Update space

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-
+from rag import run_rag
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
@@ -22,9 +22,9 @@ def respond(
             messages.append({"role": "user", "content": val[0]})
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
+        
+    messages.append({"role": "user", "content": run_rag(message)})
+ 
     response = ""
 
     for message in client.chat_completion(
@@ -38,14 +38,14 @@ def respond(
 
         response += token
         yield response
-
+ 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a useful and capable assistant .", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
@@ -60,4 +60,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(share=True)