refactor(docker): remove unused packages and simplify Dockerfile commands

- Remove paddleocr, paddlepaddle, rapidocr-paddle, and rapidocr-onnxruntime from requirements.txt files
- Simplify pip install commands in Dockerfiles
- Remove installation of paddlepaddle-gpu in china and global Dockerfiles
- Update requirements.txt files across all Docker configurations

docker/ascend_npu/Dockerfile

@@ -34,10 +34,9 @@ RUN python3 -m venv /opt/mineru_venv
 RUN /bin/bash -c "source /opt/mineru_venv/bin/activate && \
     pip3 install --upgrade pip -i https://mirrors.aliyun.com/pypi/simple && \
     wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/ascend_npu/requirements.txt -O requirements.txt && \
-    pip3 install -r requirements.txt --extra-index-url https://wheels.myhloli.com -i https://mirrors.aliyun.com/pypi/simple && \
+    pip3 install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple && \
     wget https://gitee.com/ascend/pytorch/releases/download/v6.0.rc2-pytorch2.3.1/torch_npu-2.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl && \
-    pip3 install torch_npu-2.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl && \
-    pip3 install https://gcore.jsdelivr.net/gh/myhloli/wheels@main/assets/whl/paddle-custom-npu/paddle_custom_npu-0.0.0-cp310-cp310-linux_aarch64.whl"
+    pip3 install torch_npu-2.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl"
 
 # Copy the configuration file template and install magic-pdf latest
 RUN /bin/bash -c "wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/magic-pdf.template.json && \

docker/ascend_npu/requirements.txt

@@ -11,10 +11,6 @@ torch==2.3.1
 torchvision==0.18.1
 matplotlib
 ultralytics>=8.3.48
-paddleocr==2.7.3
-paddlepaddle==3.0.0rc1
-rapidocr-paddle>=1.4.5,<2.0.0
-rapidocr-onnxruntime>=1.4.4,<2.0.0
 rapid-table>=1.0.3,<2.0.0
 doclayout-yolo==0.0.2b1
 ftfy

docker/china/Dockerfile

@@ -31,8 +31,7 @@ RUN python3 -m venv /opt/mineru_venv
 RUN /bin/bash -c "source /opt/mineru_venv/bin/activate && \
     pip3 install --upgrade pip -i https://mirrors.aliyun.com/pypi/simple && \
     wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/china/requirements.txt -O requirements.txt && \
-    pip3 install -r requirements.txt --extra-index-url https://wheels.myhloli.com -i https://mirrors.aliyun.com/pypi/simple && \
-    pip3 install paddlepaddle-gpu==3.0.0rc1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/"
+    pip3 install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple"
 
 # Copy the configuration file template and install magic-pdf latest
 RUN /bin/bash -c "wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/magic-pdf.template.json && \

docker/china/requirements.txt

@@ -11,9 +11,6 @@ torch>=2.2.2,!=2.5.0,!=2.5.1,<=2.6.0
 torchvision
 matplotlib
 ultralytics>=8.3.48
-paddleocr==2.7.3
-rapidocr-paddle>=1.4.5,<2.0.0
-rapidocr-onnxruntime>=1.4.4,<2.0.0
 rapid-table>=1.0.3,<2.0.0
 doclayout-yolo==0.0.2b1
 ftfy

docker/global/Dockerfile

@@ -31,8 +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://github.com/opendatalab/MinerU/raw/master/docker/global/requirements.txt -O requirements.txt && \
-    pip3 install -r requirements.txt --extra-index-url https://wheels.myhloli.com && \
-    pip3 install paddlepaddle-gpu==3.0.0rc1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/"
+    pip3 install -r requirements.txt"
 
 # Copy the configuration file template and install magic-pdf latest
 RUN /bin/bash -c "wget https://github.com/opendatalab/MinerU/raw/master/magic-pdf.template.json && \

docker/global/requirements.txt

@@ -11,9 +11,6 @@ torch>=2.2.2,!=2.5.0,!=2.5.1,<=2.6.0
 torchvision
 matplotlib
 ultralytics>=8.3.48
-paddleocr==2.7.3
-rapidocr-paddle>=1.4.5,<2.0.0
-rapidocr-onnxruntime>=1.4.4,<2.0.0
 rapid-table>=1.0.3,<2.0.0
 doclayout-yolo==0.0.2b1
 ftfy