app | no timeout

app.py

@@ -74,7 +74,12 @@ def predict(message, history):
     # convert the string into tensors & move to GPU
     model_inputs = tokenizer([messages], return_tensors="pt").to(device)
 
-    streamer = TextIteratorStreamer(tokenizer, timeout=30., skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(
+        tokenizer,
+        # timeout=30., # no timeout until I implement error handling for the empty stream
+        skip_prompt=True,
+        skip_special_tokens=True
+    )
     generate_kwargs = dict(
         model_inputs,
         streamer=streamer,