Dockerfile

# Base image
FROM python:3.12

# Set working directory inside the container
WORKDIR /app/rag-system

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    libpoppler-cpp-dev \
    wget \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

RUN pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu


# Install Poetry
RUN pip install --no-cache-dir poetry

# Copy project files
COPY poetry.lock pyproject.toml /app/
COPY rag-system /app/rag-system/

# Set environment variables
ENV PYTHONPATH=/app/rag-system/src
ENV TOKENIZERS_PARALLELISM=false
ENV TORCH_CPP_LOG_LEVEL=ERROR
ENV PYTORCH_DISABLE_SYSTEM_MONITORING=1

# Configure Poetry
RUN poetry config virtualenvs.create false

# Install dependencies with Poetry
RUN poetry install --no-root --no-dev

# Run preprocessing
RUN python3 -m src.preprocessing

# Expose the app's default port
EXPOSE 7860

# Command to start the app
CMD ["python3", "app.py"]