Update app.py

app.py

@@ -42,30 +42,33 @@ def predict(input, history=[]):
     # Check if the user input is a question
     is_question = "?" in input
 
-    if is_question: 
-        sql_encoding = sql_tokenizer(table=table, query=input + sql_tokenizer.eos_token, return_tensors="pt")
-        #sql_outputs = sql_model.generate(**sql_encoding)
-        #sql_response = sql_tokenizer.batch_decode(sql_outputs, skip_special_tokens=True)
-
-        bot_input_ids = torch.cat([torch.LongTensor(history), sql_encoding], dim=-1)
-        history = sql_model.generate(bot_input_ids, max_length=1000, pad_token_id=sql_tokenizer.eos_token_id).tolist()
-        response = sql_tokenizer.decode(history[0]).split("<|endoftext|>")
-        response = [(response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)]
-
-    else:
-        # tokenize the new input sentence
-        new_user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors='pt')
+
+    # tokenize the new input sentence
+    new_user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors='pt')
+
+    # append the new user input tokens to the chat history
+    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
+      
+    # generate a response
+    history = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id).tolist()
+    response_dialog = tokenizer.decode(history[0])
+
+    # Use the SQL model to generate a response
+    encoding = sql_tokenizer(table=table, query=response_dialog, return_tensors="pt")
+    outputs = sql_model.generate(**encoding)
+    response_sql = sql_tokenizer.batch_decode(outputs, skip_special_tokens=True)
+
+    # Add the SQL model's response to the chat history
+    history.extend(response_sql)
+
+    
+    # convert the tokens to text, and then split the responses into the right format
+    response = tokenizer.decode(history[0]).split("<|endoftext|>")
+    response = [(response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)]  # convert to tuples of list
+    
+
     
-        # append the new user input tokens to the chat history
-        bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
-          
-        # generate a response
-        history = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id).tolist()
     
-        # convert the tokens to text, and then split the responses into the right format
-        response = tokenizer.decode(history[0]).split("<|endoftext|>")
-        response = [(response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)]  # convert to tuples of list
-        
     return response, history