Dockerfile

FROM ubuntu:20.04

ENV DEBIAN_FRONTEND=noninteractive

# Install Python and system dependencies
RUN apt-get update && apt-get install -y \
    python3.9 \
    python3-pip \
    tesseract-ocr \
    tesseract-ocr-eng \
    libgl1-mesa-glx \
    libglib2.0-0 \
    poppler-utils \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /code

# Upgrade pip and install dependencies
COPY requirements.txt .
RUN python3.9 -m pip install --no-cache-dir --upgrade pip && \
    python3.9 -m pip install --no-cache-dir -r requirements.txt

# Copy the application
COPY . .

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00/tessdata

# Run the application
CMD ["python3.9", "app.py"]