Dockerfile

# Use an official Python runtime as a parent image
FROM nvidia/cuda:12.3.1-runtime-ubuntu22.04 
# Set Python to use unbuffered mode
ENV PYTHONUNBUFFERED 1
RUN apt-get update && \
    apt-get install -y --no-install-recommends python3-pip python3-dev && \
    rm -rf /var/lib/apt/lists/*
# Set the working directory in the container
RUN mkdir /var/www
ENV HOME /var/www
WORKDIR /var/www

# Copy the current directory contents into the container at /app
COPY . /var/www

RUN pip install -r requirements.txt
RUN pip install torch==1.12.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
# RUN python -c "import nltk; nltk.download('punkt')"
# RUN python -c "import nltk; nltk.download('stopwords')"
# RUN python -m nltk.downloader -d $HOME/nltk_data punkt stopwords

EXPOSE 7866

RUN --mount=type=secret,id=HF_TOKEN,mode=0444,required=true \
    HF_TOKEN=$(cat /run/secrets/HF_TOKEN) && export HF_TOKEN

# Define environment variable
ENV FLASK_APP app.py \
    HF_MODEL_NAME "muryshev/e5_large_rus_finetuned_20240120_122822_ep6"

# Run app.py when the container launches
CMD flask run --host=0.0.0.0 --port=7869