Update app.py

app.py

@@ -40,17 +40,11 @@ data = {
 }
 table = pd.DataFrame.from_dict(data)
 
-chat_history_ids = None
-#bot_input_ids = None
+history = None
 
+def chatbot_response(user_message, history=[]):
 
-def chatbot_response(user_message):
-
-    global chat_history_ids
-    #global bot_input_ids
-
-    print(chat_history_ids is None)
-    #print(bot_input_ids is None)
+    global history
     # Check if the user input is a question
     is_question = "?" in user_message
 
@@ -67,27 +61,28 @@ def chatbot_response(user_message):
         outputs = chatbot_model.generate(inputs, max_length=100, num_return_sequences=1)
         response = chatbot_tokenizer.decode(outputs[0], skip_special_tokens=True)
         '''
-        # encode the new user input, add the eos_token and return a tensor in Pytorch
-        new_user_input_ids = chatbot_tokenizer.encode(user_message + chatbot_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
-        if chat_history_ids is not None:
-            bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1)
-        else:
-            bot_input_ids = new_user_input_ids
-        
-        # generated a response while limiting the total chat history to 1000 tokens, 
-        chat_history_ids = chatbot_model.generate(bot_input_ids, max_length=1000, pad_token_id=chatbot_tokenizer.eos_token_id)
-
-        response = chatbot_tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
+        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()
     
-    return response
+        # 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
 
 # Define the chatbot and SQL execution interfaces using Gradio
 chatbot_interface = gr.Interface(
     fn=chatbot_response,
-    inputs=gr.Textbox(prompt="You:"),
-    outputs=gr.Textbox(),
+    #inputs=gr.Textbox(prompt="You:"),
+    #outputs=gr.Textbox(),
+    inputs=["text", "state"],
+    outputs=["chatbot", "state"],
     live=True,
     capture_session=True,
     title="ST Chatbot",