Update appStore/rag.py

appStore/rag.py

@@ -44,7 +44,7 @@ def run_query(context, label, model_sel_name):
     client = InferenceClient(model_sel_name, token = hf_token)
     
     # instantiate ChatCompletion as a generator object (stream is set to True)
-    chat_completion = client.chat.completions.create(
+    chat_completion = client.chat_completion(
         messages=messages,
         stream=True
     )