Dockerfile

# Use official Python 3.10 slim image as base
FROM python:3.10-slim

# Set working directory
WORKDIR /app

# Set environment variables for NLTK and Hugging Face cache
ENV NLTK_DATA=/app/nltk_data
ENV TRANSFORMERS_CACHE=/app/hf_cache
ENV PYTHONUNBUFFERED=1

# Install system dependencies
RUN apt-get update && apt-get install -y \
    gcc \
    g++ \
    libmariadb-dev-compat \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements.txt
COPY requirements.txt .

# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt

# Pre-download NLTK punkt data to avoid runtime permission issues
RUN python -m nltk.downloader -d /app/nltk_data punkt

# Copy application code
COPY app/main.py ./app/main.py
COPY static/index.html ./static/index.html

# Create cache directories and set permissions
RUN mkdir -p /app/nltk_data /app/hf_cache \
    && chmod -R 777 /app/nltk_data /app/hf_cache

# Create a non-root user and switch to it
RUN useradd -m -u 1000 appuser \
    && chown -R appuser:appuser /app
USER appuser

# Expose port 7860 for Hugging Face Spaces
EXPOSE 7860

# Run the FastAPI app with Uvicorn
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]