recent changes

app.py

@@ -24,7 +24,12 @@ def load_tokenized_dataset_v2(directory_path):
 def get_input_ids(text, tokenized_dataset):
     # Try to find a close match in the pre-tokenized dataset
     for entry in tokenized_dataset:
-        if entry['ai_text'].strip() == text.strip():
+        ai_text = entry['ai_text']
+        # Handle case where ai_text is a list
+        if isinstance(ai_text, list):
+            ai_text = " ".join(ai_text)  # Join list elements into a single string
+
+        if ai_text.strip() == text.strip():
             return entry['input_ids']
 
     # If no match is found, tokenize the input text on the fly