Update: Auto-evaluation on Space startup

afcl/app.py

@@ -179,19 +179,25 @@ CUSTOM_CSS = """
 
 
 def load_evaluation_dataset():
-    """Load the Arabic FC dataset from HuggingFace."""
+    """Load ALL Arabic FC dataset from HuggingFace (train + test = 1,470 samples)."""
     try:
-        dataset = load_dataset("HeshamHaroon/Arabic_Function_Calling", split="test")
+        # Load both train and test splits
+        dataset = load_dataset("HeshamHaroon/Arabic_Function_Calling")
         samples = []
-        for item in dataset:
-            sample = {
-                'id': item['id'],
-                'query_ar': item['query_ar'],
-                'functions': json.loads(item['functions']) if item['functions'] else [],
-                'ground_truth': json.loads(item['ground_truth']) if item['ground_truth'] else None,
-                'category': item['category'],
-            }
-            samples.append(sample)
+
+        # Process all splits (train + test)
+        for split_name in dataset.keys():
+            for item in dataset[split_name]:
+                sample = {
+                    'id': item['id'],
+                    'query_ar': item['query_ar'],
+                    'functions': json.loads(item['functions']) if item['functions'] else [],
+                    'ground_truth': json.loads(item['ground_truth']) if item['ground_truth'] else None,
+                    'category': item['category'],
+                }
+                samples.append(sample)
+
+        print(f"Loaded {len(samples)} total samples from all splits")
         return samples
     except Exception as e:
         print(f"Error loading dataset: {e}")
@@ -447,8 +453,8 @@ def create_app():
             """)
             gr.HTML("""
             <div style="background: rgba(255,255,255,0.03); border: 1px solid rgba(255,255,255,0.1); border-radius: 12px; padding: 24px; text-align: center; flex: 1;">
-                <div style="font-size: 2.5rem; font-weight: 700; background: linear-gradient(135deg, #22c55e, #16a34a); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">147</div>
-                <div style="color: #a0a0a0; font-size: 0.9rem; margin-top: 8px;">Test Samples</div>
+                <div style="font-size: 2.5rem; font-weight: 700; background: linear-gradient(135deg, #22c55e, #16a34a); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">1,470</div>
+                <div style="color: #a0a0a0; font-size: 0.9rem; margin-top: 8px;">Total Samples</div>
             </div>
             """)
             gr.HTML("""