YogeLiu/doc_processer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: refact logic

Browse Source
This commit is contained in:
yogeliu
2025-12-31 17:38:32 +08:00
parent 6ac50f7d2f
commit 35928c2484
17 changed files with 678 additions and 738 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
Dockerfile
View File

@@ -1,54 +1,73 @@
# DocProcesser Dockerfile
# Optimized for RTX 5080 GPU deployment
# Use NVIDIA CUDA base image with Python 3.11
# Use NVIDIA CUDA base image with Python 3.10
FROM nvidia/cuda:12.8.0-runtime-ubuntu24.04
# Set environment variables
ENV PYTHONUNBUFFERED=1 \
PYTHONDONTWRITEBYTECODE=1 \
PIP_NO_CACHE_DIR=1 \
PIP_DISABLE_PIP_VERSION_CHECK=1
PIP_DISABLE_PIP_VERSION_CHECK=1 \
# Model cache directories - mount these at runtime
MODELSCOPE_CACHE=/root/.cache/modelscope \
HF_HOME=/root/.cache/huggingface \
# Application config (override defaults for container)
# Use 127.0.0.1 for --network host mode, or override with -e for bridge mode
PP_DOCLAYOUT_MODEL_DIR=/root/.cache/modelscope/hub/models/PaddlePaddle/PP-DocLayoutV2 \
PADDLEOCR_VL_URL=http://127.0.0.1:8000/v1
# Set working directory
WORKDIR /app
# Install system dependencies
# Install system dependencies and Python 3.10 from deadsnakes PPA
RUN apt-get update && apt-get install -y --no-install-recommends \
python3.11 \
python3.11-venv \
python3.11-dev \
python3-pip \
libgl1-mesa-glx \
software-properties-common \
&& add-apt-repository -y ppa:deadsnakes/ppa \
&& apt-get update && apt-get install -y --no-install-recommends \
python3.10 \
python3.10-venv \
python3.10-dev \
python3.10-distutils \
libgl1 \
libglib2.0-0 \
libsm6 \
libxext6 \
libxrender-dev \
libgomp1 \
curl \
pandoc \
&& rm -rf /var/lib/apt/lists/* \
&& ln -sf /usr/bin/python3.11 /usr/bin/python \
&& ln -sf /usr/bin/python3.11 /usr/bin/python3
&& ln -sf /usr/bin/python3.10 /usr/bin/python \
&& ln -sf /usr/bin/python3.10 /usr/bin/python3 \
&& curl -sS https://bootstrap.pypa.io/get-pip.py | python3.10
# Install uv for fast package management
RUN curl -LsSf https://astral.sh/uv/install.sh | sh
ENV PATH="/root/.local/bin:$PATH"
# Copy dependency files first for better caching
COPY pyproject.toml ./
# Create virtual environment and install dependencies
RUN uv venv /app/.venv
# Install uv via pip (more reliable than install script)
RUN python3.10 -m pip install uv -i https://pypi.tuna.tsinghua.edu.cn/simple
ENV PATH="/app/.venv/bin:$PATH"
ENV VIRTUAL_ENV="/app/.venv"
RUN uv pip install -i https://pypi.tuna.tsinghua.edu.cn/simple -e .
# Copy dependency files first for better caching
COPY pyproject.toml ./
COPY wheels/ ./wheels/
# Create virtual environment and install dependencies
RUN uv venv /app/.venv --python python3.10 \
&& uv pip install -i https://pypi.tuna.tsinghua.edu.cn/simple -e . \
&& rm -rf ./wheels
# Copy application code
COPY app/ ./app/
# Create model directories (models should be mounted at runtime)
RUN mkdir -p /app/app/model/DocLayout /app/app/model/PP-DocLayout
# Create model cache directories (mount from host at runtime)
RUN mkdir -p /root/.cache/modelscope \
/root/.cache/huggingface \
/root/.paddlex \
/app/app/model/DocLayout \
/app/app/model/PP-DocLayout
# Declare volumes for model cache (mount at runtime to avoid re-downloading)
VOLUME ["/root/.cache/modelscope", "/root/.cache/huggingface", "/root/.paddlex"]
# Expose port
EXPOSE 8053
@@ -60,3 +79,21 @@ HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
# Run the application
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8053", "--workers", "1"]
# =============================================================================
# Usage: Mount local model cache to avoid downloading
#
# Option 1: Use host network (simplest, can access localhost services)
# docker run --gpus all --network host \
# -v /home/yoge/.paddlex:/root/.paddlex:ro \
# -v /home/yoge/.cache/modelscope:/root/.cache/modelscope:ro \
# -v /home/yoge/.cache/huggingface:/root/.cache/huggingface:ro \
# doc_processer:latest
#
# Option 2: Use bridge network with host.docker.internal (Linux needs --add-host)
# docker run --gpus all -p 8053:8053 \
# --add-host=host.docker.internal:host-gateway \
# -v /home/yoge/.paddlex:/root/.paddlex:ro \
# -v /home/yoge/.cache/modelscope:/root/.cache/modelscope:ro \
# -v /home/yoge/.cache/huggingface:/root/.cache/huggingface:ro \
# doc_processer:latest
# =============================================================================