Update huggingface dataset from CI

Author: georg-wolflein

.github/workflows/ci.yml

@@ -25,7 +25,7 @@ jobs:
         run: uv run pytest tests
 
   build-cpu:
-    needs: test
+    needs: [test]
     uses: ./.github/workflows/build.yml
     with:
       base: ubuntu:24.04
@@ -37,7 +37,7 @@ jobs:
       id-token: write
 
   build-cuda:
-    needs: test
+    needs: [test]
     uses: ./.github/workflows/build.yml
     with:
       base: nvidia/cuda:12.8.1-cudnn-devel-ubuntu24.04
@@ -46,4 +46,25 @@ jobs:
       contents: read
       packages: write
       attestations: write
-      id-token: write
+      id-token: write
+  
+  update-huggingface-dataset:
+    needs: [test, build-cpu, build-cuda]
+    if: github.ref == 'refs/heads/main'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+      - name: Install the project
+        run: uv sync --all-extras --dev
+      - name: Login to HuggingFace
+        run: |
+          uv run --with huggingface_hub huggingface-cli login --token $HF_TOKEN
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+      - name: Update HuggingFace dataset
+        run: uv run scripts/update_huggingface_dataset.py
+        env:
+          HF_COMMIT_MESSAGE: Update dataset from CI on branch ${{ github.ref }}

scripts/update_huggingface_dataset.py

@@ -0,0 +1,19 @@
+"""Script to update the HuggingFace dataset. Runs on on CI."""
+
+import os
+
+from datasets import Dataset
+from toolarena.definition import ToolDefinition
+from toolarena.utils import TASKS_DIR
+
+HF_REPO_ID = os.getenv("HF_REPO_ID", "KatherLab/ToolArena")
+HF_COMMIT_MESSAGE = os.getenv("HF_COMMIT_MESSAGE", "Update dataset")
+
+if __name__ == "__main__":
+    ds = Dataset.from_list(
+        [
+            ToolDefinition.from_yaml(f).model_dump(mode="json")
+            for f in TASKS_DIR.glob("*/task.yaml")
+        ]
+    )
+    ds.push_to_hub(HF_REPO_ID, commit_message=HF_COMMIT_MESSAGE)