trustgraph/Makefile
cybermaggedon bdfdbb3c1f
feat: add Docling-based document decoder as alternative to unstructured (#1054)
Add trustgraph-docling package providing a document decoder powered by
IBM's Docling library. Supports PDF, DOCX, XLSX, PPTX, HTML, Markdown,
and CSV with two chunking modes:

- page mode (default): groups output by page for page-based formats,
  emits TextDocument messages for the existing downstream chunker
- hybrid mode: uses Docling's HybridChunker for structure-aware
  semantic chunking, emits Chunk messages directly

Tables are preserved as HTML markup. Images are stored in the librarian
with provenance but excluded from the text pipeline. Full provenance
chain is maintained for explainability tracing.

Includes Containerfile, CI/CD integration (PR checks and release
workflows), Makefile targets, and tech spec documentation.

Added unit tests for the package.
2026-07-20 21:25:33 +01:00

142 lines
5.8 KiB
Makefile

# VERSION=$(shell git describe | sed 's/^v//')
VERSION=0.0.0
DOCKER=podman
all: containers
# Not used
wheels:
pip3 wheel --no-deps --wheel-dir dist trustgraph/
pip3 wheel --no-deps --wheel-dir dist trustgraph-base/
pip3 wheel --no-deps --wheel-dir dist trustgraph-flow/
pip3 wheel --no-deps --wheel-dir dist trustgraph-vertexai/
pip3 wheel --no-deps --wheel-dir dist trustgraph-bedrock/
pip3 wheel --no-deps --wheel-dir dist trustgraph-embeddings-hf/
pip3 wheel --no-deps --wheel-dir dist trustgraph-cli/
pip3 wheel --no-deps --wheel-dir dist trustgraph-ocr/
pip3 wheel --no-deps --wheel-dir dist trustgraph-unstructured/
pip3 wheel --no-deps --wheel-dir dist trustgraph-docling/
pip3 wheel --no-deps --wheel-dir dist trustgraph-mcp/
packages: update-package-versions
rm -rf dist/
cd trustgraph && python -m build --sdist --outdir ../dist/
cd trustgraph-base && python -m build --sdist --outdir ../dist/
cd trustgraph-flow && python -m build --sdist --outdir ../dist/
cd trustgraph-vertexai && python -m build --sdist --outdir ../dist/
cd trustgraph-bedrock && python -m build --sdist --outdir ../dist/
cd trustgraph-embeddings-hf && python -m build --sdist --outdir ../dist/
cd trustgraph-cli && python -m build --sdist --outdir ../dist/
cd trustgraph-ocr && python -m build --sdist --outdir ../dist/
cd trustgraph-unstructured && python -m build --sdist --outdir ../dist/
cd trustgraph-docling && python -m build --sdist --outdir ../dist/
cd trustgraph-mcp && python -m build --sdist --outdir ../dist/
pypi-upload:
twine upload dist/*-${VERSION}.*
CONTAINER_BASE=docker.io/trustgraph
update-package-versions:
mkdir -p trustgraph-cli/trustgraph
mkdir -p trustgraph/trustgraph
echo __version__ = \"${VERSION}\" > trustgraph-base/trustgraph/base_version.py
echo __version__ = \"${VERSION}\" > trustgraph-flow/trustgraph/flow_version.py
echo __version__ = \"${VERSION}\" > trustgraph-vertexai/trustgraph/vertexai_version.py
echo __version__ = \"${VERSION}\" > trustgraph-bedrock/trustgraph/bedrock_version.py
echo __version__ = \"${VERSION}\" > trustgraph-embeddings-hf/trustgraph/embeddings_hf_version.py
echo __version__ = \"${VERSION}\" > trustgraph-cli/trustgraph/cli_version.py
echo __version__ = \"${VERSION}\" > trustgraph-ocr/trustgraph/ocr_version.py
echo __version__ = \"${VERSION}\" > trustgraph-unstructured/trustgraph/unstructured_version.py
echo __version__ = \"${VERSION}\" > trustgraph-docling/trustgraph/docling_version.py
echo __version__ = \"${VERSION}\" > trustgraph/trustgraph/trustgraph_version.py
echo __version__ = \"${VERSION}\" > trustgraph-mcp/trustgraph/mcp_version.py
containers: container-base container-flow \
container-bedrock container-vertexai \
container-hf container-ocr \
container-unstructured container-docling container-mcp
some-containers: container-base container-flow
# container-unstructured
push:
${DOCKER} push ${CONTAINER_BASE}/trustgraph-base:${VERSION}
${DOCKER} push ${CONTAINER_BASE}/trustgraph-flow:${VERSION}
${DOCKER} push ${CONTAINER_BASE}/trustgraph-bedrock:${VERSION}
${DOCKER} push ${CONTAINER_BASE}/trustgraph-vertexai:${VERSION}
${DOCKER} push ${CONTAINER_BASE}/trustgraph-hf:${VERSION}
${DOCKER} push ${CONTAINER_BASE}/trustgraph-ocr:${VERSION}
${DOCKER} push ${CONTAINER_BASE}/trustgraph-unstructured:${VERSION}
${DOCKER} push ${CONTAINER_BASE}/trustgraph-docling:${VERSION}
${DOCKER} push ${CONTAINER_BASE}/trustgraph-mcp:${VERSION}
# Individual container build targets
container-%: update-package-versions
${DOCKER} build \
-f containers/Containerfile.${@:container-%=%} \
-t ${CONTAINER_BASE}/trustgraph-${@:container-%=%}:${VERSION} .
# Multi-arch: build both platforms sequentially into one manifest (local use)
manifest-%: update-package-versions
-@${DOCKER} manifest rm \
${CONTAINER_BASE}/trustgraph-${@:manifest-%=%}:${VERSION}
${DOCKER} build --platform linux/amd64,linux/arm64 \
-f containers/Containerfile.${@:manifest-%=%} \
--manifest \
${CONTAINER_BASE}/trustgraph-${@:manifest-%=%}:${VERSION} .
# Multi-arch: build a single platform image (for parallel CI)
platform-%-amd64: update-package-versions
${DOCKER} build --platform linux/amd64 \
-f containers/Containerfile.${@:platform-%-amd64=%} \
-t ${CONTAINER_BASE}/trustgraph-${@:platform-%-amd64=%}:${VERSION}-amd64 .
platform-%-arm64: update-package-versions
${DOCKER} build --platform linux/arm64 \
-f containers/Containerfile.${@:platform-%-arm64=%} \
-t ${CONTAINER_BASE}/trustgraph-${@:platform-%-arm64=%}:${VERSION}-arm64 .
# Push a single platform image
push-platform-%-amd64:
${DOCKER} push \
${CONTAINER_BASE}/trustgraph-${@:push-platform-%-amd64=%}:${VERSION}-amd64
push-platform-%-arm64:
${DOCKER} push \
${CONTAINER_BASE}/trustgraph-${@:push-platform-%-arm64=%}:${VERSION}-arm64
# Combine per-platform images into a multi-arch manifest
combine-manifest-%:
-@${DOCKER} manifest rm \
${CONTAINER_BASE}/trustgraph-${@:combine-manifest-%=%}:${VERSION}
${DOCKER} manifest create \
${CONTAINER_BASE}/trustgraph-${@:combine-manifest-%=%}:${VERSION} \
docker://${CONTAINER_BASE}/trustgraph-${@:combine-manifest-%=%}:${VERSION}-amd64 \
docker://${CONTAINER_BASE}/trustgraph-${@:combine-manifest-%=%}:${VERSION}-arm64
${DOCKER} manifest push \
${CONTAINER_BASE}/trustgraph-${@:combine-manifest-%=%}:${VERSION}
# Push a container
push-container-%:
${DOCKER} push \
${CONTAINER_BASE}/trustgraph-${@:push-container-%=%}:${VERSION}
# Push a manifest (from local multi-arch build)
push-manifest-%:
${DOCKER} manifest push \
${CONTAINER_BASE}/trustgraph-${@:push-manifest-%=%}:${VERSION}
clean:
rm -rf wheels/
set-version:
echo '"${VERSION}"' > templates/values/version.jsonnet
docker-hub-login:
cat docker-token.txt | \
${DOCKER} login -u trustgraph --password-stdin registry-1.docker.io