feat: optimize Docker image with multi-stage build
- Use multi-stage build to exclude build dependencies from final image - Separate builder stage using devel image from runtime stage using smaller base image - Clean venv: remove __pycache__, .pyc files, and test directories - Remove embedded model files (243MB) from app/model/ - mount at runtime instead - Expected size reduction: 18.9GB → 2-3GB (80-90% reduction) Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
This commit is contained in:
liuyuanchuang
95
Dockerfile
95
Dockerfile
@@ -1,7 +1,55 @@
|
||||
# DocProcesser Dockerfile
|
||||
# DocProcesser Dockerfile - Multi-stage optimized build
|
||||
# Optimized for RTX 5080 GPU deployment
|
||||
|
||||
# Use NVIDIA CUDA base image with Python 3.10
|
||||
# =============================================================================
|
||||
# STAGE 1: Builder - Install dependencies
|
||||
# =============================================================================
|
||||
FROM nvidia/cuda:12.9.0-devel-ubuntu24.04 AS builder
|
||||
|
||||
# Install build dependencies and Python 3.10
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
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 \
|
||||
build-essential \
|
||||
curl \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Setup Python
|
||||
RUN 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
|
||||
RUN python3.10 -m pip install uv -i https://pypi.tuna.tsinghua.edu.cn/simple
|
||||
|
||||
WORKDIR /build
|
||||
|
||||
# Copy dependency files
|
||||
COPY pyproject.toml ./
|
||||
COPY wheels/ ./wheels/
|
||||
|
||||
# Create virtual environment with dependencies
|
||||
RUN uv venv /build/venv --python python3.10 && \
|
||||
. /build/venv/bin/activate && \
|
||||
uv pip install -i https://pypi.tuna.tsinghua.edu.cn/simple -e . && \
|
||||
rm -rf ./wheels
|
||||
|
||||
# Clean up venv - remove unnecessary files
|
||||
RUN find /build/venv -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true && \
|
||||
find /build/venv -type d -name "*.dist-info/tests" -exec rm -rf {} + 2>/dev/null || true && \
|
||||
find /build/venv -type f -name "*.pyc" -delete && \
|
||||
find /build/venv -type f -name "*.pyo" -delete && \
|
||||
find /build/venv -type d -name "tests" -exec rm -rf {} + 2>/dev/null || true && \
|
||||
find /build/venv -type d -name "test" -exec rm -rf {} + 2>/dev/null || true
|
||||
|
||||
# =============================================================================
|
||||
# STAGE 2: Runtime - Minimal final image
|
||||
# =============================================================================
|
||||
FROM nvidia/cuda:12.9.0-runtime-ubuntu24.04
|
||||
|
||||
# Set environment variables
|
||||
@@ -15,20 +63,15 @@ ENV PYTHONUNBUFFERED=1 \
|
||||
# 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://127.0.0.1:8001/v1
|
||||
PADDLEOCR_VL_URL=http://127.0.0.1:8001/v1 \
|
||||
PATH="/app/.venv/bin:$PATH" \
|
||||
VIRTUAL_ENV="/app/.venv"
|
||||
|
||||
# Set working directory
|
||||
WORKDIR /app
|
||||
|
||||
# Install system dependencies and Python 3.10 from deadsnakes PPA
|
||||
# Install runtime-only system dependencies (NO build tools)
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
software-properties-common \
|
||||
&& add-apt-repository -y ppa:deadsnakes/ppa \
|
||||
&& apt-get update && apt-get install -y --no-install-recommends \
|
||||
python3.10 \
|
||||
python3.10-venv \
|
||||
python3.10-dev \
|
||||
python3.10-distutils \
|
||||
libgl1 \
|
||||
libglib2.0-0 \
|
||||
libsm6 \
|
||||
@@ -37,34 +80,24 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
libgomp1 \
|
||||
curl \
|
||||
pandoc \
|
||||
&& rm -rf /var/lib/apt/lists/* \
|
||||
&& ln -sf /usr/bin/python3.10 /usr/bin/python \
|
||||
&& ln -sf /usr/bin/python3.10 /usr/bin/python3 \
|
||||
&& curl -sS https://bootstrap.pypa.io/get-pip.py | python3.10
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Install uv via pip (more reliable than install script)
|
||||
RUN python3.10 -m pip install uv -i https://pypi.tuna.tsinghua.edu.cn/simple
|
||||
ENV PATH="/app/.venv/bin:$PATH"
|
||||
ENV VIRTUAL_ENV="/app/.venv"
|
||||
# Setup Python symlinks
|
||||
RUN ln -sf /usr/bin/python3.10 /usr/bin/python && \
|
||||
ln -sf /usr/bin/python3.10 /usr/bin/python3
|
||||
|
||||
# Copy dependency files first for better caching
|
||||
COPY pyproject.toml ./
|
||||
COPY wheels/ ./wheels/
|
||||
# Copy pre-built venv from builder stage
|
||||
COPY --from=builder /build/venv /app/.venv
|
||||
|
||||
# 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 application code (excluding model files if they're in the repo)
|
||||
COPY app/ ./app/
|
||||
|
||||
# Create model cache directories (mount from host at runtime)
|
||||
# NOTE: Remove model files from app/model to keep image lean
|
||||
RUN mkdir -p /root/.cache/modelscope \
|
||||
/root/.cache/huggingface \
|
||||
/root/.paddlex \
|
||||
/app/app/model/DocLayout \
|
||||
/app/app/model/PP-DocLayout
|
||||
/root/.paddlex && \
|
||||
rm -rf /app/app/model/*
|
||||
|
||||
# Declare volumes for model cache (mount at runtime to avoid re-downloading)
|
||||
VOLUME ["/root/.cache/modelscope", "/root/.cache/huggingface", "/root/.paddlex"]
|
||||
|
||||
Reference in New Issue
Block a user