Update main.py

main.py

@@ -26,31 +26,31 @@ def load_dataset():
     tempo_filtered=[]
     dataset=load_dataset("gaia-benchmark/GAIA","2023_level1",trust_remote_code=True)
     for question in dataset['validation']:
-    metadata = question.get('Annotator Metadata') # Use .get() for safety
-
-    if metadata: # Check if 'Annotator Metadata' exists
-        num_tools_str = metadata.get('Number of tools')
-        num_steps_str = metadata.get('Number of steps')
-
-        # Check if both numbers exist before trying to convert
-        if num_tools_str is not None and num_steps_str is not None:
-            try:
-                # Convert values to integers for comparison
-                num_tools = int(num_tools_str)
-                num_steps = int(num_steps_str)
-
-                # Apply the filter conditions
-                if num_tools < tool_threshold and num_steps < step_threshold:
-                    print(f"MATCH FOUND (Task ID: {question.get('task_id', 'N/A')}) - Tools: {num_tools}, Steps: {num_steps}")
-                    print(question) # Print the matching question dictionary
+        metadata = question.get('Annotator Metadata') # Use .get() for safety
+    
+        if metadata: # Check if 'Annotator Metadata' exists
+            num_tools_str = metadata.get('Number of tools')
+            num_steps_str = metadata.get('Number of steps')
+    
+            # Check if both numbers exist before trying to convert
+            if num_tools_str is not None and num_steps_str is not None:
+                try:
+                    # Convert values to integers for comparison
+                    num_tools = int(num_tools_str)
+                    num_steps = int(num_steps_str)
+    
+                    # Apply the filter conditions
+                    if num_tools < tool_threshold and num_steps < step_threshold:
+                        print(f"MATCH FOUND (Task ID: {question.get('task_id', 'N/A')}) - Tools: {num_tools}, Steps: {num_steps}")
+                        print(question) # Print the matching question dictionary
+                        print("------------------------------------------------------------------")
+                        tempo_filtered.append(question) # Add to the filtered list
+                    # else: # Optional: Handle items that don't match the filter
+                        # print(f"Skipping Task ID: {question.get('task_id', 'N/A')} - Tools: {num_tools}, Steps: {num_steps}")
+                except ValueError:
+                    # Handle cases where 'Number of tools' or 'Number of steps' is not a valid integer
+                    print(f"Skipping Task ID: {question.get('task_id', 'N/A')} - Could not convert tool/step count to integer.")
                     print("------------------------------------------------------------------")
-                    tempo_filtered.append(question) # Add to the filtered list
-                # else: # Optional: Handle items that don't match the filter
-                    # print(f"Skipping Task ID: {question.get('task_id', 'N/A')} - Tools: {num_tools}, Steps: {num_steps}")
-            except ValueError:
-                # Handle cases where 'Number of tools' or 'Number of steps' is not a valid integer
-                print(f"Skipping Task ID: {question.get('task_id', 'N/A')} - Could not convert tool/step count to integer.")
-                print("------------------------------------------------------------------")
     filtered_data=tempo_filtered
 
 # Prepare data structures for the API