refactor: use extra_body to pass in input_type params for asymmetric embedding models for NVIDIA Inference Provider (#3804)

# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
Previously, the NVIDIA inference provider implemented a custom
`openai_embeddings` method with a hardcoded `input_type="query"`
parameter, which is required by NVIDIA asymmetric embedding
models([https://github.com/llamastack/llama-stack/pull/3205](https://github.com/llamastack/llama-stack/pull/3205)).
Recently `extra_body` parameter is added to the embeddings API
([https://github.com/llamastack/llama-stack/pull/3794](https://github.com/llamastack/llama-stack/pull/3794)).
So, this PR updates the NVIDIA inference provider to use the base
`OpenAIMixin.openai_embeddings` method instead and pass the `input_type`
through the `extra_body` parameter for asymmetric embedding models.

<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->

## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
Run the following command for the ```embedding_model```:
```nvidia/llama-3.2-nv-embedqa-1b-v2```, ```nvidia/nv-embedqa-e5-v5```,
```nvidia/nv-embedqa-mistral-7b-v2```, and
```snowflake/arctic-embed-l```.
```
pytest -s -v tests/integration/inference/test_openai_embeddings.py --stack-config="inference=nvidia" --embedding-model={embedding_model} --env NVIDIA_API_KEY={nvidia_api_key} --env NVIDIA_BASE_URL="https://integrate.api.nvidia.com" --inference-mode=record
```

llama_stack/providers/remote/inference/nvidia/NVIDIA.md

@@ -139,16 +139,13 @@ print(f"Structured Response: {structured_response.choices[0].message.content}")
 
 The following example shows how to create embeddings for an NVIDIA NIM.
 
-> [!NOTE]
-> NVIDIA asymmetric embedding models (e.g., `nvidia/llama-3.2-nv-embedqa-1b-v2`) require an `input_type` parameter not present in the standard OpenAI embeddings API. The NVIDIA Inference Adapter automatically sets `input_type="query"` when using the OpenAI-compatible embeddings endpoint for NVIDIA. For passage embeddings, use the `embeddings` API with `task_type="document"`.
-
 ```python
-response = client.inference.embeddings(
-    model_id="nvidia/llama-3.2-nv-embedqa-1b-v2",
-    contents=["What is the capital of France?"],
-    task_type="query",
+response = client.embeddings.create(
+    model="nvidia/llama-3.2-nv-embedqa-1b-v2",
+    input=["What is the capital of France?"],
+    extra_body={"input_type": "query"},
 )
-print(f"Embeddings: {response.embeddings}")
+print(f"Embeddings: {response.data}")
 ```
 
 ### Vision Language Models Example

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

@@ -5,14 +5,6 @@
 # the root directory of this source tree.
 
 
-from openai import NOT_GIVEN
-
-from llama_stack.apis.inference import (
-    OpenAIEmbeddingData,
-    OpenAIEmbeddingsRequestWithExtraBody,
-    OpenAIEmbeddingsResponse,
-    OpenAIEmbeddingUsage,
-)
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
@@ -76,50 +68,3 @@ class NVIDIAInferenceAdapter(OpenAIMixin):
         :return: The NVIDIA API base URL
         """
         return f"{self.config.url}/v1" if self.config.append_api_version else self.config.url
-
-    async def openai_embeddings(
-        self,
-        params: OpenAIEmbeddingsRequestWithExtraBody,
-    ) -> OpenAIEmbeddingsResponse:
-        """
-        OpenAI-compatible embeddings for NVIDIA NIM.
-
-        Note: NVIDIA NIM asymmetric embedding models require an "input_type" field not present in the standard OpenAI embeddings API.
-        We default this to "query" to ensure requests succeed when using the
-        OpenAI-compatible endpoint. For passage embeddings, use the embeddings API with
-        `task_type='document'`.
-        """
-        extra_body: dict[str, object] = {"input_type": "query"}
-        logger.warning(
-            "NVIDIA OpenAI-compatible embeddings: defaulting to input_type='query'. "
-            "For passage embeddings, use the embeddings API with task_type='document'."
-        )
-
-        response = await self.client.embeddings.create(
-            model=await self._get_provider_model_id(params.model),
-            input=params.input,
-            encoding_format=params.encoding_format if params.encoding_format is not None else NOT_GIVEN,
-            dimensions=params.dimensions if params.dimensions is not None else NOT_GIVEN,
-            user=params.user if params.user is not None else NOT_GIVEN,
-            extra_body=extra_body,
-        )
-
-        data = []
-        for i, embedding_data in enumerate(response.data):
-            data.append(
-                OpenAIEmbeddingData(
-                    embedding=embedding_data.embedding,
-                    index=i,
-                )
-            )
-
-        usage = OpenAIEmbeddingUsage(
-            prompt_tokens=response.usage.prompt_tokens,
-            total_tokens=response.usage.total_tokens,
-        )
-
-        return OpenAIEmbeddingsResponse(
-            data=data,
-            model=response.model,
-            usage=usage,
-        )