feat(api)!: support passing extra_body to embeddings and vector_stores APIs

Applies the same pattern from #3777 to embeddings and vector_stores.create() endpoints.

Breaking change: Method signatures now accept a single params object with Pydantic extra="allow" instead of individual parameters. Provider-specific params can be passed via extra_body and accessed through params.model_extra.

Updated APIs: openai_embeddings(), openai_create_vector_store(), openai_create_vector_store_file_batch()

llama_stack/providers/remote/inference/llama_openai_compat/llama.py

@@ -7,6 +7,7 @@
 from llama_stack.apis.inference.inference import (
     OpenAICompletion,
     OpenAICompletionRequestWithExtraBody,
+    OpenAIEmbeddingsRequestWithExtraBody,
     OpenAIEmbeddingsResponse,
 )
 from llama_stack.log import get_logger
@@ -40,10 +41,6 @@ class LlamaCompatInferenceAdapter(OpenAIMixin):
 
     async def openai_embeddings(
         self,
-        model: str,
-        input: str | list[str],
-        encoding_format: str | None = "float",
-        dimensions: int | None = None,
-        user: str | None = None,
+        params: OpenAIEmbeddingsRequestWithExtraBody,
     ) -> OpenAIEmbeddingsResponse:
         raise NotImplementedError()