test 1 with webhooks

README.md

@@ -15,6 +15,7 @@ space_ci:
   private: true
   secrets:
   - HF_TOKEN
+  - WEBHOOK_SECRET
 tags:
 - leaderboard
 short_description: Track, rank and evaluate open LLMs and chatbots

app.py

@@ -3,7 +3,7 @@ import logging
 import time
 import gradio as gr
 import datasets
-from huggingface_hub import snapshot_download
+from huggingface_hub import snapshot_download, webhook_endpoint, WebhookPayload
 from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns
 from gradio_space_ci import enable_space_ci
 
@@ -290,4 +290,26 @@ with demo:
                 show_copy_button=True,
             )
 
+    @webhook_endpoint
+    async def update_leaderboard(payload: WebhookPayload) -> None:
+        if payload.repo.type == "dataset" and payload.event.action == "update":
+            leaderboard_dataset = datasets.load_dataset(AGGREGATED_REPO, "default", split="train", cache_dir=HF_HOME)
+            leaderboard_df = get_leaderboard_df(
+                leaderboard_dataset=leaderboard_dataset, 
+                cols=COLS,
+                benchmark_cols=BENCHMARK_COLS,
+            )
+            leaderboard.value = leaderboard_df
+
+    @webhook_endpoint    
+    async def update_queue(payload: WebhookPayload) -> None:
+        if payload.repo.type == "dataset" and payload.event.action == "update":
+            download_dataset(QUEUE_REPO, EVAL_REQUESTS_PATH)
+            eval_queue_dfs = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
+            finished_eval_queue_df, running_eval_queue_df, pending_eval_queue_df = eval_queue_dfs
+
+            finished_eval_table.value = finished_eval_queue_df
+            running_eval_table.value = running_eval_queue_df
+            pending_eval_table.value = pending_eval_queue_df
+
 demo.queue(default_concurrency_limit=40).launch()