Skip to content

Reset OCR engine to tesseract #91

Reset OCR engine to tesseract

Reset OCR engine to tesseract #91

Workflow file for this run

name: Compile KFP pipelines
on:
pull_request:
types: [opened, synchronize, reopened]
paths:
- "kubeflow-pipelines/docling-standard/**"
- "kubeflow-pipelines/docling-vlm/**"
- "kubeflow-pipelines/common/**"
- ".github/workflows/compile-kfp.yml"
push:
branches: [ main ]
paths:
- "kubeflow-pipelines/docling-standard/**"
- "kubeflow-pipelines/docling-vlm/**"
- "kubeflow-pipelines/common/**"
- ".github/workflows/compile-kfp.yml"
permissions:
contents: read
jobs:
compile:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
include:
- name: docling-standard
dir: kubeflow-pipelines/docling-standard
cmd: python standard_convert_pipeline.py
out: standard_convert_pipeline_compiled.yaml
- name: docling-vlm
dir: kubeflow-pipelines/docling-vlm
cmd: python vlm_convert_pipeline.py
out: vlm_convert_pipeline_compiled.yaml
steps:
- name: Checkout
uses: actions/checkout@v6
- name: Set up Python 3.12
uses: actions/setup-python@v6
with:
python-version: "3.12"
- name: Install requirements for ${{ matrix.name }}
working-directory: ${{ matrix.dir }}
run: |
python -m pip install --upgrade pip
pip install -r requirements.txt
- name: Compile and compare (${{ matrix.name }})
run: |
set -ux
BASE="${{ matrix.dir }}/${{ matrix.out }}"
SNAP="${BASE}.baseline"
# Snapshot committed YAML in-place using mv, or create an empty baseline
if [ -f "$BASE" ]; then
mv "$BASE" "$SNAP"
else
: > "$SNAP"
fi
# Compile (regenerates $BASE)
( cd "${{ matrix.dir }}" && ${{ matrix.cmd }} )
# Ensure compiled YAML exists and is non-empty
test -s "$BASE"
echo "Comparing compiled pipeline YAML to the committed version..."
echo "If this fails, you changed pipeline code but did not regenerate/commit the compiled YAML."
echo "To fix locally: (cd ${{ matrix.dir }} && ${{ matrix.cmd }}) and commit ${{ matrix.out }}."
diff "$BASE" "$SNAP"