Update app.py

app.py

@@ -10,6 +10,9 @@ def load_community_alignment_dataset():
     """Load the Facebook Community Alignment Dataset"""
     try:
         dataset = load_dataset("facebook/community-alignment-dataset")
+        print(f"Dataset loaded successfully. Available splits: {list(dataset.keys())}")
+        for split_name, split_data in dataset.items():
+            print(f"Split '{split_name}': {len(split_data)} items")
         return dataset
     except Exception as e:
         print(f"Error loading dataset: {e}")
@@ -45,12 +48,18 @@ def get_conversation_data(conversation_id: int) -> Dict[str, Any]:
     if not dataset:
         return None
     
-    # Search for conversation in the dataset
-    for split in dataset.keys():
-        for item in dataset[split]:
-            if item.get('conversation_id') == conversation_id:
-                return item
-    return None
+    try:
+        # Search for conversation in the dataset
+        for split in dataset.keys():
+            split_data = dataset[split]
+            for i in range(len(split_data)):
+                item = split_data[i]
+                if item.get('conversation_id') == conversation_id:
+                    return item
+        return None
+    except Exception as e:
+        print(f"Error getting conversation data: {e}")
+        return None
 
 def format_annotator_info(item: Dict[str, Any]) -> str:
     """Format annotator information"""
@@ -142,10 +151,20 @@ def get_random_conversation() -> int:
     if not dataset:
         return 0
     
-    # Get a random split and item
-    split = random.choice(list(dataset.keys()))
-    item = random.choice(dataset[split])
-    return item.get('conversation_id', 0)
+    try:
+        # Get a random split
+        split = random.choice(list(dataset.keys()))
+        split_data = dataset[split]
+        
+        # Get a random index
+        random_index = random.randint(0, len(split_data) - 1)
+        item = split_data[random_index]
+        
+        return item.get('conversation_id', 0)
+    except Exception as e:
+        print(f"Error getting random conversation: {e}")
+        # Fallback: return a default conversation ID
+        return 1061830552573006  # The ID from your example
 
 def get_dataset_stats() -> str:
     """Get dataset statistics"""
@@ -174,16 +193,21 @@ def search_conversations(query: str, field: str) -> str:
     results = []
     query_lower = query.lower()
     
-    for split_name, split_data in dataset.items():
-        for item in split_data[:100]:  # Limit search to first 100 items per split
-            if field in item and item[field]:
-                field_value = str(item[field]).lower()
-                if query_lower in field_value:
-                    results.append({
-                        'conversation_id': item.get('conversation_id'),
-                        'split': split_name,
-                        'field_value': str(item[field])[:100] + "..." if len(str(item[field])) > 100 else str(item[field])
-                    })
+    try:
+        for split_name, split_data in dataset.items():
+            # Limit search to first 100 items per split
+            for i in range(min(100, len(split_data))):
+                item = split_data[i]
+                if field in item and item[field]:
+                    field_value = str(item[field]).lower()
+                    if query_lower in field_value:
+                        results.append({
+                            'conversation_id': item.get('conversation_id'),
+                            'split': split_name,
+                            'field_value': str(item[field])[:100] + "..." if len(str(item[field])) > 100 else str(item[field])
+                        })
+    except Exception as e:
+        return f"Error during search: {e}"
     
     if not results:
         return f"No results found for '{query}' in field '{field}'"
@@ -334,4 +358,4 @@ if __name__ == "__main__":
         server_port=7860,
         share=False,
         show_error=True
-    )
+    )