feat: pdf2zh + DeepSeek V4 Flash 翻译集成

Dockerfile

@@ -1,16 +1,30 @@
 FROM python:3.11-slim
 
-RUN apt-get update && apt-get install -y --no-install-recommends poppler-utils && rm -rf /var/lib/apt/lists/*
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    poppler-utils \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    libsm6 libxext6 libxrender-dev libgomp1 \
+    && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
 
+# Install PyTorch CPU + pdf2zh
+RUN pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cpu
+RUN pip install --no-cache-dir pdf2zh
+
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
+
 COPY . .
 
+# Pre-download the layout model
+RUN python3 -c "from pdf2zh.doclayout import OnnxModel; OnnxModel.from_pretrained()"
+
 VOLUME ["/app/papers", "/app/data"]
 EXPOSE 8000
 ENV PORT=8000
 ENV LOG_LEVEL=info
+ENV DEEPSEEK_MODEL=deepseek-chat
 
 CMD ["sh", "-c", "python3 -m uvicorn api.server:app --host 0.0.0.0 --port ${PORT} --log-level ${LOG_LEVEL}"]