Dockerfile

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

# Set environment variables to avoid prompts during package installation
ENV DEBIAN_FRONTEND=noninteractive

# Install system dependencies for OCR (Tesseract) and other libraries
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    libtesseract-dev \
    libgl1-mesa-glx \
    && rm -rf /var/lib/apt/lists/*

# Ensure Tesseract is in the PATH - include both possible locations
ENV PATH="/usr/bin:/usr/local/bin:${PATH}"

# Verify Tesseract installation
RUN tesseract --version

# Set working directory
WORKDIR /app

# Copy the requirements file
COPY requirements.txt .

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

# Copy the application files
COPY . .

# Expose the port Gradio uses (default is 7860)
EXPOSE 7860

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