Update app.py

app.py

@@ -153,8 +153,11 @@ if prompt := st.chat_input(f"Hi I'm {selected_model}, ask me a question"):
 
     # Display assistant response in chat message container
     with st.chat_message("assistant"):
-        stream = InferenceClient(
+        client = InferenceClient(
             model=model_links[selected_model],
+            headers)
+
+        output = client.text_generation(
             messages=[
                 {"role": m["role"], "content": m["content"]}
                 for m in st.session_state.messages