Dockerfile

# Use a Debian-based Python image.
FROM python:3.10

# Set the working directory
WORKDIR /app

# Expose the port Streamlit runs on
EXPOSE 8501

# Copy the requirements file and application code
COPY requirements.txt .
COPY pdf_utils.py .
COPY merged.py .
COPY app.py .

# --- ROBUST DEPENDENCY INSTALLATION ---

# 1. Upgrade pip for stability
RUN pip install --upgrade pip

# 2. Install PyTorch ONLY, using the CPU-specific index.
RUN pip install torch --index-url https://download.pytorch.org/whl/cpu

# 3. Install all remaining complex and general dependencies using the standard index (PyPI).
# We install these explicitly here since they were previously excluded from requirements.txt
RUN pip install \
    accelerate \
    transformers \
    huggingface-hub

# 4. Install the final, smaller dependencies from the trimmed requirements.txt
RUN pip install -r requirements.txt
RUN apt-get update && apt-get install -y fonts-dejavu
# --- END INSTALLATION ---

# Command to run the Streamlit application
CMD ["streamlit", "run", "app.py", "--server.port", "8501", "--server.address", "0.0.0.0"]