OpenAI completion prompt can also be an array

The OpenAI completion prompt field can be a string or an array, so
update things to use and pass that properly.

This also stubs in a basic conversion of OpenAI non-streaming
completion requests to Llama Stack completion calls, for those
providers that don't actually have an OpenAI backend to allow them to
still accept requests via the OpenAI APIs.

Signed-off-by: Ben Browning <bbrownin@redhat.com>

llama_stack/providers/remote/inference/vllm/vllm.py

@@ -424,7 +424,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
     async def openai_completion(
         self,
         model: str,
-        prompt: str,
+        prompt: Union[str, List[str]],
         best_of: Optional[int] = None,
         echo: Optional[bool] = None,
         frequency_penalty: Optional[float] = None,