Update dataset_utils.py

dataset_utils.py

@@ -12,6 +12,7 @@ class DatasetHandler:
     def load_descriptions(self, max_records=500):
         dataset = load_dataset(self.dataset_name)
         descriptions = {}
+        # Limit to the first 500 records for testing
         for record in dataset["train"].select(range(max_records)):
             species_name = record.get("species_name", "Unknown Species")
             description = record.get("description", "No description available.")