chore(docker): reintroduce llama-cpp-python pre-built wheel for faster build

Dockerfile

@@ -1,15 +1,23 @@
-# Use official Python 3.12 image
-FROM python:3.12
+# Use official Python 3.12 slim image for smaller size
+FROM python:3.12-slim
 
 # Set working directory
 WORKDIR /app
 
-# Upgrade pip
-RUN pip install --upgrade pip
+# Install minimal system dependencies for llama-cpp-python
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    wget \
+    curl \
+    git \
+    && rm -rf /var/lib/apt/lists/*
 
-# Copy requirements and install dependencies
+# Upgrade pip and install llama-cpp-python pre-built wheel + other dependencies
 COPY ./requirements.txt /app/requirements.txt
-RUN pip install --no-cache-dir --force-reinstall -r requirements.txt
+RUN pip install --upgrade pip && \
+    pip install --no-cache-dir --force-reinstall \
+    -r requirements.txt \
+    --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
 
 # Copy application code
 COPY . /app
@@ -17,5 +25,5 @@ COPY . /app
 # Expose FastAPI port
 EXPOSE 7860
 
-# Use Gunicorn with Uvicorn workers
+# Start FastAPI with Gunicorn + Uvicorn
 CMD ["gunicorn", "app.main:app", "-k", "uvicorn.workers.UvicornWorker", "--bind", "0.0.0.0:7860", "--workers", "1", "--timeout", "120"]