Update app.py

app.py

@@ -11,15 +11,22 @@ a Llama 2 model with 70B parameters fine-tuned for chat instructions.
 # Initialize client
 client = Client("https://ysharma-explore-llamav2-with-tgi.hf.space/")
 
+
+with st.sidebar:
+    system_promptSide = st.text_input("Optional system prompt:")
+    temperatureSide = st.slider("Temperature", min_value=0.0, max_value=1.0, value=0.9, step=0.05)
+    max_new_tokensSide = st.slider("Max new tokens", min_value=0, max_value=4096, value=4096, step=32)
+
+    
 # Prediction function
 def predict(message, system_prompt="", temperature=0.9, max_new_tokens=4096):
     with st.status("Requesting LLama-2"):
         st.write("Requesting API")
         response = client.predict(
     			message,	# str in 'Message' Textbox component
-                system_prompt,	# str in 'Optional system prompt' Textbox component
-    			temperature,	# int | float (numeric value between 0.0 and 1.0)
-    			max_new_tokens,	# int | float (numeric value between 0 and 4096)
+                system_promptSide,	# str in 'Optional system prompt' Textbox component
+    			temperatureSide,	# int | float (numeric value between 0.0 and 1.0)
+    			max_new_tokensSide,	# int | float (numeric value between 0 and 4096)
     			0.3,	# int | float (numeric value between 0.0 and 1)
     			1,	# int | float (numeric value between 1.0 and 2.0)
     			api_name="/chat"