Update Dockerfile

Dockerfile

@@ -2,35 +2,38 @@ FROM python:3.10-slim
 
 WORKDIR /app
 
-# Install minimal system dependencies
+# Install minimal system dependencies + build tools
 RUN apt-get update && apt-get install -y \
     wget \
     curl \
+    build-essential \
+    cmake \
+    python3-dev \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy requirements first for better caching
+# Copy requirements
 COPY requirements.txt .
 
-# Install Python dependencies, forcing precompiled wheels for llama-cpp-python
+# Install Python packages
 RUN pip install --no-cache-dir --upgrade pip && \
     pip install --no-cache-dir --prefer-binary -r requirements.txt
 
-# Download model file
+# Download GGUF model
 RUN echo "📥 Downloading CapybaraHermes model..." && \
     wget --progress=bar:force:noscroll -O capybarahermes-2.5-mistral-7b.Q5_K_M.gguf \
     https://huggingface.co/TheBloke/CapybaraHermes-2.5-Mistral-7B-GGUF/resolve/main/capybarahermes-2.5-mistral-7b.Q5_K_M.gguf && \
     echo "✅ Model downloaded: $(du -h capybarahermes-2.5-mistral-7b.Q5_K_M.gguf | cut -f1)"
 
-# Copy application files
+# Copy app code
 COPY api.py .
 COPY app.py .
 
-# Expose Hugging Face Spaces port
+# Expose Hugging Face port
 EXPOSE 7860
 
 # Health check
 HEALTHCHECK --interval=30s --timeout=30s --start-period=300s --retries=3 \
   CMD curl --fail http://localhost:7860/_stcore/health || exit 1
 
-# Run Streamlit on port 7860
+# Start Streamlit
 CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0", "--server.headless=true"]