Address comments

docs/docs/providers/batches/index.mdx

@@ -18,14 +18,14 @@ title: Batches
 ## Overview
 
 The Batches API enables efficient processing of multiple requests in a single operation,
-particularly useful for processing large datasets, batch evaluation workflows, and
-cost-effective inference at scale.
+    particularly useful for processing large datasets, batch evaluation workflows, and
+    cost-effective inference at scale.
 
-The API is designed to allow use of openai client libraries for seamless integration.
+    The API is designed to allow use of openai client libraries for seamless integration.
 
-This API provides the following extensions:
+    This API provides the following extensions:
      - idempotent batch creation
 
-Note: This API is currently under active development and may undergo changes.
+    Note: This API is currently under active development and may undergo changes.
 
 This section contains documentation for all available providers for the **batches** API.

llama_stack/providers/remote/inference/nvidia/nvidia.py

@@ -146,7 +146,7 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference):
         # Convert query to text format
         if isinstance(query, str):
             query_text = query
-        elif hasattr(query, "text"):
+        elif isinstance(query, OpenAIChatCompletionContentPartTextParam):
             query_text = query.text
         else:
             raise ValueError("Query must be a string or text content part")
@@ -156,7 +156,7 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference):
         for item in items:
             if isinstance(item, str):
                 passages.append({"text": item})
-            elif hasattr(item, "text"):
+            elif isinstance(item, OpenAIChatCompletionContentPartTextParam):
                 passages.append({"text": item.text})
             else:
                 raise ValueError("Items must be strings or text content parts")