Dockerfile

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

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

# Verify Tesseract installation by checking version and path
RUN which tesseract && tesseract --version

# Set the Tesseract path environment variable, just in case
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"]