Dockerfile

# Use NVIDIA CUDA base image
FROM nvidia/cuda:12.3.2-cudnn9-devel-ubuntu22.04

# Install system dependencies for Python and Poetry
RUN apt-get update && apt-get install -y \
    python3 python3-pip python3-venv build-essential curl git \
    && rm -rf /var/lib/apt/lists/*

# Install Poetry globally
RUN pip install --no-cache-dir --upgrade pip \
    && pip install --no-cache-dir poetry

# Set environment variables for Poetry and Python
ENV POETRY_VIRTUALENVS_CREATE=false \
    POETRY_CACHE_DIR=/root/.cache/pypoetry \
    PATH="/root/.local/bin:$PATH"

# Set the working directory
WORKDIR /app

# Copy Poetry configuration files
COPY pyproject.toml ./

# Install Python dependencies with Poetry
RUN poetry install --no-interaction --no-ansi \
    && pip install --no-build-isolation flash-attn \
    && pip install "rerankers[all]"

RUN useradd -m -u 1000 user
USER user
ENV HOME /home/user
ENV PATH $HOME/.local/bin:$PATH

# Copy the rest of the application
WORKDIR $HOME
RUN mkdir app
WORKDIR $HOME/app
COPY . $HOME/app

# Expose a port if needed (update according to your application)
#EXPOSE 8501
#
#CMD streamlit run app.py \
#    --server.headless true \
#    --server.enableCORS false \
#    --server.enableXsrfProtection false \
#    --server.fileWatcherType none

EXPOSE 7860

CMD ["streamlit", "run", "app.py", "--server.address=0.0.0.0", "--server.port=7860"]

#EXPOSE 8501
#
#HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
#
#ENTRYPOINT ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]