Update app.py

app.py

@@ -111,14 +111,20 @@ if prompt := st.chat_input(f"Hi I'm {selected_model}, How can I help you today?"
     with st.chat_message("assistant"):
         client = InferenceClient(
             model=model_links[selected_model], )
-        output = client.text_generation(
-            formated_text,
-            temperature=temp_values,  # 0.5
-            max_new_tokens=3000,
-            stream=True
-        )
-        response = st.write_stream(output)
-        st.session_state.messages.append({"role": "assistant", "content": response})
-        
-        # Save the updated conversation history to the file
-        save_conversation_history(st.session_state.messages)
+        max_new_tokens = 2048  # Adjust this value as needed
+        try:
+            output = client.text_generation(
+                formated_text,
+                temperature=temp_values,
+                max_new_tokens=max_new_tokens,
+                stream=True
+            )
+            response = st.write_stream(output)
+        except ValueError as e:
+            if "Input validation error" in str(e):
+                st.error("Error: The input prompt is too long. Please try a shorter prompt.")
+            else:
+                st.error(f"An error occurred: {e}")
+        else:
+            st.session_state.messages.append({"role": "assistant", "content": response})
+            save_conversation_history(st.session_state.messages)