implement streaming

app.py

@@ -5,6 +5,7 @@ import services.scraper
 import stores.chroma
 from llm_setup.llm_setup import LLMService
 from caching.lfu import LFUCache
+import time 
 
 logger = logging.getLogger()  # Create a logger object
 logger.setLevel(logging.INFO)  # Set the logging level to INFO
@@ -34,7 +35,10 @@ def respond(user_input,session_hash):
 def echo(text, chat_history, request: gr.Request):
     if request:
         session_hash = request.session_hash
-        return respond(text, session_hash)
+        resp = respond(text, session_hash)
+        for i in range(len(resp)):
+            time.sleep(0.05)
+            yield resp[: i + 1]
     else:
         return "No request object received."