mirror of
https://github.com/deepset-ai/haystack.git
synced 2026-01-20 19:16:39 +00:00
091711b8c4
* Remove caching and install audio deps * Fix `Tutorials` as well * Run all tutorials even though some fail * Forgot fi * fix failure condition * proper bash string equality * Enable debug logs * remove audio files * Update Documentation & Code Style * Use the setup action in the Tutorial CI as well * Try with a file that exists * Update Documentation & Code Style * Fix the comments in the tutorials * Update Documentation & Code Style * Fix tutorials.sh * Remove debug logging * import pprint and try editable install * Update Documentation & Code Style * extract no run list * Add tutorial18 to no run list nightly * import pprint correctly * Update Documentation & Code Style * try making site-packages editable * Make pythonpath editable every time Tut17 is run on CI * typo * fix imports in tut5 * add git clean * Update Documentation & Code Style * add comments and remove` -e` * accidentally deleted a line * Update .github/utils/tutorials.sh Co-authored-by: Massimiliano Pippi <mpippi@gmail.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
75 lines
2.6 KiB
YAML
75 lines
2.6 KiB
YAML
name: Tutorials
|
|
|
|
on:
|
|
workflow_dispatch: # Activate this workflow manually
|
|
pull_request:
|
|
paths:
|
|
- 'tutorials/*.*'
|
|
|
|
|
|
env:
|
|
# Tutorials that require a GPU to run, so can't be run on CI without self-hosted runners
|
|
DONT_RUN: Tutorial2_ Tutorial9_ Tutorial13_ Tutorial18_
|
|
|
|
|
|
jobs:
|
|
|
|
run:
|
|
runs-on: ubuntu-latest
|
|
|
|
steps:
|
|
- uses: actions/checkout@v2
|
|
|
|
- name: Setup Python
|
|
uses: ./.github/actions/python_cache/
|
|
|
|
- name: Run Elasticsearch
|
|
run: docker run -d -p 9200:9200 -e "discovery.type=single-node" -e "ES_JAVA_OPTS=-Xms128m -Xmx256m" elasticsearch:7.9.2
|
|
|
|
- name: Run Apache Tika
|
|
run: docker run -d -p 9998:9998 -e "TIKA_CHILD_JAVA_OPTS=-JXms128m" -e "TIKA_CHILD_JAVA_OPTS=-JXmx128m" apache/tika:1.24.1
|
|
|
|
- name: Run GraphDB
|
|
run: docker run -d -p 7200:7200 --name graphdb-instance-tutorial docker-registry.ontotext.com/graphdb-free:9.4.1-adoptopenjdk11
|
|
|
|
- name: Install pdftotext
|
|
run: wget --no-check-certificate https://dl.xpdfreader.com/xpdf-tools-linux-4.04.tar.gz && tar -xvf xpdf-tools-linux-4.04.tar.gz && sudo cp xpdf-tools-linux-4.04/bin64/pdftotext /usr/local/bin
|
|
|
|
# Some tutorials require these libraries to run
|
|
# - Tutorial 17 for the audio libs
|
|
# - Tutorial 11, 14, 15, 16 for pygraphviz
|
|
- name: Install graphviz and audio libs
|
|
run: sudo apt install libgraphviz-dev graphviz libsndfile1 ffmpeg
|
|
|
|
# Some tutorials require these libraries to run
|
|
# - Tutorial 15
|
|
- name: Install torch-scatter
|
|
run: pip install torch-scatter -f https://data.pyg.org/whl/torch-1.12.0+cpu.html
|
|
|
|
# Haystack needs to be reinstalled at this stage to make sure the current commit's version is the one getting tested.
|
|
# The cache can last way longer than a specific action's run, so older Haystack version could be carried over.
|
|
- name: Reinstall Haystack
|
|
run: |
|
|
pip install --upgrade pip
|
|
pip install .[all]
|
|
pip install pygraphviz
|
|
pip install ipython nbformat
|
|
|
|
- name: Cache mini GoT dataset
|
|
run: |
|
|
mkdir -p data/tutorials
|
|
cd data/tutorials
|
|
wget https://s3.eu-central-1.amazonaws.com/deepset.ai-farm-qa/datasets/documents/wiki_gameofthrones_txt1_mini.zip -q &> /dev/null
|
|
unzip wiki_gameofthrones_txt1_mini.zip
|
|
rm wiki_gameofthrones_txt1_mini.zip
|
|
|
|
- uses: jitterbit/get-changed-files@v1
|
|
id: diff
|
|
continue-on-error: true
|
|
with:
|
|
format: space-delimited
|
|
token: ${{ secrets.GITHUB_TOKEN }}
|
|
|
|
- name: Run tutorials
|
|
run: ./.github/utils/tutorials.sh ${{ env.pythonLocation }} "${{ steps.diff.outputs.added_modified }}" "${{ env.DONT_RUN }}" "EDITABLE"
|