mirror of
https://github.com/docling-project/docling-serve.git
synced 2025-12-03 02:23:19 +00:00
c6539c42de
* api v1alpha1 Signed-off-by: Guillaume Moutier <gmoutier@redhat.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * use actual types in request models and refactor Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * make gradio optional and update README Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * Run workflow jobs sequentially to avoid disk space outage (#19) Github Action runners are running out of the space while building both the images in parallel. This change will build the image sequentially and also clean up the cpu images before start building gpu image. Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * Add github job to build image (and not publish) on PR creation (#20) Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add start_server script for local dev Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * fix 3.12-only syntax Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * fix more py3.10-11 compatibility Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * rework output format and background tasks Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * speficy return schemas for openapi Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add processing time and update REDAME Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * lint markdown Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add MD033 to config Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * use port 5000 Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * use port 5001 as default Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update deps Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * refactor input request Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * return docling document Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * update new payload in README Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add base64 example Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * wrap example in <details> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * rename /url in /source Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * move main execution to __main__ Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: Guillaume Moutier <gmoutier@redhat.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Anil Vishnoi <vishnoianil@gmail.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Anil Vishnoi <vishnoianil@gmail.com>
62 lines
2.2 KiB
Docker
62 lines
2.2 KiB
Docker
ARG BASE_IMAGE=quay.io/sclorg/python-312-c9s:c9s
|
|
|
|
FROM ${BASE_IMAGE}
|
|
|
|
ARG CPU_ONLY=false
|
|
|
|
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 $(cat /tmp/os-packages.txt) && \
|
|
dnf -y clean all && \
|
|
rm -rf /var/cache/dnf
|
|
|
|
ENV TESSDATA_PREFIX=/usr/share/tesseract/tessdata/
|
|
|
|
###################################################################################################
|
|
# Docling layer #
|
|
###################################################################################################
|
|
|
|
USER 1001
|
|
|
|
WORKDIR /opt/app-root/src
|
|
|
|
# On container environments, always set a thread budget to avoid undesired thread congestion.
|
|
ENV OMP_NUM_THREADS=4
|
|
|
|
ENV LANG=en_US.UTF-8
|
|
ENV LC_ALL=en_US.UTF-8
|
|
ENV PYTHONIOENCODING=utf-8
|
|
|
|
ENV WITH_UI=True
|
|
|
|
COPY --chown=1001:0 pyproject.toml poetry.lock models_download.py README.md ./
|
|
|
|
RUN pip install --no-cache-dir poetry && \
|
|
# We already are in a virtual environment, so we don't need to create a new one, only activate it.
|
|
poetry config virtualenvs.create false && \
|
|
source /opt/app-root/bin/activate && \
|
|
if [ "$CPU_ONLY" = "true" ]; then \
|
|
poetry install --no-root --no-cache --no-interaction --all-extras --with cpu --without dev; \
|
|
else \
|
|
poetry install --no-root --no-cache --no-interaction --all-extras --without dev; \
|
|
fi && \
|
|
echo "Downloading models..." && \
|
|
python models_download.py && \
|
|
chown -R 1001:0 /opt/app-root/src && \
|
|
chmod -R g=u /opt/app-root/src
|
|
|
|
COPY --chown=1001:0 --chmod=664 ./docling_serve ./docling_serve
|
|
|
|
EXPOSE 5001
|
|
|
|
CMD ["python", "-m", "docling_serve"]
|