Dockerfile

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

# Install system-level dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    libglib2.0-0 \
    libgl1 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    poppler-utils \
    ffmpeg \
    git \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV PIP_NO_CACHE_DIR=1
ENV HF_HUB_DISABLE_SYMLINKS_WARNING=1

# Set working directory
WORKDIR /home/user/app

# Copy dependencies and install
COPY requirements.txt .
RUN pip install --upgrade pip && pip install -r requirements.txt

# Copy app source files
COPY . .

# Download NLTK data (punkt tokenizer)
RUN python -m nltk.downloader punkt

# Expose Gradio's default port
EXPOSE 7860

# Launch the Gradio app
CMD ["python", "app.py"]