diff --git a/llama_stack/providers/remote/inference/nvidia/nvidia.py b/llama_stack/providers/remote/inference/nvidia/nvidia.py index 69e6335c6..99c8d0613 100644 --- a/llama_stack/providers/remote/inference/nvidia/nvidia.py +++ b/llama_stack/providers/remote/inference/nvidia/nvidia.py @@ -203,7 +203,7 @@ 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,