Dockerfile

# Use an official Python image from Docker Hub
FROM python:3.10-slim

# Install system dependencies and Tesseract OCR
RUN apt-get update && \
    apt-get install -y tesseract-ocr && \
    apt-get clean

# Set the environment variable for Tesseract to be in PATH
ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00/tessdata/

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

# Copy the application code
COPY . .

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