Dockerfile

# Use the official Python 3.12 image as a base
FROM python:3.12-slim

# Set environment variables to prevent Python from writing .pyc files and buffering stdout/stderr
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    git \
    wget \
    curl \
    unzip \
    && rm -rf /var/lib/apt/lists/*

# Create a working directory
WORKDIR /app

# Install Python dependencies
RUN pip install --upgrade pip
RUN pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
RUN pip install transformers accelerate
RUN pip install -r requirements.txt

# Copy the current directory contents into the container at /app
COPY . /app

# Copy the zip file containing XML and JSON data into the container
COPY data.zip /app/data.zip

# Unzip the data.zip file into the /app/data directory
RUN unzip /data.zip -d /app/data

# Set the default command to run when starting the container
CMD ["python", "model.py"]