fix(docker): resolve llama-cpp-python module import error

Dockerfile

@@ -1,29 +1,28 @@
-# Use official Python 3.12 slim image for smaller size
+# Use official Python 3.12 slim image
 FROM python:3.12-slim
 
-# Set working directory
 WORKDIR /app
 
-# Install minimal system dependencies for llama-cpp-python
+# Install minimal runtime dependencies
 RUN apt-get update && apt-get install -y \
-    build-essential \
     wget \
     curl \
-    git \
     && rm -rf /var/lib/apt/lists/*
 
-# Upgrade pip and install llama-cpp-python pre-built wheel + other dependencies
 COPY ./requirements.txt /app/requirements.txt
-RUN pip install --upgrade pip && \
-    pip install --no-cache-dir --force-reinstall \
-    -r requirements.txt \
+
+# Upgrade pip
+RUN pip install --upgrade pip
+
+# Install llama-cpp-python from pre-built wheel
+RUN pip install llama-cpp-python \
     --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
 
-# Copy application code
+# Install other requirements
+RUN pip install --no-cache-dir -r requirements.txt
+
 COPY . /app
 
-# Expose FastAPI port
 EXPOSE 7860
 
-# Start FastAPI with Gunicorn + Uvicorn
-CMD ["gunicorn", "app.main:app", "-k", "uvicorn.workers.UvicornWorker", "--bind", "0.0.0.0:7860", "--workers", "1", "--timeout", "120"]
+CMD ["gunicorn", "app.main:app", "-k", "uvicorn.workers.UvicornWorker", "--bind", "0.0.0.0:7860", "--workers", "1", "--timeout", "120"]