Update app.py

app.py

@@ -49,6 +49,7 @@ conn.close()
 
 
 # Create a sample DataFrame with 3,000 records and 20 columns
+'''
 num_records = 3000
 num_columns = 20
 
@@ -64,7 +65,7 @@ data["year"] = [random.choice(years) for _ in range(num_records)]
 data["city"] = [random.choice(cities) for _ in range(num_records)]
 
 table = pd.DataFrame(data)
-
+'''
 #table = pd.read_csv(csv_file.name, delimiter=",")
 #table.fillna(0, inplace=True)
 #table = table.astype(str)
@@ -73,7 +74,7 @@ data = {
     "year": [1896, 1900, 1904, 2004, 2008, 2012],
     "city": ["athens", "paris", "st. louis", "athens", "beijing", "london"]
 }
-#table = pd.DataFrame.from_dict(data)
+table = pd.DataFrame.from_dict(data)
 
 
 # Load the chatbot model
@@ -132,6 +133,7 @@ def sqlquery(input): #, history=[]):
     global conversation_history
 
     #======================================================================
+    '''
     batch_size = 10  # Number of records in each batch
     num_records = 3000  # Total number of records in the dataset
     for start_idx in range(0, num_records, batch_size):
@@ -160,7 +162,7 @@ def sqlquery(input): #, history=[]):
         for response in enumerate(responses):
             # Update conversation history            
             conversation_history.append("Bot: " + response)
-            
+     '''       
         '''
         
         = []
@@ -194,7 +196,7 @@ def sqlquery(input): #, history=[]):
         '''
             
     # ==========================================================================
-    '''
+    
     inputs = [input]
     sql_encoding = sql_tokenizer(table=table, query=input, return_tensors="pt")
     sql_outputs = sql_model.generate(**sql_encoding)
@@ -203,7 +205,7 @@ def sqlquery(input): #, history=[]):
     #history.append((input, sql_response))
     conversation_history.append(("User", input))
     conversation_history.append(("Bot", sql_response))
-    '''
+    
     # Build conversation string
     #conversation = "\n".join([f"User: {user_msg}\nBot: {resp_msg}" for user_msg, resp_msg in conversation_history])
     conversation = "\n".join([f"{sender}: {msg}" for sender, msg in conversation_history])
@@ -266,36 +268,3 @@ combine_interface = gr.TabbedInterface(
 if __name__ == '__main__':
     combine_interface.launch()
     #iface.launch(debug=True)
-
-
-'''
-batch_size = 10  # Number of records in each batch
-num_records = 3000  # Total number of records in the dataset
-
-for start_idx in range(0, num_records, batch_size):
-    end_idx = min(start_idx + batch_size, num_records)
-    
-    # Get a batch of records
-    batch_data = dataset[start_idx:end_idx]  # Replace with your dataset
-    
-    # Tokenize the batch
-    tokenized_batch = tokenizer.batch_encode_plus(
-        batch_data, padding=True, truncation=True, return_tensors="pt"
-    )
-    
-    # Perform inference
-    with torch.no_grad():
-        output = model.generate(
-            input_ids=tokenized_batch["input_ids"],
-            max_length=1024,
-            pad_token_id=tokenizer.eos_token_id,
-        )
-    
-    # Decode the output and process the responses
-    responses = [tokenizer.decode(ids, skip_special_tokens=True) for ids in output]
-    
-    # Process responses and maintain conversation context
-    # ...
-
-
-'''