| name: Weekly ACL Anthology sync | |
| on: | |
| schedule: | |
| - cron: "0 3 * * 1" # every Monday 03:00 UTC | |
| workflow_dispatch: {} | |
| jobs: | |
| sync: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.11" | |
| - name: Install dependencies | |
| run: pip install -e . | |
| - name: Checkout acl-anthology data | |
| run: git clone --depth 1 https://github.com/acl-org/acl-anthology.git ./anthology-data | |
| - name: Run sync | |
| env: | |
| ANTHOLOGY_PATH: ./anthology-data | |
| HF_REPO_ID: ${{ secrets.HF_REPO_ID }} | |
| HF_TOKEN: ${{ secrets.HF_TOKEN }} | |
| EMBEDDING_BASE_URL: ${{ secrets.EMBEDDING_BASE_URL }} | |
| EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }} | |
| run: python -m sync.run_sync | |
| - name: Restart HF Space to pick up fresh snapshot | |
| env: | |
| HF_TOKEN: ${{ secrets.HF_TOKEN }} | |
| HF_SPACE_ID: ${{ secrets.HF_SPACE_ID }} | |
| run: | | |
| curl -X POST \ | |
| -H "Authorization: Bearer $HF_TOKEN" \ | |
| "https://huggingface.co/api/spaces/$HF_SPACE_ID/restart" | |