Update app.py

app.py

@@ -128,33 +128,12 @@ client = InferenceClient(SPACE_URL, token=HF_API_KEY)
 
 
 
-
-
-def fetch_response(prompt):
-    """
-    Fetch full text response from the HF Inference Endpoint using the InferenceClient.
-    Returns tokens in a streaming fashion.
-    """
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-        
+    
 
 # -------------------------
 #    Streaming Logic using Generator
 # -------------------------
-def stream_response(prompt_text, api_key):
+def stream_response(prompt_text):
     """
     Stream text from the HF Inference Endpoint using the InferenceClient.
     Yields each partial chunk of text as it arrives.
@@ -199,7 +178,7 @@ if prompt:
     with st.spinner("Dubs is thinking... Woof Woof! 🐾"):
         msg=""
         with st.chat_message("assistant", avatar=DUBS_PATH):
-            full_response = fetch_response(chat_history)
+            full_response = stream_response(chat_history)
             msg=st.write_stream(full_response)