feat: add nvidia embedding implementation for new signature, task_type, output_dimention, text_truncation (#1213)

# What does this PR do?

updates nvidia inference provider's embedding implementation to use new
signature

add support for task_type, output_dimensions, text_truncation parameters

## Test Plan

`LLAMA_STACK_BASE_URL=http://localhost:8321 pytest -v
tests/client-sdk/inference/test_embedding.py --embedding-model
baai/bge-m3`

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

@@ -8,7 +8,7 @@ import logging
 import warnings
 from typing import AsyncIterator, List, Optional, Union
 
-from openai import APIConnectionError, AsyncOpenAI
+from openai import APIConnectionError, AsyncOpenAI, BadRequestError
 
 from llama_stack.apis.common.content_types import (
     InterleavedContent,
@@ -144,19 +144,38 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
         #
         # we can ignore str and always pass List[str] to OpenAI
         #
-        flat_contents = [
-            item.text if isinstance(item, TextContentItem) else item
-            for content in contents
-            for item in (content if isinstance(content, list) else [content])
-        ]
+        flat_contents = [content.text if isinstance(content, TextContentItem) else content for content in contents]
         input = [content.text if isinstance(content, TextContentItem) else content for content in flat_contents]
         model = self.get_provider_model_id(model_id)
 
-        response = await self._client.embeddings.create(
-            model=model,
-            input=input,
-            # extra_body={"input_type": "passage"|"query"},  # TODO(mf): how to tell caller's intent?
-        )
+        extra_body = {}
+
+        if text_truncation is not None:
+            text_truncation_options = {
+                TextTruncation.none: "NONE",
+                TextTruncation.end: "END",
+                TextTruncation.start: "START",
+            }
+            extra_body["truncate"] = text_truncation_options[text_truncation]
+
+        if output_dimension is not None:
+            extra_body["dimensions"] = output_dimension
+
+        if task_type is not None:
+            task_type_options = {
+                EmbeddingTaskType.document: "passage",
+                EmbeddingTaskType.query: "query",
+            }
+            extra_body["input_type"] = task_type_options[task_type]
+
+        try:
+            response = await self._client.embeddings.create(
+                model=model,
+                input=input,
+                extra_body=extra_body,
+            )
+        except BadRequestError as e:
+            raise ValueError(f"Failed to get embeddings: {e}") from e
 
         #
         # OpenAI: CreateEmbeddingResponse(data=[Embedding(embedding=List[float], ...)], ...)