fix

callback_handler.py

@@ -42,3 +42,15 @@ class StreamingStdOutCallBackHandler(BaseCallbackHandler):
 
     def on_llm_end(self, response: str, **kwargs: Any) -> None:
         """Run when LLM ends running."""
+
+class QueueCallback(BaseCallbackHandler):
+    """Callback handler for streaming LLM responses to a queue."""
+
+    def __init__(self, q):
+        self.q = q
+
+    def on_llm_new_token(self, token: str, **kwargs: any) -> None:
+        self.q.put(token)
+
+    def on_llm_end(self, *args, **kwargs: any) -> None:
+        return self.q.empty()