Update Dockerfile

Dockerfile

@@ -1,19 +1,32 @@
-# Use Python 3.10 base
+# Start from a basic Python 3.10 image
 FROM python:3.10-slim
 
-# Install system dependencies
-RUN apt-get update && apt-get install -y wget build-essential && rm -rf /var/lib/apt/lists/*
+# Set frontend to noninteractive to avoid prompts
+ENV DEBIAN_FRONTEND=noninteractive
 
-# Install Python packages
-COPY requirements.txt /app/requirements.txt
+# Install system dependencies needed to *build* llama-cpp-python
+# This fixes compile errors.
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    cmake \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set the working directory inside the container
 WORKDIR /app
-RUN pip install --no-cache-dir -r requirements.txt
 
-# Pre-download smallest model to make build faster
-RUN wget -O stablelm-zephyr-3b.Q3_K_S.gguf https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF/resolve/main/stablelm-zephyr-3b.Q3_K_S.gguf || true
+# Copy the requirements file first
+COPY ./requirements.txt /app/requirements.txt
 
-# Copy app code
-COPY . /app
+# Install Python packages
+RUN pip install --no-cache-dir --upgrade pip
+RUN pip install --no-cache-dir -r /app/requirements.txt
 
+# Copy the main application file
+COPY ./app.py /app/app.py
+
+# Expose the port that FastAPI (uvicorn) will run on
 EXPOSE 7860
-CMD ["python", "app.py"]
+
+# Command to run the application
+# This starts app.py, which will THEN download the model.
+CMD ["python", "app.py"]