stream

app.py

@@ -15,8 +15,12 @@ def generate_response(
     temperature,
     top_p,
 ):
-    response = client.text_generation(message, max_new_tokens=256)
-    return response['generated_text']
+    stream = client.text_generation(message,stream=True, max_new_tokens=256)
+    output = ""
+    for response in stream:
+        output += response.token.text
+        yield output
+    return output
 
 
 def respond(