Update app.py

app.py

@@ -64,6 +64,8 @@ status = ""
 
 agreed = ""
 
+history=[]
+
 from llama_cpp import Llama
 llm = Llama(model_path=model_file, model_type="mistral",n_gpu_layers=-1,n_ctx = 2048)
 
@@ -170,8 +172,7 @@ def generate(prompt, history):
                   """
 
         response = ""
-        history2 = []
-
+        
         while(len(response) < 1):
             output = llm(context, max_tokens=400, stop=["Nurse:"], echo=False)
             response = output["choices"][0]["text"]