Dockerfile

# Use a full Debian-based image with Python
FROM python:3.9-slim

# Set environment variables for non-interactive installs
ENV DEBIAN_FRONTEND=noninteractive

# Install Tesseract and required system dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    libtesseract-dev \
    libleptonica-dev \
    poppler-utils \
    pkg-config \
    build-essential \
    python3-dev \
    && rm -rf /var/lib/apt/lists/*

# (Optional) Add Hindi or other Tesseract language packs if needed:
# RUN apt-get install -y tesseract-ocr-hin tesseract-ocr-eng

# Set working directory
WORKDIR /app

# Copy project files
COPY . .

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

# Set environment PATH explicitly in case PATH issues exist
ENV PATH="/usr/bin/tesseract:${PATH}"

# Default command to run the Gradio app
CMD ["python", "app.py"]