Dockerfile

# Install Tesseract and language packs
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-eng \
    tesseract-ocr-urd \
    libgl1 \
    && rm -rf /var/lib/apt/lists/*

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

# Install system dependencies for Tesseract and OpenCV
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-eng \
    tesseract-ocr-urd \
    libgl1 \
    && rm -rf /var/lib/apt/lists/*

# Set the Tesseract data path
ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00/tessdata

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

# Copy the application code
COPY . .

# Expose the port for Streamlit
EXPOSE 8501

# Run the Streamlit app
CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]