From a8a860ea1fb4ee13c803d9d99cf0979aecf54363 Mon Sep 17 00:00:00 2001
From: Yuan Tang <terrytangyuan@gmail.com>
Date: Sun, 6 Oct 2024 09:44:20 -0400
Subject: [PATCH] Fix async case

---
 llama_stack/providers/adapters/inference/openai/openai.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/llama_stack/providers/adapters/inference/openai/openai.py b/llama_stack/providers/adapters/inference/openai/openai.py
index 7ce1a724e..2a1e279d8 100644
--- a/llama_stack/providers/adapters/inference/openai/openai.py
+++ b/llama_stack/providers/adapters/inference/openai/openai.py
@@ -173,7 +173,7 @@ class OpenAIInferenceAdapter(Inference):
                         stop_reason = StopReason.out_of_tokens
                     break
 
-                text = chunk.choices[0].message.content
+                text = chunk.choices[0].delta.content
                 if text is None:
                     continue