Jeasonize it MORE and MORE?

app.py

@@ -87,7 +87,7 @@ temp_values = st.sidebar.slider(
 )
 
 custom_instructions = st.sidebar.text_area(
-    "Custom Instructions",
+    "Custom System Instructions",
     value="You are helpful assistant, act like a Human in conversation. Keep answers very short and in English only!",
     help="Customize how the AI should behave"
 )
@@ -132,33 +132,10 @@ if prompt := st.chat_input(f"Hi I'm {selected_model}, How can I help you today?"
 
     st.session_state.messages.append({"role": "user", "content": prompt})
 
-    formated_text = format_promt(prompt, custom_instructions, temp_values)
-
-
     with st.chat_message("assistant"):
         client = InferenceClient(
             model=model_links[selected_model],)
 
-        output = client.post(
-            json=format_promt(prompt, custom_instructions, temp_values)
-        )
-
-        # Create a placeholder for the streaming response
-        message_placeholder = st.empty()
-        full_response = ""
-
-        # Stream the response and accumulate it
-        for chunk in output:
-            if isinstance(chunk, dict) and "generated_text" in chunk:
-                text_chunk = chunk["generated_text"]
-            elif isinstance(chunk, str):
-                text_chunk = chunk
-            else:
-                continue
-                
-            full_response += text_chunk
-            message_placeholder.markdown(full_response + "▌")
-        
-        # Display final response and store it
-        message_placeholder.markdown(full_response)
-        st.session_state.messages.append({"role": "assistant", "content": full_response})
+        try:
+            # Combine system prompt and user input
+            full_prompt = f"<|system|>{custom_instructions}</s>