diff --git a/docs/source/basic_tutorials/consuming_tgi.md b/docs/source/basic_tutorials/consuming_tgi.md
index 60b0d203..b69cee2e 100644
--- a/docs/source/basic_tutorials/consuming_tgi.md
+++ b/docs/source/basic_tutorials/consuming_tgi.md
@@ -125,10 +125,33 @@ The UI looks like this 👇
You can try the demo directly here 👇
-
+
+
+
+
+
+
-You can disable streaming mode using `return` instead of `yield` in your inference function.
+You can disable streaming mode using `return` instead of `yield` in your inference function, like below.
+
+```diff
+def inference(message, history):
+ partial_message = ""
+ for token in client.text_generation(message, max_new_tokens=20, stream=True):
+ partial_message += token
+- yield partial_message
++ return partial_message
+```
+
You can read more about how to customize a `ChatInterface` [here](https://www.gradio.app/guides/creating-a-chatbot-fast).
## API documentation