mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-06-10 15:25:14 +02:00
6b1dd16f9f
- Paginate heavy Cassandra reads (triples, graph/document embeddings) using synchronous session.execute() in run_in_executor with fetch_size paging, preventing materialization hang on large result sets - Fix document stream endpoint to use workspace-scoped librarian queues - Add decoder error handling for PDF/OCR/unstructured processors - Add WebSocket mux guards for missing auth fields - Add null check in librarian document streaming - Rewrite get_document_content CLI to stream via librarian - Add Poppler dependency to unstructured container
54 lines
2 KiB
Text
54 lines
2 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 poppler-utils && \
|
|
alternatives --install /usr/bin/python python /usr/bin/python3.13 1 && \
|
|
python -m ensurepip --upgrade && \
|
|
pip3 install --no-cache-dir --upgrade 'pip>=26.0' 'setuptools>=78.1.1' && \
|
|
pip3 install --no-cache-dir build wheel aiohttp && \
|
|
pip3 install --no-cache-dir pulsar-client==3.11.0 && \
|
|
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 /
|