Use Python venv in runtime to avoid PEP 668 pip install error

Dockerfile

@@ -33,10 +33,12 @@ ENV DEBIAN_FRONTEND=noninteractive \
     HF_HOME=/data/hf-cache \
     MODEL_DIR=/data/models \
     MODEL_PATH=/data/models/model.gguf
+ENV PATH=/opt/venv/bin:$PATH
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     python3 \
-    python3-pip \
+  python3-pip \
+  python3-venv \
     ca-certificates \
     libopenblas0-pthread \
     libgomp1 \
@@ -46,8 +48,9 @@ COPY --from=builder /opt/llama.cpp/build/bin/llama-server /usr/local/bin/llama-s
 
 WORKDIR /app
 COPY requirements.txt /app/requirements.txt
-RUN python3 -m pip install --no-cache-dir --upgrade pip \
-  && python3 -m pip install --no-cache-dir -r /app/requirements.txt \
+RUN python3 -m venv /opt/venv \
+  && /opt/venv/bin/python -m pip install --no-cache-dir --upgrade pip \
+  && /opt/venv/bin/pip install --no-cache-dir -r /app/requirements.txt \
   && rm -rf /root/.cache/pip
 
 COPY download_model.py /app/download_model.py