From 6aaa7322960741a84da11ac360516e4ec813dfff Mon Sep 17 00:00:00 2001 From: Justa Date: Tue, 13 May 2025 19:52:44 +0800 Subject: [PATCH] add ChatTemplateKwargs to ChatCompletionRequest (#980) Co-authored-by: Justa --- chat.go | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/chat.go b/chat.go index 0f91d48..c8a3e81 100644 --- a/chat.go +++ b/chat.go @@ -275,6 +275,11 @@ type ChatCompletionRequest struct { Metadata map[string]string `json:"metadata,omitempty"` // Configuration for a predicted output. Prediction *Prediction `json:"prediction,omitempty"` + // ChatTemplateKwargs provides a way to add non-standard parameters to the request body. + // Additional kwargs to pass to the template renderer. Will be accessible by the chat template. + // Such as think mode for qwen3. "chat_template_kwargs": {"enable_thinking": false} + // https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes + ChatTemplateKwargs map[string]any `json:"chat_template_kwargs,omitempty"` } type StreamOptions struct {