fix build memory

Dockerfile

@@ -1,8 +1,9 @@
-FROM python:3.10-slim
+FROM python:3.12-slim
 WORKDIR /app
-RUN apt-get update && apt-get install -y curl && rm -rf /var/lib/apt/lists/*
-RUN pip install --upgrade pip
+RUN apt-get update && apt-get install -y --no-install-recommends curl && rm -rf /var/lib/apt/lists/*
+RUN pip install --no-cache-dir llama-cpp-python==0.3.23 \
+  --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
 COPY requirements.txt .
-RUN pip install -r requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
 COPY . .
 CMD ["python", "app.py"]

requirements.txt

@@ -1,4 +1,3 @@
 fastapi
 uvicorn
-llama-cpp-python
 huggingface_hub