diff --git a/docs/online_serving/README.md b/docs/online_serving/README.md index 24d9d58da..c68a62896 100644 --- a/docs/online_serving/README.md +++ b/docs/online_serving/README.md @@ -52,6 +52,7 @@ For a description of the OpenAI protocol, refer to the document [OpenAI Chat Com ## Parameter Differences ### Request Parameter Differences The differences in request parameters between FastDeploy and the OpenAI protocol are as follows. Other request parameters will be ignored: + - `prompt` (supported only in the `v1/completions` interface) - `messages` (supported only in the `v1/chat/completions` interface) - `frequency_penalty`: Optional[float] = 0.0 @@ -77,6 +78,7 @@ The additional return fields added by FastDeploy are as follows: - `reasoning_content`: The returned result of the reasoning chain Overview of return parameters: + ```python ChatCompletionStreamResponse: id: str @@ -94,4 +96,4 @@ DeltaMessage: content: Optional[str] = None token_ids: Optional[List[int]] = None reasoning_content: Optional[str] = None -``` \ No newline at end of file +```