# Use a base image that supports Python and is suitable for Streamlit
FROM python:3.10-slim

# Install Tesseract and Poppler (required by pdf2image) using apt-get
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    libtesseract-dev \
    poppler-utils \
    && rm -rf /var/lib/apt/lists/*

# Copy your requirements file first (for better caching)
COPY requirements.txt .

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

# Set the working directory inside the container
WORKDIR /app

# Copy the rest of your application code (including app.py, tessdata/, etc.)
COPY . .

# Expose the port Streamlit runs on (default is 8501)
EXPOSE 8501

# Define the command to run your Streamlit app
# Use --server.address 0.0.0.0 to allow external connections
CMD ["streamlit", "run", "app.py", "--server.address", "0.0.0.0"]