Merge pull request #3284 from vespa-engine/kkraune/linkcheck #2466
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Vespa Documentation Search Feed | |
| on: | |
| push: | |
| branches: [ master ] | |
| env: | |
| DATA_PLANE_PUBLIC_KEY : ${{ secrets.VESPA_TEAM_DATA_PLANE_PUBLIC_CERT }} | |
| DATA_PLANE_PRIVATE_KEY : ${{ secrets.VESPA_TEAM_DATA_PLANE_PRIVATE_KEY }} | |
| VESPA_CLI_DATA_PLANE_CERT : ${{ secrets.VESPA_TEAM_VESPA_CLI_DATA_PLANE_CERT }} | |
| VESPA_CLI_DATA_PLANE_KEY : ${{ secrets.VESPA_TEAM_VESPA_CLI_DATA_PLANE_KEY }} | |
| jobs: | |
| build: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: ruby/setup-ruby@v1 | |
| with: | |
| ruby-version: 3.1 | |
| bundler-cache: false | |
| - name: Build site | |
| run: | | |
| bundle install | |
| bundle exec jekyll build -p _plugins-vespafeed | |
| - name: Setup Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.x' | |
| - name: Install dependencies | |
| run: | | |
| pip3 install PyYAML mmh3 requests html5lib beautifulsoup4 markdownify tiktoken | |
| - name: Get Vespa CLI - update to later versions as needed | |
| run: | | |
| apt update && apt -y install curl | |
| curl -SsLo vespa-cli.tar.gz https://github.com/vespa-engine/vespa/releases/download/v8.209.11/vespa-cli_8.209.11_linux_amd64.tar.gz | |
| tar -xvf vespa-cli.tar.gz && ln -fs vespa-cli_8.209.11_linux_amd64/bin/vespa | |
| - name: Feed docs site | |
| run: | | |
| # The python scripts below uses the Vespa CLI for feeding / data access. | |
| # See https://docs.vespa.ai/en/vespa-cli.html. | |
| # The environment variables below have credentials for endpoint access - | |
| # use the key/cert files in .vespa and paste their content into GitHub Secrets. | |
| # VESPA_CLI_API_KEY must be set and empty as below. | |
| export VESPA_CLI_DATA_PLANE_CERT | |
| export VESPA_CLI_DATA_PLANE_KEY | |
| export VESPA_CLI_API_KEY= | |
| ./feed_to_vespa.py _config.yml | |
| - name: Feed paragraphs site | |
| run: | | |
| export VESPA_CLI_DATA_PLANE_CERT | |
| export VESPA_CLI_DATA_PLANE_KEY | |
| export VESPA_CLI_API_KEY= | |
| ./feed-split.py open_index.json https://docs.vespa.ai questions.jsonl | |
| ./feed_to_vespa.py _paragraphs_config.yml | |
| - name: Feed suggestions | |
| run: | | |
| export VESPA_CLI_DATA_PLANE_CERT | |
| export VESPA_CLI_DATA_PLANE_KEY | |
| export VESPA_CLI_API_KEY= | |
| ./feed_to_vespa.py _suggestions_config.yml | |
| - name: Generate and feed reference suggestions | |
| run: | | |
| ./generate_suggestions_from_reference.py en/reference/schema-reference.html https://docs.vespa.ai/ open-p > suggestions.jsonl | |
| ./generate_suggestions_from_reference.py en/reference/services-admin.html https://docs.vespa.ai/ open-p >> suggestions.jsonl | |
| ./generate_suggestions_from_reference.py en/reference/services-container.html https://docs.vespa.ai/ open-p >> suggestions.jsonl | |
| ./generate_suggestions_from_reference.py en/reference/services-docproc.html https://docs.vespa.ai/ open-p >> suggestions.jsonl | |
| ./generate_suggestions_from_reference.py en/reference/services-processing.html https://docs.vespa.ai/ open-p >> suggestions.jsonl | |
| ./generate_suggestions_from_reference.py en/reference/services-search.html https://docs.vespa.ai/ open-p >> suggestions.jsonl | |
| ./generate_suggestions_from_reference.py en/reference/services-http.html https://docs.vespa.ai/ open-p >> suggestions.jsonl | |
| ./generate_suggestions_from_reference.py en/reference/services-content.html https://docs.vespa.ai/ open-p >> suggestions.jsonl | |
| ./convert.py suggestions.jsonl suggestions_reference_index.json | |
| ./feed_to_vespa.py _suggestions_reference_config.yml |