diff --git a/llama.h b/llama.h
index ff2c47019..e0fe2e0bb 100644
--- a/llama.h
+++ b/llama.h
@@ -706,6 +706,7 @@ extern "C" {
 
     /// Apply chat template and maybe tokenize it. Inspired by hf apply_chat_template() on python.
     /// Both "model" and "custom_template" are optional, but at least one is required. "custom_template" has higher precedence than "model"
+    /// NOTE: This function only support some know jinja templates. It is not a jinja parser.
     /// @param custom_template A Jinja template to use for this conversion. If this is nullptr, the model’s default chat template will be used instead.
     /// @param msg Pointer to a list of multiple llama_chat_message
     /// @param add_ass Whether to end the prompt with the token(s) that indicate the start of an assistant message.