Docling-UI / Containerfile
Michele Dolfi
chore: extend timeout for downloading the model artifacts (#90)
2847b94 unverified
raw
history blame
2.72 kB
ARG BASE_IMAGE=quay.io/sclorg/python-312-c9s:c9s
FROM ${BASE_IMAGE}
ARG MODELS_LIST="layout tableformer picture_classifier easyocr" \
UV_SYNC_EXTRA_ARGS=""
USER 0
###################################################################################################
# OS Layer #
###################################################################################################
RUN --mount=type=bind,source=os-packages.txt,target=/tmp/os-packages.txt \
dnf -y install --best --nodocs --setopt=install_weak_deps=False dnf-plugins-core && \
dnf config-manager --best --nodocs --setopt=install_weak_deps=False --save && \
dnf config-manager --enable crb && \
dnf -y update && \
dnf install -y $(cat /tmp/os-packages.txt) && \
dnf -y clean all && \
rm -rf /var/cache/dnf
ENV TESSDATA_PREFIX=/usr/share/tesseract/tessdata/
###################################################################################################
# Docling layer #
###################################################################################################
USER 1001
WORKDIR /opt/app-root/src
ENV \
# On container environments, always set a thread budget to avoid undesired thread congestion.
OMP_NUM_THREADS=4 \
LANG=en_US.UTF-8 \
LC_ALL=en_US.UTF-8 \
PYTHONIOENCODING=utf-8 \
UV_COMPILE_BYTECODE=1 \
UV_LINK_MODE=copy \
UV_PROJECT_ENVIRONMENT=/opt/app-root \
DOCLING_SERVE_ARTIFACTS_PATH=/opt/app-root/src/.cache/docling/models
RUN --mount=from=ghcr.io/astral-sh/uv:0.6.1,source=/uv,target=/bin/uv \
--mount=type=cache,target=/opt/app-root/src/.cache/uv,uid=1001 \
--mount=type=bind,source=uv.lock,target=uv.lock \
--mount=type=bind,source=pyproject.toml,target=pyproject.toml \
uv sync --frozen --no-install-project --no-dev --all-extras ${UV_SYNC_EXTRA_ARGS}
RUN echo "Downloading models..." && \
HF_HUB_DOWNLOAD_TIMEOUT="90" \
HF_HUB_ETAG_TIMEOUT="90" \
docling-tools models download -o "${DOCLING_SERVE_ARTIFACTS_PATH}" ${MODELS_LIST} && \
chown -R 1001:0 /opt/app-root/src/.cache && \
chmod -R g=u /opt/app-root/src/.cache
COPY --chown=1001:0 ./docling_serve ./docling_serve
RUN --mount=from=ghcr.io/astral-sh/uv:0.6.1,source=/uv,target=/bin/uv \
--mount=type=cache,target=/opt/app-root/src/.cache/uv,uid=1001 \
--mount=type=bind,source=uv.lock,target=uv.lock \
--mount=type=bind,source=pyproject.toml,target=pyproject.toml \
uv sync --frozen --no-dev --all-extras ${UV_SYNC_EXTRA_ARGS}
EXPOSE 5001
CMD ["docling-serve", "run"]