Add docs-pr.yml and docs-pr-close.yml workflows

.github/workflows/docs-pr-close.yml

@@ -0,0 +1,32 @@
+name: Clean up PR documentation
+
+on:
+  pull_request:
+    types: [closed]
+
+jobs:
+  cleanup:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout docs-site
+        uses: actions/checkout@v4
+        with:
+          ref: gh-pages
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: pip install -e .[docs]
+
+      - name: Set git credentials
+        run: |
+          git config --global user.name "${{ github.actor }}"
+          git config --global user.email "${{ github.actor }}@users.noreply.github.com"
+
+      - name: Remove PR documentation
+        run: |
+          PR_NUMBER=${{ github.event.pull_request.number }}
+          mike delete pr-$PR_NUMBER --push

.github/workflows/docs-pr.yml

@@ -0,0 +1,79 @@
+name: Publish PR documentation
+
+on:
+  pull_request:
+    types:
+      - opened
+      - synchronize
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    steps:
+      - name: checkout docs-site
+        uses: actions/checkout@v4
+        with:
+          ref: gh-pages
+
+      - uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          # Looks like it's not working very well for other people:
+          # https://github.com/actions/setup-python/issues/436
+          # cache: "pip"
+          # cache-dependency-path: pyproject.toml
+
+      - uses: actions/cache@v3
+        id: cache
+        with:
+          path: ${{ env.pythonLocation }}
+          key: ${{ runner.os }}-python-${{ env.pythonLocation }}-${{ hashFiles('pyproject.toml') }}-docs-pr-v00
+
+      - name: Install dependencies
+        if: steps.cache.outputs.cache-hit != 'true'
+        run: pip install -e .[docs]
+
+      - name: Set git credentials
+        run: |
+          git config --global user.name "${{ github.actor }}"
+          git config --global user.email "${{ github.actor }}@users.noreply.github.com"
+
+      - name: Deploy hidden docs for PR
+        run: |
+          PR_NUMBER=$(echo $GITHUB_REF | awk 'BEGIN { FS = "/" } ; { print $3 }')
+          mike deploy pr-$PR_NUMBER --prop-set hidden=true --push
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Comment PR with docs link
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const pr_number = context.payload.pull_request.number;
+            const owner = context.repo.owner;
+            const repo = context.repo.repo;
+
+            // Check if a comment already exists
+            const comments = await github.rest.issues.listComments({
+              issue_number: pr_number,
+              owner: owner,
+              repo: repo
+            });
+
+            const botComment = comments.data.find(comment => 
+              comment.user.type === 'Bot' && 
+              comment.body.includes('Documentation for this PR has been built')
+            );
+
+            if (!botComment) {
+              // Post new comment only if it doesn't exist
+              await github.rest.issues.createComment({
+                issue_number: pr_number,
+                owner: owner,
+                repo: repo,
+                body: `Documentation for this PR has been built. You can view it at: https://distilabel.argilla.io/pr-${pr_number}/`
+              });
+            }

.github/workflows/docs.yml

@@ -32,7 +32,7 @@ jobs:
         id: cache
         with:
           path: ${{ env.pythonLocation }}
-          key: ${{ runner.os }}-python-${{ env.pythonLocation }}-${{ hashFiles('pyproject.toml') }}-docs
+          key: ${{ runner.os }}-python-${{ env.pythonLocation }}-${{ hashFiles('pyproject.toml') }}-docs-v00
 
       - name: Install dependencies
         if: steps.cache.outputs.cache-hit != 'true'
@@ -46,9 +46,9 @@ jobs:
       - run: mike deploy dev --push
         if: github.ref == 'refs/heads/develop'
         env:
-          GH_ACCESS_TOKEN: ${{ secrets.GH_ACCESS_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - run: mike deploy ${{ github.ref_name }} latest --update-aliases --push
         if: startsWith(github.ref, 'refs/tags/')
         env:
-          GH_ACCESS_TOKEN: ${{ secrets.GH_ACCESS_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

docs/scripts/gen_popular_issues.py

@@ -24,9 +24,8 @@
 REPOSITORY = "argilla-io/distilabel"
 DATA_PATH = "sections/community/popular_issues.md"
 
-GITHUB_ACCESS_TOKEN = os.getenv(
-    "GH_ACCESS_TOKEN"
-)  # public_repo and read:org scopes are required
+# public_repo and read:org scopes are required
+GITHUB_TOKEN = os.getenv("GITHUB_TOKEN")
 
 
 def fetch_issues_from_github_repository(
@@ -119,7 +118,7 @@ def get_org_members(auth_token: Union[str, None] = None) -> List[str]:
 
 
 with mkdocs_gen_files.open(DATA_PATH, "w") as f:
-    df = fetch_issues_from_github_repository(REPOSITORY, GITHUB_ACCESS_TOKEN)
+    df = fetch_issues_from_github_repository(REPOSITORY, GITHUB_TOKEN)
 
     open_issues = df.loc[df["State"] == "open"]
     engagement_df = (
@@ -129,7 +128,7 @@ def get_org_members(auth_token: Union[str, None] = None) -> List[str]:
         .reset_index()
     )
 
-    members = get_org_members(GITHUB_ACCESS_TOKEN)
+    members = get_org_members(GITHUB_TOKEN)
     community_issues = df.loc[~df["Author"].isin(members)]
     community_issues_df = (
         community_issues[