FROM python:3.10-slim

WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    curl \
    git \
    software-properties-common \
    libpoppler-dev \
    libmagic1 \
    tesseract-ocr \
    libreoffice \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first for better caching
COPY requirements.txt .

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

# Pre-download NLTK data
RUN python -m nltk.downloader punkt averaged_perceptron_tagger stopwords words wordnet omw-1.4

# Create directory for NLTK data with proper permissions
RUN mkdir -p /usr/local/share/nltk_data && chmod 777 /usr/local/share/nltk_data

# Copy the rest of the application
COPY . .

# Set environment variable to specify NLTK data path
ENV NLTK_DATA=/usr/local/share/nltk_data

# Expose the port Streamlit runs on
EXPOSE 7860

# Command to run the application
CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]