Dockerfile

# Use NVIDIA CUDA base image for GPU support
FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04

# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV HF_HOME=/app/cache
ENV TRANSFORMERS_CACHE=/app/cache

# Install Python and other dependencies
RUN apt-get update && apt-get install -y \
    python3 \
    python3-pip \
    python3-dev \
    git \
    && rm -rf /var/lib/apt/lists/*

# Set Python alias
RUN ln -sf /usr/bin/python3 /usr/bin/python

# Create a non-root user with a home directory
RUN useradd -m -u 1000 appuser

# Set the working directory
WORKDIR /app

# Copy requirements and install dependencies first (for better caching)
COPY requirements.txt .
RUN pip3 install --no-cache-dir -r requirements.txt

# Create directories with appropriate permissions
RUN mkdir -p /app/cache && chown -R appuser:appuser /app

# Copy the application code
COPY . .
RUN chown -R appuser:appuser /app

# Switch to the non-root user
USER appuser

# Expose the application port
EXPOSE 8000

# Run the FastAPI application with log level
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000", "--log-level", "info"]