Update app.py

app.py

@@ -16,7 +16,7 @@ llm = Llama(
     # n_gpu_layers=50, # change n_gpu_layers if you have more or less VRAM 
 ) 
 
-# history = []
+history = []
 
 # system_message = """
 # You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
@@ -24,7 +24,7 @@ llm = Llama(
 # """
 
 
-def generate_text(message):
+def generate_text(message, history):
     # temp = ""
     # input_prompt = f"[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n "
     # for interaction in history:
@@ -47,7 +47,7 @@ def generate_text(message):
         temp += stream["choices"][0]["text"]
         yield temp
 
-    # history = ["init", input_prompt]
+    history = ["init", input_prompt]
 
 
 demo = gr.ChatInterface(