Update app.py

app.py

@@ -197,7 +197,8 @@ chain = ConversationChain(
     verbose=True,
 )
 
-
+!pip install langchain==0.0.233
+from langchain.chains.conversation.memory import ConversationBufferWindowMemory
 def get_llama_response(message: str, history: list) -> str:
   query_text = message
 
@@ -224,11 +225,9 @@ def get_llama_response(message: str, history: list) -> str:
 
   #print(template)
   chain.prompt=prompt
-  #res = chain(query_text)
-  inputs = tokenizer(query_text, return_tensors="pt")
-  outputs = model.generate(inputs.input_ids, max_length=50)
-  response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-  return(response)
+  res = chain(query_text)
+  
+  return(res['response'])
 
 import gradio as gr