diff --git a/llama_stack/providers/remote/inference/nvidia/nvidia.py b/llama_stack/providers/remote/inference/nvidia/nvidia.py index 51c8c6a79..5caf19fda 100644 --- a/llama_stack/providers/remote/inference/nvidia/nvidia.py +++ b/llama_stack/providers/remote/inference/nvidia/nvidia.py @@ -205,7 +205,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper): extra_body["input_type"] = task_type_options[task_type] try: - response = await self._client.embeddings.create( + response = await self._get_client(model).embeddings.create( model=model, input=input, extra_body=extra_body,