Dockerfile

# Use Python 3.9 as base image
FROM python:3.9-slim

# Set working directory
WORKDIR /app

# Create a non-root user
RUN useradd -m -u 1000 user && \
    chown -R user:user /app

# Set environment variables
ENV PYTHONUNBUFFERED=1 \
    TRANSFORMERS_CACHE=/app/cache \
    MPLCONFIGDIR=/app/matplotlib \
    HOME=/app

# Copy requirements first to leverage Docker cache
COPY requirements.txt .

# Install dependencies and download required NLTK data
RUN pip install --no-cache-dir -r requirements.txt && \
    python -m textblob.download_corpora && \
    python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger'); nltk.download('wordnet')"

# Install additional system dependencies for sentence-transformers
RUN apt-get update && apt-get install -y \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Copy the rest of the application
COPY . .

# Create necessary directories and set permissions
RUN mkdir -p /app/cache /app/matplotlib && \
    chown -R user:user /app

# Switch to non-root user
USER user

# Expose port 7860 for Gradio
EXPOSE 7860

# Set environment variables
ENV GRADIO_SERVER_NAME=0.0.0.0

# Command to run the application
CMD ["python", "app.py"]