v1.5出来后就开始尝试部署，但是按照官方的部署流程，一直不成功，这里记录一下。

conda create -n MonkeyOCR python=3.10
conda activate MonkeyOCR

git clone https://github.com/Yuliang-Liu/MonkeyOCR.git
cd MonkeyOCR

export CUDA_VERSION=126 # for CUDA 12.6
# export CUDA_VERSION=118 # for CUDA 11.8

pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu${CUDA_VERSION}/
pip install langchain==0.3.26
pip install "paddlex[base]==3.1.4"

到这里不会报错

pip install torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 --index-url https://download.pytorch.org/whl/cu${CUDA_VERSION}

pip install -e .

会出现报错：

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the foll
owing dependency conflicts.
paddlepaddle-gpu 3.0.0 requires nvidia-nccl-cu12==2.25.1; platform_system == "Linux" and platform_machine == "x86_64", but you have nvidia-nccl-cu12 2.21.5 which is incompatible.

不用管

# CUDA 12.6
pip install lmdeploy==0.9.2
# CUDA 11.8
# pip install https://github.com/InternLM/lmdeploy/releases/download/v0.9.2/lmdeploy-0.9.2+cu118-cp310-cp310-many

下一步按照官网下载模型权重：

pip install modelscope

python tools/download_model.py -t modelscope -n MonkeyOCR-pro-3B

然后运行

python parse.py  x x x x x x x x

会出现报错：

ImportError: Paddlex is not installed. Please install it using 'pip install paddlex'.

这个时候使用pip list会发现langchain的版本不对。

重新运行作者的指定的安装版本：

pip install langchain==0.3.26

到此环境配置成功，可以正常运行。