Dockerfile

FROM python:3.10-slim

RUN apt-get update && apt-get install -y \
    bash \
    build-essential \
    curl \
    software-properties-common \
    git\
    git-lfs \
    wget \
    sudo \
    procps \
    htop \
    vim \
    neovim && \
    rm -rf /var/lib/apt/lists/*

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

WORKDIR /app
COPY --chown=user ./requirements.txt requirements.txt

RUN pip install --no-cache-dir streamlit pandas transformers torch faiss-cpu scikit-learn neo4j pydeck requests folium streamlit-folium

#RUN python -c "from transformers import AutoTokenizer, AutoModel; AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v2'); AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')"
COPY model/ ./model/
COPY requirements.txt ./
COPY src/ ./src/

RUN pip install -r requirements.txt

COPY --chown=user . /app

EXPOSE 8501

HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
ENV NEO4J_URI=$NEO4J_URI
ENV NEO4J_USERNAME=$NEO4J_USERNAME
ENV NEO4J_PASSWORD=$NEO4J_PASSWORD
ENV OPENAI_API_KEY=$openai_api_key
ENV STREAMLIT_HOME="/tmp/.streamlit"
ENV TRANSFORMERS_CACHE="/tmp/hf_cache"
CMD ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]