add a token

app.py

@@ -111,7 +111,9 @@ st.markdown(
     trained on the Indonesian [Oscar](https://huggingface.co/datasets/oscar), [MC4](https://huggingface.co/datasets/mc4) 
     and [Wikipedia](https://huggingface.co/datasets/wikipedia) dataset. We created it as part of the 
     [Huggingface JAX/Flax event](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/).
-    It is also possible to write a custom prompt on your own language.
+    
+    The demo supports "multi language" ;-), feel free to try a prompt on your language. We are also experimenting with 
+    the sentence based image search using Wikipedia passages encoded with distillbert, and search it using Faiss.  
     """
 )