add completion api support to nvidia inference provider (#533)

# What does this PR do?

add the completion api to the nvidia inference provider


## Test Plan

while running the meta/llama-3.1-8b-instruct NIM from
https://build.nvidia.com/meta/llama-3_1-8b-instruct?snippet_tab=Docker

```
➜ pytest -s -v --providers inference=nvidia llama_stack/providers/tests/inference/ --env NVIDIA_BASE_URL=http://localhost:8000 -k test_completion --inference-model Llama3.1-8B-Instruct
=============================================== test session starts ===============================================
platform linux -- Python 3.10.15, pytest-8.3.3, pluggy-1.5.0 -- /home/matt/.conda/envs/stack/bin/python
cachedir: .pytest_cache
rootdir: /home/matt/Documents/Repositories/meta-llama/llama-stack
configfile: pyproject.toml
plugins: anyio-4.6.2.post1, asyncio-0.24.0, httpx-0.34.0
asyncio: mode=strict, default_loop_scope=None
collected 20 items / 18 deselected / 2 selected                                                                             

llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[-nvidia] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion_structured_output[-nvidia] SKIPPED

============================= 1 passed, 1 skipped, 18 deselected, 6 warnings in 5.40s =============================
```

the structured output functionality works but the accuracy fails

## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [x] Ran pre-commit to handle lint / formatting issues.
- [x] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [x] Wrote necessary unit or integration tests.

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

@@ -9,6 +9,7 @@ from typing import AsyncIterator, List, Optional, Union
 
 from llama_models.datatypes import SamplingParams
 from llama_models.llama3.api.datatypes import (
+    ImageMedia,
     InterleavedTextMedia,
     Message,
     ToolChoice,
@@ -22,6 +23,7 @@ from llama_stack.apis.inference import (
     ChatCompletionRequest,
     ChatCompletionResponse,
     ChatCompletionResponseStreamChunk,
+    CompletionRequest,
     CompletionResponse,
     CompletionResponseStreamChunk,
     EmbeddingsResponse,
@@ -37,8 +39,11 @@ from llama_stack.providers.utils.inference.model_registry import (
 from . import NVIDIAConfig
 from .openai_utils import (
     convert_chat_completion_request,
+    convert_completion_request,
     convert_openai_chat_completion_choice,
     convert_openai_chat_completion_stream,
+    convert_openai_completion_choice,
+    convert_openai_completion_stream,
 )
 from .utils import _is_nvidia_hosted, check_health
 
@@ -115,7 +120,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
             timeout=self._config.timeout,
         )
 
-    def completion(
+    async def completion(
         self,
         model_id: str,
         content: InterleavedTextMedia,
@@ -124,7 +129,38 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
         stream: Optional[bool] = False,
         logprobs: Optional[LogProbConfig] = None,
     ) -> Union[CompletionResponse, AsyncIterator[CompletionResponseStreamChunk]]:
-        raise NotImplementedError()
+        if isinstance(content, ImageMedia) or (
+            isinstance(content, list)
+            and any(isinstance(c, ImageMedia) for c in content)
+        ):
+            raise NotImplementedError("ImageMedia is not supported")
+
+        await check_health(self._config)  # this raises errors
+
+        request = convert_completion_request(
+            request=CompletionRequest(
+                model=self.get_provider_model_id(model_id),
+                content=content,
+                sampling_params=sampling_params,
+                response_format=response_format,
+                stream=stream,
+                logprobs=logprobs,
+            ),
+            n=1,
+        )
+
+        try:
+            response = await self._client.completions.create(**request)
+        except APIConnectionError as e:
+            raise ConnectionError(
+                f"Failed to connect to NVIDIA NIM at {self._config.url}: {e}"
+            ) from e
+
+        if stream:
+            return convert_openai_completion_stream(response)
+        else:
+            # we pass n=1 to get only one completion
+            return convert_openai_completion_choice(response.choices[0])
 
     async def embeddings(
         self,