From db4a5a7a78d763915c3d99aeff64bc928a38b3d8 Mon Sep 17 00:00:00 2001
From: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com>
Date: Tue, 25 Nov 2025 17:07:05 +0100
Subject: [PATCH] ci: Add HF_TOKEN to dataset loading and merge CI

---
 .github/workflows/dataset_loading.yml    | 27 ++++++++++++++---------
 .github/workflows/dataset_loading_pr.yml | 28 ------------------------
 2 files changed, 17 insertions(+), 38 deletions(-)
 delete mode 100644 .github/workflows/dataset_loading_pr.yml

diff --git a/.github/workflows/dataset_loading.yml b/.github/workflows/dataset_loading.yml
index 3f8b4b040f..0f525dc946 100644
--- a/.github/workflows/dataset_loading.yml
+++ b/.github/workflows/dataset_loading.yml
@@ -1,27 +1,34 @@
 name: Datasets available on HuggingFace
-
 on:
   push:
     branches: [main]
+  pull_request:
+    paths:
+      - "mteb/tasks/**.py"
 
 jobs:
-  extract-and-run:
+  dataset-loading-check:
     runs-on: ubuntu-latest
-
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v3
-
+      uses: actions/checkout@v4
+    
     - name: Set up Python
       uses: actions/setup-python@v4
       with:
-        python-version: '3.10'
+        python-version: '3.11'
         cache: 'pip'
-
+    
     - name: Install dependencies
       run: |
-          make install-for-tests
-
+        make install-for-tests
+    
     - name: Run dataset loading tests
+      env:
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
-        make dataset-load-test
+        if [ "${{ github.event_name }}" == "pull_request" ]; then
+          make dataset-load-test-pr BASE_BRANCH=${{ github.event.pull_request.base.ref }}
+        else
+          make dataset-load-test
+        fi
\ No newline at end of file
diff --git a/.github/workflows/dataset_loading_pr.yml b/.github/workflows/dataset_loading_pr.yml
deleted file mode 100644
index c9de1d2300..0000000000
--- a/.github/workflows/dataset_loading_pr.yml
+++ /dev/null
@@ -1,28 +0,0 @@
-name: Datasets available on HuggingFace - PR
-
-on:
-  pull_request:
-    paths:
-      - "mteb/tasks/**.py"
-
-jobs:
-  run-pr-datasets-loading-check:
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v4
-
-    - name: Set up Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.11'
-        cache: 'pip'
-
-    - name: Install dependencies
-      run: |
-          make install-for-tests
-
-    - name: Run dataset loading tests
-      run: |
-        make dataset-load-test-pr BASE_BRANCH=${{ github.event.pull_request.base.ref }}