mirror of
https://github.com/QuivrHQ/quivr.git
synced 2024-12-15 01:21:48 +03:00
56 lines
1.3 KiB
Docker
56 lines
1.3 KiB
Docker
|
FROM python:3.11.6-slim-bullseye AS BUILDER
|
||
|
|
|
||
|
|
ARG DEV_MODE
|
||
|
|
ENV DEV_MODE=$DEV_MODE
|
||
|
|
|
||
|
|
# Install GEOS library, Rust, and other dependencies, then clean up
|
||
|
|
RUN apt-get clean && apt-get update && apt-get install -y \
|
||
|
|
libgeos-dev \
|
||
|
|
libcurl4-openssl-dev \
|
||
|
|
libssl-dev \
|
||
|
|
binutils \
|
||
|
|
curl \
|
||
|
|
git \
|
||
|
|
gcc \
|
||
|
|
autoconf \
|
||
|
|
automake \
|
||
|
|
build-essential \
|
||
|
|
libtool \
|
||
|
|
python-dev \
|
||
|
|
wget \
|
||
|
|
# Additional dependencies for document handling
|
||
|
|
libmagic-dev \
|
||
|
|
tesseract-ocr \
|
||
|
|
poppler-utils \
|
||
|
|
tesseract-ocr \
|
||
|
|
libreoffice \
|
||
|
|
libpq-dev \
|
||
|
|
pandoc && \
|
||
|
|
rm -rf /var/lib/apt/lists/*
|
||
|
|
|
||
|
|
RUN curl -sSL https://install.python-poetry.org | POETRY_HOME=/opt/poetry python && \
|
||
|
|
cd /usr/local/bin && \
|
||
|
|
ln -s /opt/poetry/bin/poetry && \
|
||
|
|
poetry config virtualenvs.create false
|
||
|
|
|
||
|
|
WORKDIR /code/worker
|
||
|
|
# Add Rust binaries to the PATH
|
||
|
|
ENV PATH="/root/.cargo/bin:${PATH}" \
|
||
|
|
POETRY_CACHE_DIR=/tmp/poetry_cache \
|
||
|
|
PYTHONDONTWRITEBYTECODE=1 \
|
||
|
|
POETRY_VIRTUALENVS_PATH=/code/worker/.venv-docker
|
||
|
|
|
||
|
|
COPY . /code/
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# Cache playwright dependency
|
||
|
|
RUN poetry run pip install playwright && playwright install --with-deps
|
||
|
|
|
||
|
|
# Run install
|
||
|
|
RUN poetry install && rm -rf $POETRY_CACHE_DIR
|
||
|
|
|
||
|
|
RUN poetry run python -c "from unstructured.nlp.tokenize import download_nltk_packages; download_nltk_packages()"
|
||
|
|
|
||
|
|
ENV PYTHONPATH=/code/worker
|