trustgraph/containers/Containerfile.unstructured
cybermaggedon 413f917676 Add missing pdf extra to unstructured dependency (#728)
* Fix PDF processing deps so that PDF processing works
2026-03-29 20:22:45 +01:00

53 lines
1.9 KiB
Text

# ----------------------------------------------------------------------------
# Base container with system dependencies
# ----------------------------------------------------------------------------
FROM docker.io/fedora:42 AS base
ENV PIP_BREAK_SYSTEM_PACKAGES=1
RUN dnf install -y python3.13 libxcb mesa-libGL && \
alternatives --install /usr/bin/python python /usr/bin/python3.13 1 && \
python -m ensurepip --upgrade && \
pip3 install --no-cache-dir build wheel aiohttp && \
pip3 install --no-cache-dir pulsar-client==3.7.0 && \
dnf clean all
# ----------------------------------------------------------------------------
# Build a container which contains the built Python packages. The build
# creates a bunch of left-over cruft, a separate phase means this is only
# needed to support package build
# ----------------------------------------------------------------------------
FROM base AS build
COPY trustgraph-base/ /root/build/trustgraph-base/
COPY trustgraph-unstructured/ /root/build/trustgraph-unstructured/
WORKDIR /root/build/
RUN pip3 wheel -w /root/wheels/ --no-deps ./trustgraph-base/
RUN pip3 wheel -w /root/wheels/ --no-deps ./trustgraph-unstructured/
RUN ls /root/wheels
# ----------------------------------------------------------------------------
# Finally, the target container. Start with base and add the package.
# ----------------------------------------------------------------------------
FROM base
# Pre-install CPU-only PyTorch so that unstructured[pdf]'s torch
# dependency is satisfied without pulling in CUDA (~190MB vs ~2GB+)
RUN pip3 install --no-cache-dir torch==2.11.0+cpu \
--index-url https://download.pytorch.org/whl/cpu
COPY --from=build /root/wheels /root/wheels
RUN \
pip3 install --no-cache-dir /root/wheels/trustgraph_base-* && \
pip3 install --no-cache-dir /root/wheels/trustgraph_unstructured-* && \
rm -rf /root/wheels
WORKDIR /