Dockerfile

# Use an official Python runtime as a parent image
FROM python:3.10-slim

# Install system dependencies for document processing and OCR
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    libtesseract-dev \
    poppler-utils \
    libgl1 \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    gcc \
    python3-dev \
    && rm -rf /var/lib/apt/lists/*

# Set the working directory in the container
WORKDIR /app

# Copy the requirements file into the container
COPY requirements.txt .

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

# Copy the rest of the application code
COPY . .

# Create directories for documents and indices
RUN mkdir -p documents indices

# Expose the port the app runs on
EXPOSE 5000

# Command to run the application
CMD ["python", "app.py"]