wip

src/app.py

@@ -19,7 +19,8 @@ current_test_type: str = "grounding"
 
 def format_leaderboard_for_display(df: pd.DataFrame) -> pd.DataFrame:
     """Format the leaderboard dataframe for display in the UI.
-    This ensures consistent display across environments like Huggingface Spaces."""
+    This ensures consistent display across environments
+    like Huggingface Spaces."""
     # Create a copy of the dataframe with only the columns we want to display
     display_df = pd.DataFrame()
     display_df["Judge Name"] = df["judge_name"]
@@ -314,7 +315,6 @@ def get_evaluation2(
         # Display the evaluation (time is already included in the evaluation)
         display_eval = eval2["display_evaluation"]
 
-        # Make the selection button visible once the evaluation is ready and show additional buttons
         return (
             display_eval,
             gr.update(visible=True),
@@ -322,7 +322,15 @@ def get_evaluation2(
         )
     except Exception as e:
         logger.error(f"Error getting evaluation 2: {e}")
-        return f"Error: {str(e)}", gr.update(visible=False), gr.update(visible=False)
+        return (
+            f"Error: {str(e)}",
+            gr.update(
+                visible=False,
+            ),
+            gr.update(
+                visible=False,
+            ),
+        )
 
 
 def format_inputs_for_evaluation(
@@ -391,7 +399,10 @@ def save_to_history(
             history_df = pd.DataFrame(columns=list(history_row.keys()))
 
         # Append the new row
-        history_df = pd.concat([history_df, pd.DataFrame([history_row])], ignore_index=True)
+        history_df = pd.concat(
+            [history_df, pd.DataFrame([history_row])],
+            ignore_index=True,
+        )
 
         # Save to CSV
         history_df.to_csv(HISTORY_PATH, index=False)