Update Dockerfile

Dockerfile

@@ -1,27 +1,38 @@
 FROM python:3.10-slim
 
-# Install system dependencies for llama-cpp-python compilation
+# Install system dependencies for OpenCV, PaddlePaddle, and compiling llama-cpp-python
 RUN apt-get update && apt-get install -y \
     libgl1 \
     libglib2.0-0 \
     libgomp1 \
     build-essential \
     python3-dev \
-    cmake \
     && rm -rf /var/lib/apt/lists/*
 
+# Set working directory
 WORKDIR /app
 
+# Copy requirements and install
 COPY requirements.txt .
+
+# Install dependencies (llama-cpp-python will compile from source)
+# Note: To enable CUDA for NVIDIA GPUs, add `ENV CMAKE_ARGS="-DGGML_CUDA=on"` before this step 
+# and use an `nvidia/cuda` base image instead of `python:3.10-slim`.
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Pre-download the GGUF model weights into the image
+# Pre-download the local LLM weights into the Docker image cache 
+# so it doesn't download on every container start.
 RUN python -c "from huggingface_hub import hf_hub_download; hf_hub_download(repo_id='Qwen/Qwen2.5-7B-Instruct-GGUF', filename='qwen2.5-7b-instruct-q4_k_m.gguf')"
 
+# Copy application files
 COPY . .
 
+# Set environment variables for Gradio
 ENV GRADIO_SERVER_NAME="0.0.0.0"
 ENV GRADIO_SERVER_PORT="7860"
+
+# Expose the Gradio port
 EXPOSE 7860
 
+# Run the application
 CMD ["python", "app.py"]