You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-services/openai/includes/chat-completion.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -547,7 +547,7 @@ The token counting portion of the code demonstrated previously is a simplified v
547
547
548
548
## Troubleshooting
549
549
550
-
### Do not use ChatML syntax with the Chat Completions endpoints
550
+
### Do not use ChatML syntax with the Chat Completions endpoint
551
551
552
552
We have found that some customers will try using the [legacy ChatML syntax](./chat-markup-language.md) with the chat completion endpoints and newer models. ChatML was a preview capability that only worked with the legacy completions endpoint with the `gpt-35-turbo` version 0301 model which is [slated for retirement](../concepts/model-retirements.md). Attempting to use ChatML syntax with newer models and the chat completions endpoint can result in unexpected model response behavior and is not recommended.
0 commit comments