presidio/presidio-analyzer/Dockerfile.transformers

FROM python:3.9-slim

ARG NAME
ARG NLP_CONF_FILE=presidio_analyzer/conf/transformers.yaml
ARG ANALYZER_CONF_FILE=presidio_analyzer/conf/default_analyzer.yaml
ARG RECOGNIZER_REGISTRY_CONF_FILE=presidio_analyzer/conf/default_recognizers.yaml
ENV PIP_NO_CACHE_DIR=1
WORKDIR /usr/bin/${NAME}

ENV ANALYZER_CONF_FILE=${ANALYZER_CONF_FILE}
ENV RECOGNIZER_REGISTRY_CONF_FILE=${RECOGNIZER_REGISTRY_CONF_FILE}
ENV NLP_CONF_FILE=${NLP_CONF_FILE}

COPY ${ANALYZER_CONF_FILE} /usr/bin/${NAME}/${ANALYZER_CONF_FILE}
COPY ${RECOGNIZER_REGISTRY_CONF_FILE} /usr/bin/${NAME}/${RECOGNIZER_REGISTRY_CONF_FILE}
COPY ${NLP_CONF_FILE} /usr/bin/${NAME}/${NLP_CONF_FILE}

COPY ./pyproject.toml /usr/bin/${NAME}/
COPY ./README.md /usr/bin/${NAME}/
RUN pip install poetry && poetry install -E server -E transformers

RUN poetry add torch transformers huggingface_hub --no-lock

# install nlp models specified in NLP_CONF_FILE
COPY ./install_nlp_models.py /usr/bin/${NAME}/

RUN poetry run python install_nlp_models.py --conf_file ${NLP_CONF_FILE}

COPY . /usr/bin/${NAME}/
EXPOSE ${PORT}
CMD poetry run python app.py --host 0.0.0.0