Improved the Chatbot

app.py

@@ -9,12 +9,12 @@ description = """
 <p>
 <center>
 The bot was trained on Rick and Morty dialogues Kaggle Dataset using DialoGPT.
-<img src="https://huggingface.co/spaces/kingabzpro/Rick_and_Morty_Bot/resolve/main/img/rick.png" alt="rick" width="200"/>
+<img src="https://huggingface.co/spaces/kingabzpro/Rick_and_Morty_Bot/img/rick.png" alt="rick" width="200"/>
 </center>
 </p>
 """
 article = "<p style='text-align: center'><a href='https://medium.com/geekculture/discord-bot-using-dailogpt-and-huggingface-api-c71983422701' target='_blank'>Complete Tutorial</a></p><p style='text-align: center'><a href='https://dagshub.com/kingabzpro/DailoGPT-RickBot' target='_blank'>Project is Available at DAGsHub</a></p></center><center><img src='https://visitor-badge.glitch.me/badge?page_id=kingabzpro/Rick_and_Morty_Bot' alt='visitor badge'></center></p>"
-
+examples = [["How are you Rick?"]]
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
@@ -29,14 +29,23 @@ def predict(input, 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()
+    history = model.generate(bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id).tolist()
 
-    # convert the tokens to text, and then split the responses into the right format
+    # convert the tokens to text, and then split the responses into lines
     response = tokenizer.decode(history[0]).split("<|endoftext|>")
+    #print('decoded_response-->>'+str(response))
     response = [(response[i], response[i+1]) for i in range(0, len(response)-1, 2)]  # convert to tuples of list
+    #print('response-->>'+str(response))
     return response, history
 
-gr.Interface(fn = predict, inputs = ["textbox","state"], outputs = ["chatbot","state"],allow_flagging = "manual",title = title, flagging_callback = hf_writer, description = description, article = article ).launch(enable_queue=True)  # customizes the input component
+gr.Interface(fn=predict,
+             title=title,
+             description=description,
+             examples=examples,
+             flagging_callback = hf_writer,
+             allow_flagging = "manual",
+             inputs=["text", "state"],
+             outputs=["chatbot", "state"]).launch()
 
  #theme ="grass", 
  #title = title,