Update Dockerfile

Dockerfile

@@ -1,7 +1,7 @@
 FROM ollama/ollama:latest
 
 # 1. Install dependencies
-RUN apt-get update && apt-get install -y curl bash python3 python3-pip && rm -rf /var/lib/apt/lists/*
+RUN apt-get update && apt-get install -y curl bash python3 python3-pip python3-venv && rm -rf /var/lib/apt/lists/*
 
 # 2. Download your model
 RUN curl -L "https://huggingface.co/JohnLicode/johnli-qwen-gguf/resolve/main/johnli-qwen.gguf?download=true" -o /root/johnli-qwen.gguf
@@ -12,13 +12,14 @@ RUN echo 'FROM /root/johnli-qwen.gguf' > /root/Modelfile && \
     echo 'PARAMETER temperature 0.7' >> /root/Modelfile && \
     echo 'PARAMETER num_predict 256' >> /root/Modelfile
 
-# 4. Copy app files
+# 4. Setup Python virtual environment and install packages
 WORKDIR /app
 COPY requirements.txt .
-RUN pip3 install --no-cache-dir -r requirements.txt
+RUN python3 -m venv /app/venv && \
+    /app/venv/bin/pip install --no-cache-dir -r requirements.txt
 COPY app.py .
 
-# 5. Create startup script that runs both Ollama and Gradio
+# 5. Create startup script
 RUN printf '#!/bin/bash\n\
 echo "Starting Ollama server..."\n\
 ollama serve &\n\
@@ -26,7 +27,7 @@ sleep 10\n\
 echo "Creating model..."\n\
 ollama create johnli-persona -f /root/Modelfile\n\
 echo "Starting Gradio app..."\n\
-python3 /app/app.py\n' > /start.sh && chmod +x /start.sh
+/app/venv/bin/python /app/app.py\n' > /start.sh && chmod +x /start.sh
 
 # 6. Port for Gradio
 EXPOSE 7860