Update app.py

app.py

@@ -48,7 +48,7 @@ conn.close()
 '''
 
 # Create a sample DataFrame with 3,000 records and 20 columns
-num_records = 50
+num_records = 30
 num_columns = 20
 
 data = {
@@ -59,8 +59,8 @@ data = {
 years = list(range(2000, 2023))  # Range of years
 cities = ["New York", "Los Angeles", "Chicago", "Houston", "Miami"]  # List of cities
 
-data["year"] = [random.choice(years) for _ in range(num_records)]
-data["city"] = [random.choice(cities) for _ in range(num_records)]
+#data["year"] = [random.choice(years) for _ in range(num_records)]
+#data["city"] = [random.choice(cities) for _ in range(num_records)]
 
 table = pd.DataFrame(data)
 
@@ -76,11 +76,17 @@ chatbot_model_name = "microsoft/DialoGPT-medium"
 tokenizer = AutoTokenizer.from_pretrained(chatbot_model_name)
 model = AutoModelForCausalLM.from_pretrained(chatbot_model_name)
 
+cmax_token_limit = tokenizer.max_model_input_sizes[chatbot_model_name]
+print(f"Chat bot Maximum token limit for {chatbot_model_name}: {cmax_token_limit}")
+
 # Load the SQL Model
 sql_model_name = "microsoft/tapex-large-finetuned-wtq"
 sql_tokenizer = TapexTokenizer.from_pretrained(sql_model_name)
 sql_model = BartForConditionalGeneration.from_pretrained(sql_model_name)
 
+max_token_limit = TapexTokenizer.max_model_input_sizes[sql_model_name]
+print(f"SQL Maximum token limit for {sql_model_name}: {max_token_limit}")
+
 #sql_response = None
 conversation_history = []