Update app.py

app.py

@@ -18,7 +18,7 @@ print ("Inf.Client")
 client = InferenceClient("https://api-inference.huggingface.co/models/meta-llama/Llama-2-70b-chat-hf")
 
 # generate function
-def generate(text):
+def generate(text, history):
     payload = tokenizer.apply_chat_template([{"role":"user","content":text}],tokenize=False)
     res = client.text_generation(
                     payload,