Update Dockerfile

Dockerfile

@@ -2,38 +2,37 @@ FROM python:3.10-slim
 
 WORKDIR /app
 
-# Install minimal system dependencies + build tools
+# Install minimal system dependencies
 RUN apt-get update && apt-get install -y \
     wget \
     curl \
-    build-essential \
-    cmake \
-    python3-dev \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy requirements
-COPY requirements.txt .
+# Install precompiled llama-cpp-python wheel (v0.2.24 for Python 3.10)
+RUN pip install --no-cache-dir \
+  https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.24/llama_cpp_python-0.2.24-cp310-cp310-manylinux2014_x86_64.whl
 
-# Install Python packages
+# Copy and install the rest of the Python dependencies
+COPY requirements.txt .
 RUN pip install --no-cache-dir --upgrade pip && \
-    pip install --no-cache-dir --prefer-binary -r requirements.txt
+    pip install --no-cache-dir -r requirements.txt
 
-# Download GGUF model
+# Download the quantized model file (Q5_K_M)
 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 app code
+# Copy application files
 COPY api.py .
 COPY app.py .
 
-# Expose Hugging Face port
+# Expose Streamlit port
 EXPOSE 7860
 
-# Health check
+# Health check for Hugging Face Spaces
 HEALTHCHECK --interval=30s --timeout=30s --start-period=300s --retries=3 \
   CMD curl --fail http://localhost:7860/_stcore/health || exit 1
 
-# Start Streamlit
+# Start Streamlit app
 CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0", "--server.headless=true"]