feat(api): Add options for supporting various embedding models (#1192)

We need to support:
- asymmetric embedding models (#934)
- truncation policies (#933)
- varying dimensional output (#932) 

## Test Plan

```bash
$ cd llama_stack/providers/tests/inference
$ pytest -s -v -k fireworks test_embeddings.py \
   --inference-model nomic-ai/nomic-embed-text-v1.5 --env EMBEDDING_DIMENSION=784
$  pytest -s -v -k together test_embeddings.py \
   --inference-model togethercomputer/m2-bert-80M-8k-retrieval --env EMBEDDING_DIMENSION=784
$ pytest -s -v -k ollama test_embeddings.py \
   --inference-model all-minilm:latest --env EMBEDDING_DIMENSION=784
```

llama_stack/providers/inline/inference/vllm/vllm.py

@@ -22,12 +22,14 @@ from llama_stack.apis.inference import (
     CompletionResponse,
     CompletionResponseStreamChunk,
     EmbeddingsResponse,
+    EmbeddingTaskType,
     Inference,
     InterleavedContentItem,
     LogProbConfig,
     Message,
     ResponseFormat,
     SamplingParams,
+    TextTruncation,
     ToolChoice,
     ToolConfig,
     ToolDefinition,
@@ -231,5 +233,12 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
         async for chunk in process_chat_completion_stream_response(stream, request):
             yield chunk
 
-    async def embeddings(self, model_id: str, contents: List[str] | List[InterleavedContentItem]) -> EmbeddingsResponse:
+    async def embeddings(
+        self,
+        model_id: str,
+        contents: List[str] | List[InterleavedContentItem],
+        text_truncation: Optional[TextTruncation] = TextTruncation.none,
+        output_dimension: Optional[int] = None,
+        task_type: Optional[EmbeddingTaskType] = None,
+    ) -> EmbeddingsResponse:
         raise NotImplementedError()