Dockerfile.python

# Python 服务 Dockerfile
# 包含 Tesseract OCR 和 Embedding 模型预下载

FROM python:3.10-slim

# 使用阿里云 Debian 镜像源（国内加速）
RUN sed -i 's/deb.debian.org/mirrors.aliyun.com/g' /etc/apt/sources.list.d/debian.sources

# 安装系统依赖
RUN apt-get update && apt-get install -y --no-install-recommends \
    tesseract-ocr \
    tesseract-ocr-chi-sim \
    tesseract-ocr-eng \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# 先复制 requirements.txt，利用 Docker 缓存
COPY python-service/requirements.txt .
RUN pip install --no-cache-dir --default-timeout=600 --retries=5 -i https://pypi.tuna.tsinghua.edu.cn/simple --trusted-host pypi.tuna.tsinghua.edu.cn -r requirements.txt

# 复制服务代码
COPY python-service/ .

# 创建必要的目录
RUN mkdir -p uploads temp faiss_index

EXPOSE 8000

CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]