Update main.py

main.py

@@ -47,12 +47,12 @@ def read_root(data: req):
     new_user_input_ids = tokenizer.encode(data.prompt + tokenizer.eos_token, return_tensors='pt')
 
     # append the new user input tokens to the chat history
-    bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
+    bot_input_ids = torch.cat(new_user_input_ids, dim=-1) if step > 0 else new_user_input_ids
 
     # generated a response while limiting the total chat history to 1000 tokens, 
     chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
 
-    generated_text = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
+    generated_text = tokenizer.decode(chat_history_ids[:, :][0], skip_special_tokens=True)
     answer_data = { "answer": generated_text }
     print("Answer:", generated_text)