diff --git a/docs/source/distributions/importing_as_library.md b/docs/source/distributions/importing_as_library.md
index 815660fd4..7e15062df 100644
--- a/docs/source/distributions/importing_as_library.md
+++ b/docs/source/distributions/importing_as_library.md
@@ -21,7 +21,7 @@ print(response)
 ```python
 response = await client.inference.chat_completion(
     messages=[UserMessage(content="What is the capital of France?", role="user")],
-    model="Llama3.1-8B-Instruct",
+    model_id="Llama3.1-8B-Instruct",
     stream=False,
 )
 print("\nChat completion response:")
diff --git a/llama_stack/providers/remote/inference/ollama/ollama.py b/llama_stack/providers/remote/inference/ollama/ollama.py
index 74c0b8601..f89629afc 100644
--- a/llama_stack/providers/remote/inference/ollama/ollama.py
+++ b/llama_stack/providers/remote/inference/ollama/ollama.py
@@ -180,7 +180,6 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
     async def _nonstream_completion(self, request: CompletionRequest) -> AsyncGenerator:
         params = await self._get_params(request)
         r = await self.client.generate(**params)
-        assert isinstance(r, dict)
 
         choice = OpenAICompatCompletionChoice(
             finish_reason=r["done_reason"] if r["done"] else None,