Merge remote-tracking branch 'github-desktop-kudos07/vespa-work' into pr/3233

Author: bogdankostic

.github/dependabot.yml

@@ -4,3 +4,5 @@ updates:
     directory: '/'
     schedule:
       interval: 'daily'
+    cooldown:
+      default-days: 1

.github/labeler.yml

@@ -1,4 +1,9 @@
 # Integrations
+integration:alloydb:
+  - changed-files:
+      - any-glob-to-any-file: "integrations/alloydb/**/*"
+      - any-glob-to-any-file: ".github/workflows/alloydb.yml"
+
 integration:aimlapi:
   - changed-files:
       - any-glob-to-any-file: "integrations/aimlapi/**/*"
@@ -29,6 +34,11 @@ integration:astra:
       - any-glob-to-any-file: "integrations/astra/**/*"
       - any-glob-to-any-file: ".github/workflows/astra.yml"
 
+integration:brave:
+  - changed-files:
+      - any-glob-to-any-file: "integrations/brave/**/*"
+      - any-glob-to-any-file: ".github/workflows/brave.yml"
+
 integration:azure-ai-search:
   - changed-files:
       - any-glob-to-any-file: "integrations/azure_ai_search/**/*"
@@ -69,11 +79,21 @@ integration:docling:
       - any-glob-to-any-file: "integrations/docling/**/*"
       - any-glob-to-any-file: ".github/workflows/docling.yml"
 
+integration:docling-serve:
+  - changed-files:
+      - any-glob-to-any-file: "integrations/docling_serve/**/*"
+      - any-glob-to-any-file: ".github/workflows/docling_serve.yml"
+
 integration:dspy:
   - changed-files:
       - any-glob-to-any-file: "integrations/dspy/**/*"
       - any-glob-to-any-file: ".github/workflows/dspy.yml"
 
+integration:e2b:
+  - changed-files:
+      - any-glob-to-any-file: "integrations/e2b/**/*"
+      - any-glob-to-any-file: ".github/workflows/e2b.yml"
+
 integration:elasticsearch:
   - changed-files:
       - any-glob-to-any-file: "integrations/elasticsearch/**/*"
@@ -84,6 +104,12 @@ integration:faiss:
       - any-glob-to-any-file: "integrations/faiss/**/*"
       - any-glob-to-any-file: ".github/workflows/faiss.yml"
 
+
+integration:falkordb:
+  - changed-files:
+      - any-glob-to-any-file: "integrations/falkordb/**/*"
+      - any-glob-to-any-file: ".github/workflows/falkordb.yml"
+
 integration:fastembed:
   - changed-files:
       - any-glob-to-any-file: "integrations/fastembed/**/*"
@@ -207,6 +233,11 @@ integration:paddleocr:
       - any-glob-to-any-file: "integrations/paddleocr/**/*"
       - any-glob-to-any-file: ".github/workflows/paddleocr.yml"
 
+integration:perplexity:
+  - changed-files:
+      - any-glob-to-any-file: "integrations/perplexity/**/*"
+      - any-glob-to-any-file: ".github/workflows/perplexity.yml"
+
 integration:pgvector:
   - changed-files:
       - any-glob-to-any-file: "integrations/pgvector/**/*"

.github/utils/validate_version.py

@@ -3,7 +3,7 @@
 
 # * integrations/<INTEGRATION_FOLDER_NAME>-v1.0.0
 # * integrations/<INTEGRATION_FOLDER_NAME>-v1.0.0.post0 (for post-releases)
-INTEGRATION_VERSION_REGEX = r"integrations/([a-zA-Z_]+)-v([0-9]+\.[0-9]+\.[0-9]+(?:\.post[0-9]+)?)"
+INTEGRATION_VERSION_REGEX = r"integrations/([a-zA-Z0-9_]+)-v([0-9]+\.[0-9]+\.[0-9]+(?:\.post[0-9]+)?)"
 
 
 def validate_version_number(tag: str):

.github/workflows/CI_check_api_ref.yml

@@ -81,7 +81,9 @@ jobs:
 
       - name: Install Hatch
         if: steps.changed.outputs.integrations != '[]'
-        run: pip install hatch
+        run: |
+          python -m pip install --upgrade pip
+          pip install hatch --uploaded-prior-to=P1D
 
       - name: Generate API references
         if: steps.changed.outputs.integrations != '[]'

.github/workflows/CI_coverage_comment.yml

@@ -9,16 +9,20 @@ on:
       - "Test / anthropic"
       - "Test / arcadedb"
       - "Test / astra"
+      - "Test / brave"
       - "Test / azure_ai_search"
       - "Test / azure_doc_intelligence"
       - "Test / chonkie"
       - "Test / chroma"
       - "Test / cohere"
       - "Test / cometapi"
       - "Test / deepeval"
+      - "Test / docling_serve"
       - "Test / dspy"
+      - "Test / e2b"
       - "Test / elasticsearch"
       - "Test / faiss"
+      - "Test / falkordb"
       - "Test / fastembed"
       - "Test / firecrawl"
       - "Test / github"
@@ -42,6 +46,7 @@ on:
       - "Test / opensearch"
       - "Test / optimum"
       - "Test / paddleocr"
+      - "Test / perplexity"
       - "Test / pgvector"
       - "Test / pinecone"
       - "Test / presidio"

.github/workflows/CI_docusaurus_sync.yml

@@ -32,7 +32,9 @@ jobs:
           python-version: "3.10"
 
       - name: Install Hatch
-        run: pip install hatch
+        run: |
+          python -m pip install --upgrade pip
+          pip install hatch --uploaded-prior-to=P1D
 
       - name: Get project folder
         id: pathfinder

.github/workflows/CI_labeler.yml

@@ -10,6 +10,6 @@ jobs:
   triage:
     runs-on: ubuntu-slim
     steps:
-    - uses: actions/labeler@634933edcd8ababfe52f92936142cc22ac488b1b # v6.0.1
+    - uses: actions/labeler@f27b608878404679385c85cfa523b85ccb86e213 # v6.1.0
       with:
         repo-token: "${{ secrets.GITHUB_TOKEN }}"

.github/workflows/CI_license_compliance.yml

@@ -3,22 +3,22 @@ name: Core / License Compliance
 on:
   pull_request:
     paths:
-    - "integrations/**/pyproject.toml"
-    - ".github/workflows/CI_license_compliance.yml"
+      - "integrations/**/pyproject.toml"
+      - ".github/workflows/CI_license_compliance.yml"
   # Since we test PRs, there is no need to run the workflow at each
   # merge on `main`. Let's use a cron job instead.
   schedule:
     - cron: "0 0 * * *" # every day at midnight
 
 env:
   PYTHON_VERSION: "3.10"
-  EXCLUDE_PACKAGES: "(?i)^(azure-identity|fastembed|ragas|tqdm|psycopg|mistralai|pgvector).*"
+  EXCLUDE_PACKAGES: "(?i)^(azure-identity|azure-search-documents|fastembed|tqdm|psycopg|mistralai|pgvector).*"
 
   # Exclusions must be explicitly motivated
   #
   # - azure-identity is MIT but the license is not available on PyPI
+  # - azure-search-documents is MIT but the license is not available on PyPI
   # - fastembed is Apache 2.0 but the license on PyPI is unclear ("Other/Proprietary License (Apache License)")
-  # - ragas is Apache 2.0 but the license is not available on PyPI
   # - mistralai is Apache 2.0 but the license is not available on PyPI
   # - pgvector is MIT but the license is not available on PyPI
 
@@ -53,7 +53,8 @@ jobs:
 
       - name: Get direct dependencies from pyproject.toml files
         run: |
-          pip install toml
+          python -m pip install --upgrade pip
+          pip install toml --uploaded-prior-to=P1D
 
           # Determine the list of pyproject.toml files to process
           if [ "${{ github.event_name }}" = "schedule" ] || [ "${{ steps.changed-files.outputs.workflow_any_changed }}" = "true" ]; then
@@ -91,6 +92,6 @@ jobs:
 
       - name: Notify Slack on nightly failure
         if: failure() && github.event_name == 'schedule'
-        uses: deepset-ai/notify-slack-action@3cda73b77a148f16f703274198e7771340cf862b # v1
+        uses: deepset-ai/notify-slack-action@a65def0c8bf91d6520286ab34280151c76a5a008 # v1.1.0
         with:
           slack-webhook-url: ${{ secrets.SLACK_WEBHOOK_URL_NOTIFICATIONS }}

.github/workflows/CI_project.yml

@@ -10,7 +10,7 @@ jobs:
     name: Add new issues to project for triage
     runs-on: ubuntu-slim
     steps:
-      - uses: actions/add-to-project@244f685bbc3b7adfa8466e08b698b5577571133e # v1.0.2
+      - uses: actions/add-to-project@5afcf98fcd03f1c2f92c3c83f58ae24323cc57fd # v2.0.0
         with:
           project-url: https://github.com/orgs/deepset-ai/projects/5
           github-token: ${{ secrets.GH_PROJECT_PAT }}

.github/workflows/CI_pypi_release.yml

@@ -38,7 +38,9 @@ jobs:
           python-version: "3.12"
 
       - name: Install dependencies
-        run: pip install hatch requests
+        run: |
+          python -m pip install --upgrade pip
+          pip install hatch requests --uploaded-prior-to=P1D
 
       - name: Validate version number
         run: python .github/utils/validate_version.py --tag ${{ github.ref_name }}
@@ -62,7 +64,7 @@ jobs:
           packages-dir: ${{ steps.pathfinder.outputs.project_path }}/dist
 
       - name: Generate changelog
-        uses: orhun/git-cliff-action@c93ef52f3d0ddcdcc9bd5447d98d458a11cd4f72 # v4.7.1
+        uses: orhun/git-cliff-action@f50e11560dce63f7c33227798f90b924471a88b5 # v4.8.0
         env:
           OUTPUT: "${{ steps.pathfinder.outputs.project_path }}/CHANGELOG.md"
         with: