Add telemetry to github actions [skip-test]

.github/workflows/create_search_index.yml

@@ -4,14 +4,18 @@ on:
   push:
     branches:
       - master
+  pull_request:
+    branches:
+      - master
 
 concurrency:
   # Make sure only workflow run at a time for create_search_index.yml
   group: ${{ github.workflow }}
 
 jobs:
   jekyll:
-    runs-on: ubuntu-latest
+    runs-on: self-hosted
+    timeout-minutes: 600
     environment: jekyll
     steps:
       - uses: actions/checkout@v2
@@ -41,21 +45,10 @@ jobs:
           && mv _site/backup-benchmarking.json ./
           && mv _site/backup-references.json ./)
           || true
-      - name: Incremental build
-        id: incremental-build
-        env:
-          ELASTICSEARCH_URL: ${{ secrets.ELASTICSEARCH_URL }}
-          ELASTICSEARCH_ACCESS_TOKEN: ${{ secrets.ELASTICSEARCH_ACCESS_TOKEN }}
-          ELASTICSEARCH_INDEX_NAME: ${{ secrets.ELASTICSEARCH_INDEX_NAME }}
-          SEARCH_ORIGIN: ${{ secrets.SEARCH_ORIGIN }}
-          ORIGIN: ${{ secrets.ORIGIN }}
-        working-directory: docs
-        run: |
-          bundle exec jekyll build --incremental
-        continue-on-error: ${{ steps.incremental-build.outputs.require_full_build == 'true' }}
+      - name: Collect Workflow Telemetry
+        uses: catchpoint/workflow-telemetry-action@v2
       - name: Full build
         id: full-build
-        if: ${{ steps.incremental-build.outputs.require_full_build == 'true' }}
         env:
           ELASTICSEARCH_URL: ${{ secrets.ELASTICSEARCH_URL }}
           ELASTICSEARCH_ACCESS_TOKEN: ${{ secrets.ELASTICSEARCH_ACCESS_TOKEN }}
@@ -65,7 +58,7 @@ jobs:
         working-directory: docs
         run: |
           rm -f .jekyll-metadata
-          FULL_BUILD=1 bundle exec jekyll build --incremental
+          FULL_BUILD=1 bundle exec jekyll build --incremental --profile
       - uses: actions/setup-node@v3
         with:
           node-version: 16

docs/_config_local.yml

@@ -0,0 +1,235 @@
+# NOTE: This config is intended for local development only. It skips the generation of the model hub cards.
+# Run with bundle install; bundle exec jekyll serve --incremental --trace --config _config_local.yml
+#
+# Welcome to Jekyll!
+#
+# This config file is meant for settings that affect your whole blog, values
+# which you are expected to set up once and rarely need to edit after that.
+# For technical reasons, this file is *NOT* reloaded automatically when you use
+# 'jekyll serve'. If you change this file, please restart the server process.
+#
+# ,--------.      ,--.   ,--. ,--.
+# '--.  .--',---.  \  `.'  /,-'  '-.
+#    |  |  | .-. :  .'    \ '-.  .-'
+#    |  |  \   --. /  .'.  \  |  |
+#    `--'   `----''--'   '--' `--'
+
+## !USE TEXT THEME
+# theme: jekyll-text-theme # Gem-based Jekyll Themes
+remote_theme: kitian616/jekyll-TeXt-theme # Jekyll Remote Theme, see https://github.com/benbalter/jekyll-remote-theme for more information.
+
+## => Site Settings
+##############################
+text_skin: default # "default" (default), "dark", "forest", "ocean", "chocolate", "orange"
+highlight_theme: tomorrow-night-eighties # "default" (default), "tomorrow", "tomorrow-night", "tomorrow-night-eighties", "tomorrow-night-blue", "tomorrow-night-bright"
+url     : # the base hostname & protocol for your site e.g. https://www.someone.com
+baseurl : # does not include hostname
+title   : Spark NLP
+description: > # this means to ignore newlines until "Language & timezone"
+  High Performance NLP with Apache Spark
+
+
+## => Language and Timezone
+##############################
+lang: # the language of your site, default as "en"
+timezone: # see https://en.wikipedia.org/wiki/List_of_tz_database_time_zones for the available values
+
+
+## => Author and Social
+##############################
+author:
+  type      : # "person" (default), "organization"
+  name      :
+  url       :
+  avatar    : # path or url of avatar image (square)
+  bio       :
+  email     :
+  facebook  : # "user_name" the last part of your profile url, e.g. https://www.facebook.com/user_name
+  twitter   : # "user_name" the last part of your profile url, e.g. https://twitter.com/user_name
+  weibo     : # "user_id"   the last part of your profile url, e.g. https://www.weibo.com/user_id/profile?...
+  googleplus: # "user_id"   the last part of your profile url, e.g. https://plus.google.com/u/0/user_id
+  telegram  : # "user_name" the last part of your profile url, e.g. https://t.me/user_name
+  medium    : # "user_name" the last part of your profile url, e.g. https://medium.com/user_name
+  zhihu     : # "user_name" the last part of your profile url, e.g. https://www.zhihu.com/people/user_name
+  douban    : # "user_name" the last part of your profile url, e.g. https://www.douban.com/people/user_name
+  linkedin  : # "user_name" the last part of your profile url, e.g. https://www.linkedin.com/in/user_name
+  github    : # "user_name" the last part of your profile url, e.g. https://github.com/user_name
+  npm       : # "user_name" the last part of your profile url, e.g. https://www.npmjs.com/~user_name
+
+
+## => GitHub Repository (if the site is hosted by GitHub)
+##############################
+repository: johnsnowlabs/spark-nlp
+repository_tree: master/docs
+
+
+## => Paths
+##############################
+paths:
+  root    : # title link url, "/" (default)
+  home    : # home layout url, "/" (default)
+  archive : # "/archive.html" (default)
+  rss     : # "/feed.xml" (default)
+
+
+## => Post
+##############################
+## excerpt
+excerpt_separator: <!--more-->
+
+## license
+license: # "CC-BY-4.0", "CC-BY-SA-4.0", "CC-BY-NC-4.0", "CC-BY-ND-4.0"
+
+## TOC
+toc:
+  selectors: # "h1,h2,h3" (default)
+
+
+## => Markdown Enhancements
+##############################
+## Mathjax
+mathjax: false # false (default), true
+mathjax_autoNumber: false # false (default), true
+
+## Mermaid
+mermaid: false # false (default), true
+
+## Chart
+chart: false # false (default), true
+
+
+## => Paginate
+##############################
+paginate: 8
+paginate_path: /page:num # don't change this unless for special need
+
+
+## => Sources
+##############################
+sources: bootcdn # bootcdn (default), unpkg
+
+
+## => Sharing
+##############################
+sharing:
+  provider: false # false (default), "addtoany", "addthis", "custom"
+
+  ## AddThis
+  addthis:
+    id: # AddThis pubid, e.g. ra-5xxxxxxxxxxx
+
+
+## => Comments
+##############################
+comments:
+  provider: false # false (default), "disqus", "gitalk", "valine", "custom"
+
+  ## Disqus
+  disqus:
+    shortname: # the Disqus shortname for the site
+
+  ## Gitalk
+  # please refer to https://github.com/gitalk/gitalk for more info.
+  gitalk:
+    clientID    : # GitHub Application Client ID
+    clientSecret: # GitHub Application Client Secret
+    repository  : # GitHub repo
+    owner       : # GitHub repo owner
+    admin: # GitHub repo owner and collaborators, only these guys can initialize GitHub issues, IT IS A LIST.
+      # - your GitHub Id
+
+  ## Valine
+  # please refer to https://valine.js.org/en/ for more info.
+  valine:
+    app_id      : # LeanCloud App id
+    app_key     : # LeanCloud App key
+    placeholder : # Prompt information
+    visitor     : # false (default)
+    meta        : # "[nick, mail, link]" (default) nickname, E-mail, Personal-site
+
+
+## => Pageview
+##############################
+pageview:
+  provider: false # false (default), "leancloud", "custom"
+
+  ## Leancloud
+  leancloud:
+    app_id    : # LeanCloud App id
+    app_key   : # LeanCloud App key
+    app_class : # LeanCloud App class
+
+
+## => Search
+##############################
+search:
+  provider: false # "default" (default), false, "google", "custom"
+
+  ## Google Custom Search Engine
+  google:
+    custom_search_engine_id: 005514095864560561482:hupbermpchw # Google Custom Search Engine ID
+
+
+## => Analytics
+##############################
+## analytics:
+##  provider: "google" # false (default), "google", "custom"
+
+  ## Google Analytics
+##  google:
+ ##   tracking_id : UA-70312582-2 # Google Analytics id for the site
+ ##   anonymize_ip: false # Anonymize IP tracking for Analytics
+
+
+## => Build
+##############################
+markdown    : kramdown
+highlighter : rouge
+permalink   : date
+
+exclude:
+  - CHANGELOG.md
+  - HOW_TO_RELEASE.md
+  - Gemfile
+  - Gemfile.lock
+  - LICENSE
+  - README-*.md
+  - README.md
+  - gulpfile.js
+  - jekyll-text-theme.gemspec
+  - package-lock.json
+  - package.json
+  - /node_modules
+  - /screenshots
+  - /test
+  - /vendor
+  - backup-*.json
+  - /_frontend
+  - /_scripts
+  - /_posts
+
+defaults:
+  ## docs
+  - scope:
+      path: "en"
+    values:
+      layout: article
+      nav_key: docs
+      aside:
+        toc: true
+      license: false
+      demomenu: false
+      show_edit_on_github: true
+      show_date: true
+      header:
+        theme: light
+        background: "#ecf0f1"
+      # lightbox: true
+## => Plugins
+##############################
+plugins:
+  - jekyll-feed
+  - jekyll-paginate
+  - jekyll-sitemap
+  - jemoji
+  - jekyll-incremental

docs/_plugins/search_index.rb

@@ -578,9 +578,10 @@ def is_latest?(group, model)
     models_references_json = backup_references_data.merge(models_references_json)
   end
 
-  filename = File.join(site.config['destination'], 'models.json')
-  File.write(filename, models_json.values.to_json)
-  File.write(backup_filename, models_json.to_json)
+  # filename = File.join(site.config['destination'], 'models.json')
+  # Commenting so that the site builds
+  # File.write(filename, models_json.values.to_json)
+  # File.write(backup_filename, models_json.to_json)
 
   benchmarking_filename = File.join(site.config['destination'], 'benchmarking.json')
   File.write(benchmarking_filename, models_benchmarking_json.to_json)

docs/en/transformer_entries/JanusForMultiModal.md

@@ -17,6 +17,8 @@ val visualQA = JanusForMultiModal.pretrained()
   .setInputCols("image_assembler")
   .setOutputCol("answer")
 ```
+{%- endcapture -%}
+
 {%- capture input_anno -%}
 IMAGE
 {%- endcapture -%}

docs/en/transformer_entries/SmolVLMTransformer.md

@@ -16,6 +16,8 @@ val visualQA = SmolVLMTransformer.pretrained()
   .setInputCols("image_assembler")
   .setOutputCol("answer")
 ```
+{%- endcapture -%}
+
 {%- capture input_anno -%}
 IMAGE
 {%- endcapture -%}