Files
weave/pipelines/containers/docker_files/Dockerfile.bert_topic

39 lines
777 B
Docker

FROM python:3.12-bookworm
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV PIP_NO_CACHE_DIR=1
RUN apt-get update && apt-get install -y \
build-essential \
gcc \
g++ \
git \
libgomp1 \
libpq-dev \
&& rm -rf /var/lib/apt/lists/*
WORKDIR /app
COPY pipelines ./pipelines
RUN python -m pip install --upgrade pip setuptools wheel && \
python -m pip install \
torch \
--index-url https://download.pytorch.org/whl/cpu && \
python -m pip install \
typer \
sqlalchemy \
bertopic \
sentence-transformers \
scikit-learn \
pandas \
numpy \
"psycopg[binary]"
ENV HF_HOME=/cache/huggingface
ENV TRANSFORMERS_CACHE=/cache/huggingface
ENTRYPOINT ["python", "-m"]
CMD ["pipelines.bert_topic.train"]