Docling/.github/workflows/checks.yml
Nikos Livathinos 6d3fea0196
docs: Introduce example with custom models for RapidOCR (#874)
* docs: Introduce example with custom models for RapidOCR

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

* chore: Exclude the example with custom RapidOCR models from the examples to run in github actions

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>

---------

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
2025-02-04 10:07:00 +01:00

41 lines
1.4 KiB
YAML

on:
workflow_call:
jobs:
run-checks:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ['3.9', '3.10', '3.11', '3.12', '3.13']
steps:
- uses: actions/checkout@v4
- name: Install tesseract
run: sudo apt-get update && sudo apt-get install -y tesseract-ocr tesseract-ocr-eng tesseract-ocr-fra tesseract-ocr-deu tesseract-ocr-spa tesseract-ocr-script-latn libleptonica-dev libtesseract-dev pkg-config
- name: Set TESSDATA_PREFIX
run: |
echo "TESSDATA_PREFIX=$(dpkg -L tesseract-ocr-eng | grep tessdata$)" >> "$GITHUB_ENV"
- uses: ./.github/actions/setup-poetry
with:
python-version: ${{ matrix.python-version }}
- name: Run styling check
run: poetry run pre-commit run --all-files
- name: Install with poetry
run: poetry install --all-extras
- name: Testing
run: |
poetry run pytest -v tests
- name: Run examples
run: |
for file in docs/examples/*.py; do
# Skip batch_convert.py
if [[ "$(basename "$file")" =~ ^(batch_convert|minimal|export_multimodal|custom_convert|develop_picture_enrichment|rapidocr_with_custom_models).py ]]; then
echo "Skipping $file"
continue
fi
echo "Running example $file"
poetry run python "$file" || exit 1
done
- name: Build with poetry
run: poetry build