Use prebuilt CPU wheel for llama-cpp-python (source build OOMs)

Dockerfile

@@ -5,7 +5,7 @@ ENV PYTHONUNBUFFERED=1
 ENV PIP_NO_CACHE_DIR=1
 
 RUN apt-get update \
-    && apt-get install -y --no-install-recommends build-essential cmake \
+    && apt-get install -y --no-install-recommends libgomp1 \
     && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
@@ -13,7 +13,9 @@ WORKDIR /app
 COPY requirements.txt /app/requirements.txt
 
 RUN pip install --upgrade pip \
-    && pip install -r /app/requirements.txt
+    && pip install --prefer-binary \
+        --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu \
+        -r /app/requirements.txt
 
 COPY main.py /app/main.py