quick_usage/#apiwebuisglang-clientserver)
     - `sglang`适配`0.4.8`版本，大幅降低`vlm-sglang`后端的显存要求，最低可在`8G显存`(Turing及以后架构)的显卡上运行
     - 对所有命令增加`sglang`的参数透传，使得`sglang-engine`后端可以与`sglang-server`一致，接收`sglang`的所有参数
-    - 支持基于配置文件的功能扩展，包含`自定义公式标识符`、`开启标题分级功能`、`自定义本地模型目录`，详细使用方法请参考[文档](#4-基于配置文件扩展-mineru-功能)
+    - 支持基于配置文件的功能扩展，包含`自定义公式标识符`、`开启标题分级功能`、`自定义本地模型目录`，详细使用方法请参考[文档](https://opendatalab.github.io/MinerU/zh/usage/quick_usage/#mineru_1)
   - 新特性：  
     - `pipeline`后端更新 PP-OCRv5 多语种文本识别模型，支持法语、西班牙语、葡萄牙语、俄语、韩语等 37 种语言的文字识别，平均精度涨幅超30%。[详情](https://paddlepaddle.github.io/PaddleOCR/latest/version3.x/algorithm/PP-OCRv5/PP-OCRv5_multi_languages.html)
     - `pipeline`后端增加对竖排文本的有限支持

docker/china/Dockerfile

@@ -3,14 +3,18 @@ FROM lmsysorg/sglang:v0.4.8.post1-cu126
 
 # Install libgl for opencv support & Noto fonts for Chinese characters
 RUN apt-get update && \
-    apt-get install -y fonts-noto-core fonts-noto-cjk && \
-    apt-get install -y libgl1 && \
-    apt-get clean && \
+    apt-get install -y \
+        fonts-noto-core \
+        fonts-noto-cjk \
+        fontconfig \
+        libgl1 && \
     fc-cache -fv && \
+    apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
 # Install mineru latest
-RUN python3 -m pip install -U 'mineru[core]' -i https://mirrors.aliyun.com/pypi/simple --break-system-packages
+RUN python3 -m pip install -U 'mineru[core]' -i https://mirrors.aliyun.com/pypi/simple --break-system-packages && \
+    python3 -m pip cache purge
 
 # Download models and update the configuration file
 RUN /bin/bash -c "mineru-models-download -s modelscope -m all"

docker/global/Dockerfile

@@ -1,16 +1,20 @@
 # Use the official sglang image
 FROM lmsysorg/sglang:v0.4.8.post1-cu126
 
-# Install libgl for opencv support
+# Install libgl for opencv support & Noto fonts for Chinese characters
 RUN apt-get update && \
-    apt-get install -y fonts-noto-core fonts-noto-cjk && \
-    apt-get install -y libgl1 && \
-    apt-get clean && \
+    apt-get install -y \
+        fonts-noto-core \
+        fonts-noto-cjk \
+        fontconfig \
+        libgl1 && \
     fc-cache -fv && \
+    apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
 # Install mineru latest
-RUN python3 -m pip install -U 'mineru[core]' --break-system-packages
+RUN python3 -m pip install -U 'mineru[core]' --break-system-packages && \
+    python3 -m pip cache purge
 
 # Download models and update the configuration file
 RUN /bin/bash -c "mineru-models-download -s huggingface -m all"

docs/en/quick_start/docker_deployment.md

@@ -26,7 +26,7 @@ MinerU's Docker uses `lmsysorg/sglang` as the base image, so it includes the `sg
 >
 > If your device doesn't meet the above requirements, you can still use other features of MinerU, but cannot use `sglang` to accelerate VLM model inference, meaning you cannot use the `vlm-sglang-engine` backend or start the `vlm-sglang-server` service.
 
-## Start Docker Container:
+## Start Docker Container
 
 ```bash
 docker run --gpus all \
@@ -60,7 +60,7 @@ wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml
 ### Start sglang-server service
 connect to `sglang-server` via `vlm-sglang-client` backend
   ```bash
-  docker compose -f compose.yaml --profile mineru-sglang-server up -d
+  docker compose -f compose.yaml --profile sglang-server up -d
   ```
   >[!TIP]
   >In another terminal, connect to sglang server via sglang client (only requires CPU and network, no sglang environment needed)
@@ -72,7 +72,7 @@ connect to `sglang-server` via `vlm-sglang-client` backend
 
 ### Start Web API service
   ```bash
-  docker compose -f compose.yaml --profile mineru-api up -d
+  docker compose -f compose.yaml --profile api up -d
   ```
   >[!TIP]
   >Access `http://<server_ip>:8000/docs` in your browser to view the API documentation.
@@ -81,7 +81,7 @@ connect to `sglang-server` via `vlm-sglang-client` backend
 
 ### Start Gradio WebUI service
   ```bash
-  docker compose -f compose.yaml --profile mineru-gradio up -d
+  docker compose -f compose.yaml --profile gradio up -d
   ```
   >[!TIP]
   >

docs/zh/quick_start/docker_deployment.md

@@ -25,7 +25,7 @@ Mineru的docker使用了`lmsysorg/sglang`作为基础镜像，因此在docker中
 >
 > 如果您的设备不满足上述条件，您仍然可以使用MinerU的其他功能，但无法使用`sglang`加速VLM模型推理，即无法使用`vlm-sglang-engine`后端和启动`vlm-sglang-server`服务。
 
-## 启动 Docker 容器：
+## 启动 Docker 容器
 
 ```bash
 docker run --gpus all \
@@ -58,7 +58,7 @@ wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml
 ### 启动 sglang-server 服务
 并通过`vlm-sglang-client`后端连接`sglang-server`
   ```bash
-  docker compose -f compose.yaml --profile mineru-sglang-server up -d
+  docker compose -f compose.yaml --profile sglang-server up -d
   ```
   >[!TIP]
   >在另一个终端中通过sglang client连接sglang server（只需cpu与网络，不需要sglang环境）
@@ -70,7 +70,7 @@ wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml
 
 ### 启动 Web API 服务
   ```bash
-  docker compose -f compose.yaml --profile mineru-api up -d
+  docker compose -f compose.yaml --profile api up -d
   ```
   >[!TIP]
   >在浏览器中访问 `http://<server_ip>:8000/docs` 查看API文档。
@@ -79,7 +79,7 @@ wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml
 
 ### 启动 Gradio WebUI 服务
   ```bash
-  docker compose -f compose.yaml --profile mineru-gradio up -d
+  docker compose -f compose.yaml --profile gradio up -d
   ```
   >[!TIP]
   > 

mineru/version.py

@@ -1 +1 @@
-__version__ = "2.1.0"
+__version__ = "2.1.1"

pyproject.toml

@@ -109,8 +109,10 @@ pipeline_old_linux = [
 ]
 
 [project.urls]
-Home = "https://mineru.net/"
-Repository = "https://github.com/opendatalab/MinerU"
+homepage = "https://mineru.net/"
+documentation = "https://opendatalab.github.io/MinerU/"
+repository = "https://github.com/opendatalab/MinerU"
+issues = "https://github.com/opendatalab/MinerU/issues"
 
 [project.scripts]
 mineru = "mineru.cli:client.main"

signatures/version1/cla.json

@@ -391,6 +391,278 @@
       "created_at": "2025-07-16T08:53:24Z",
       "repoId": 765083837,
       "pullRequestNo": 3070
+    },
+    {
+      "name": "huazZeng",
+      "id": 125243371,
+      "comment_id": 3100630363,
+      "created_at": "2025-07-22T03:04:40Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3129
+    },
+    {
+      "name": "jinghuan-Chen",
+      "id": 42742857,
+      "comment_id": 3114162786,
+      "created_at": "2025-07-24T16:49:20Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3175
+    },
+    {
+      "name": "androllen",
+      "id": 5212108,
+      "comment_id": 3124534114,
+      "created_at": "2025-07-27T16:47:06Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3190
+    },
+    {
+      "name": "SirlyDreamer",
+      "id": 45280500,
+      "comment_id": 3138729334,
+      "created_at": "2025-07-31T06:36:17Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3222
+    },
+    {
+      "name": "yeahjack",
+      "id": 48432972,
+      "comment_id": 3155914249,
+      "created_at": "2025-08-05T16:59:05Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3269
+    },
+    {
+      "name": "loveRhythm1990",
+      "id": 52204121,
+      "comment_id": 3166629630,
+      "created_at": "2025-08-08T05:32:33Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3281
+    },
+    {
+      "name": "sleepyy-dog",
+      "id": 203856888,
+      "comment_id": 3209716785,
+      "created_at": "2025-08-21T09:23:23Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3354
+    },
+    {
+      "name": "147phoenix",
+      "id": 136807090,
+      "comment_id": 3294702328,
+      "created_at": "2025-09-16T03:18:30Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3477
+    },
+    {
+      "name": "e06084",
+      "id": 24450527,
+      "comment_id": 3302810047,
+      "created_at": "2025-09-17T12:42:23Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3489
+    },
+    {
+      "name": "cjsdurj",
+      "id": 29703648,
+      "comment_id": 3385821350,
+      "created_at": "2025-10-09T13:13:49Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3672
+    },
+    {
+      "name": "ye7love7",
+      "id": 72247118,
+      "comment_id": 3393172470,
+      "created_at": "2025-10-11T10:34:06Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3699
+    },
+    {
+      "name": "magicyuan876",
+      "id": 72277650,
+      "comment_id": 3408782163,
+      "created_at": "2025-10-16T01:09:35Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3739
+    },
+    {
+      "name": "yongtenglei",
+      "id": 65058560,
+      "comment_id": 3408954858,
+      "created_at": "2025-10-16T02:42:08Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3740
+    },
+    {
+      "name": "xvlincaigou",
+      "id": 123342936,
+      "comment_id": 3446786700,
+      "created_at": "2025-10-25T14:38:54Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3841
+    },
+    {
+      "name": "pzc163",
+      "id": 105222039,
+      "comment_id": 3449251055,
+      "created_at": "2025-10-27T02:17:34Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3842
+    },
+    {
+      "name": "aopstudio",
+      "id": 32569353,
+      "comment_id": 3460341998,
+      "created_at": "2025-10-29T08:27:03Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3870
+    },
+    {
+      "name": "Flynn-Zh",
+      "id": 23734538,
+      "comment_id": 3510150100,
+      "created_at": "2025-11-10T08:32:38Z",
+      "repoId": 765083837,
+      "pullRequestNo": 3966
+    },
+    {
+      "name": "eric-ozim",
+      "id": 233696103,
+      "comment_id": 3562698108,
+      "created_at": "2025-11-21T11:56:22Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4040
+    },
+    {
+      "name": "zyileven",
+      "id": 40888939,
+      "comment_id": 3579403940,
+      "created_at": "2025-11-26T06:12:20Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4066
+    },
+    {
+      "name": "borderlayout",
+      "id": 19464348,
+      "comment_id": 3626366462,
+      "created_at": "2025-12-08T11:07:40Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4141
+    },
+    {
+      "name": "lc345",
+      "id": 67670904,
+      "comment_id": 3659976666,
+      "created_at": "2025-12-16T11:03:21Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4196
+    },
+    {
+      "name": "RIORYO",
+      "id": 39397888,
+      "comment_id": 3701766690,
+      "created_at": "2025-12-31T08:54:17Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4277
+    },
+    {
+      "name": "kingdomad",
+      "id": 34766852,
+      "comment_id": 3707777776,
+      "created_at": "2026-01-04T06:16:13Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4283
+    },
+    {
+      "name": "tommygood",
+      "id": 96759292,
+      "comment_id": 3748312307,
+      "created_at": "2026-01-14T08:05:44Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4365
+    },
+    {
+      "name": "pgoslatara",
+      "id": 14027534,
+      "comment_id": 3799210889,
+      "created_at": "2026-01-26T11:58:59Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4421
+    },
+    {
+      "name": "guguducken",
+      "id": 22561920,
+      "comment_id": 3815970299,
+      "created_at": "2026-01-29T07:33:53Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4435
+    },
+    {
+      "name": "Arrmsgt",
+      "id": 115080429,
+      "comment_id": 3851141607,
+      "created_at": "2026-02-05T05:17:32Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4498
+    },
+    {
+      "name": "wzgrx",
+      "id": 39661556,
+      "comment_id": 3854380968,
+      "created_at": "2026-02-05T15:26:44Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4504
+    },
+    {
+      "name": "marswen",
+      "id": 24496561,
+      "comment_id": 3971065560,
+      "created_at": "2026-02-27T06:26:29Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4555
+    },
+    {
+      "name": "vanchy-z",
+      "id": 63965264,
+      "comment_id": 3976573836,
+      "created_at": "2026-02-28T07:14:07Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4560
+    },
+    {
+      "name": "troyhantech",
+      "id": 92877246,
+      "comment_id": 4088446017,
+      "created_at": "2026-03-19T07:58:56Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4631
+    },
+    {
+      "name": "vivekvar-dl",
+      "id": 69627205,
+      "comment_id": 4103182168,
+      "created_at": "2026-03-21T11:54:30Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4636
+    },
+    {
+      "name": "vivekvar-dl",
+      "id": 69627205,
+      "comment_id": 4103186013,
+      "created_at": "2026-03-21T11:57:40Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4636
+    },
+    {
+      "name": "UaRuairc",
+      "id": 77743840,
+      "comment_id": 4118931754,
+      "created_at": "2026-03-24T14:51:59Z",
+      "repoId": 765083837,
+      "pullRequestNo": 4654
     }
   ]
 }