feat: add Docker support for offline deployment with qwen3:14b

Major additions:
- All-in-One Docker image with Ollama + models bundled
- Separate deployment option for existing Ollama installations
- Changed default model from qwen3:8b to qwen3:14b
- Comprehensive deployment documentation

Files added:
- Dockerfile: Basic app-only image
- Dockerfile.allinone: Complete image with Ollama + models
- docker-compose.yml: Easy deployment configuration
- docker-entrypoint.sh: Startup script for all-in-one image
- requirements.txt: Python dependencies
- .dockerignore: Exclude unnecessary files from image

Scripts:
- export-ollama-models.sh: Export models from local Ollama
- build-allinone.sh: Build complete offline-deployable image
- build-and-export.sh: Build and export basic image

Documentation:
- DEPLOYMENT.md: Comprehensive deployment guide
- QUICK_START.md: Quick reference for common tasks

Configuration:
- Updated config.py: DEFAULT_CHAT_MODEL = qwen3:14b
- Updated frontend/opro.html: Page title to 系统提示词优化

Dockerfile

@@ -0,0 +1,38 @@
+FROM python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements file
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY _qwen_xinference_demo/ ./_qwen_xinference_demo/
+COPY frontend/ ./frontend/
+COPY config.py .
+
+# Create outputs directory
+RUN mkdir -p outputs
+
+# Expose port
+EXPOSE 8010
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+ENV OLLAMA_HOST=http://host.docker.internal:11434
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8010/health || exit 1
+
+# Run the application
+CMD ["uvicorn", "_qwen_xinference_demo.api:app", "--host", "0.0.0.0", "--port", "8010"]
+