Update app.py

app.py

@@ -2,64 +2,67 @@ import streamlit as st
 from gradio_client import Client
 
 # Constants
-TITLE = "Llama2 70B Chatbot"
-DESCRIPTION = """
-This Space demonstrates model [Llama-2-70b-chat-hf](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) by Meta, 
-a Llama 2 model with 70B parameters fine-tuned for chat instructions. 
+APP_TITLE = "Llama2 70B Chatbot"
+APP_DESCRIPTION = """
+This application demonstrates the Llama-2-70b chatbot model by Meta, 
+fine-tuned for chat instructions. You can interact with the model and ask questions.
 """
 
 # Initialize client
-client = Client("https://ysharma-explore-llamav2-with-tgi.hf.space/")
-
+llama2_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=0.0, max_value=4096.0, value=4096.0, step=64.0)
-    ToppSide = st.slider("Top-p (nucleus sampling)", min_value=0.0, max_value=1.0, value=0.6, step=0.05)
-    RepetitionpenaltySide = st.slider("Repetition penalty", min_value=0.0, max_value=2.0, value=1.2, step=0.05)
-
+    system_prompt_input = st.text_input("Optional system prompt:")
+    temperature_slider = st.slider("Temperature", min_value=0.0, max_value=1.0, value=0.9, step=0.05)
+    max_new_tokens_slider = st.slider("Max new tokens", min_value=0.0, max_value=4096.0, value=4096.0, step=64.0)
+    topp_slider = st.slider("Top-p (nucleus sampling)", min_value=0.0, max_value=1.0, value=0.6, step=0.05)
+    repetition_penalty_slider = st.slider("Repetition penalty", min_value=0.0, max_value=2.0, value=1.2, step=0.05)
 
-    
 # Prediction function
-def predict(message, system_prompt, temperature, max_new_tokens,Topp,Repetitionpenalty):
-    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)
-    			Topp,	# int | float (numeric value between 0.0 and 1)
-    			Repetitionpenalty,	# int | float (numeric value between 1.0 and 2.0)
-    			api_name="/chat"
+def get_llama2_response(user_message, system_prompt, temperature, max_new_tokens, topp, repetition_penalty):
+    with st.status("Requesting Llama-2"):
+        st.write("Requesting API...")
+        response = llama2_client.predict(
+            user_message,
+            system_prompt,
+            temperature,
+            max_new_tokens,
+            topp,
+            repetition_penalty,
+            api_name="/chat"
         )
         st.write("Done")
         return response
 
 # Streamlit UI
-st.title(TITLE)
-st.write(DESCRIPTION)
-
+st.title(APP_TITLE)
+st.write(APP_DESCRIPTION)
 
-if "messages" not in st.session_state:
-    st.session_state.messages = []
+if "chat_history" not in st.session_state:
+    st.session_state.chat_history = []
 
 # Display chat messages from history on app rerun
-for message in st.session_state.messages:
+for message in st.session_state.chat_history:
     with st.chat_message(message["role"]):
         st.markdown(message["content"])
         
 # React to user input
-if prompt := st.chat_input("Ask LLama-2-70b anything..."):
+if user_input := st.chat_input("Ask Llama-2-70B anything..."):
     # Display user message in chat message container
-    st.chat_message("human",avatar = "🧑‍💻").markdown(prompt)
+    st.chat_message("user", avatar="🧑‍💻").markdown(user_input)
     # Add user message to chat history
-    st.session_state.messages.append({"role": "human", "content": prompt})
+    st.session_state.chat_history.append({"role": "user", "content": user_input})
 
-    response = predict(prompt,system_promptSide,temperatureSide,max_new_tokensSide,ToppSide,RepetitionpenaltySide)
+    response = get_llama2_response(
+        user_input,
+        system_prompt_input,
+        temperature_slider,
+        max_new_tokens_slider,
+        topp_slider,
+        repetition_penalty_slider
+    )
     # Display assistant response in chat message container
     with st.chat_message("assistant", avatar='🦙'):
         st.markdown(response)
     # Add assistant response to chat history
-    st.session_state.messages.append({"role": "assistant", "content": response})
+    st.session_state.chat_history.append({"role": "assistant", "content": response})