Dockerfile

FROM ubuntu:22.04

WORKDIR /app

# ARG HOME= /app
# # RUN mkdir ${HOME}
# ENV SENTENCE_TRANSFORMERS_HOME=${HOME}
# ENV TORCH_HOME=${HOME}

RUN apt update \
    && apt install python3.10 pip -y \
    && rm -rf /var/lib/apt/lists/*

# # Install problematic flash attention from source
# RUN apt update \
#     && apt install git -y \
#     && rm -rf /var/lib/apt/lists/*

# RUN pip install git+https://github.com/Dao-AILab/flash-attention.git

COPY requirements.txt .
RUN python3.10 -m pip install --no-cache-dir -r requirements.txt

COPY . .

# Expose the port that the application listens on.
EXPOSE 8000

# Run the application.
CMD streamlit run inference_main.py  --server.port 7860