Create streaming_callback.py

streaming_callback.py

@@ -0,0 +1,10 @@
+from langchain.callbacks.base import BaseCallbackHandler
+
+class StreamHandler(BaseCallbackHandler):
+    def __init__(self, container):
+        self.container = container
+        self.text = ""
+
+    def on_llm_new_token(self, token: str, **kwargs):
+        self.text += token
+        self.container.markdown(self.text)