Dockerfile

FROM python:3.11-slim

WORKDIR /rag-application

# Install system dependencies
RUN apt-get update && \
    apt-get install -y curl

# Install Ollama
RUN curl -fsSL https://ollama.com/install.sh | sh

RUN pip install poetry

# Copy only the needed files first to leverage Docker cache
COPY pyproject.toml poetry.lock /rag-application/

# Install dependencies
RUN poetry config virtualenvs.create false \
    && poetry lock \
    && poetry install --no-interaction --no-ansi --no-root

# Copy the rest of the application files
COPY . /rag-application
 
# Copy the startup script and make it executable
COPY install_model_in_ollama.sh /rag-application/install_model_in_ollama.sh
RUN chmod +x /rag-application/install_model_in_ollama.sh

RUN mkdir -p /.ollama && \
    chown -R 1000:1000 /.ollama

# Expose port 5000 for the Flask app
EXPOSE 5000

# Define environment variable to ensure the Flask app runs in a container
ENV PYTHONUNBUFFERED=1

# Run the command to start the Gunicorn server
CMD ["/rag-application/install_model_in_ollama.sh"]

# CMD ["gunicorn", "-c", "gunicorn.py", "app:app"]