feat(api): introduce /rerank (#2940)

# What does this PR do?
Context: https://github.com/meta-llama/llama-stack/issues/2937

The API design is inspired by existing offerings, but not exactly the
same:
* `top_n` as the parameter to control number of results, instead of
`top_k`, since `n` is conventional to control number
* `truncation` bool instead of `max_token_per_doc`, since we should just
handle the truncation automatically depending on model capability,
instead of user setting the context length manually.
* `data` field in the response, to be consistent with other OpenAI APIs
(though they don't have a rerank API). Also, it is one less name to
learn in the API.

## Test Plan

Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>

llama_stack/providers/inline/inference/meta_reference/inference.py

@@ -33,6 +33,9 @@ from llama_stack.apis.inference import (
     InterleavedContent,
     LogProbConfig,
     Message,
+    OpenAIChatCompletionContentPartImageParam,
+    OpenAIChatCompletionContentPartTextParam,
+    RerankResponse,
     ResponseFormat,
     SamplingParams,
     StopReason,
@@ -442,6 +445,15 @@ class MetaReferenceInferenceImpl(
         results = await self._nonstream_chat_completion(request_batch)
         return BatchChatCompletionResponse(batch=results)
 
+    async def rerank(
+        self,
+        model: str,
+        query: str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam,
+        items: list[str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam],
+        max_num_results: int | None = None,
+    ) -> RerankResponse:
+        raise NotImplementedError("Reranking is not supported for Meta Reference")
+
     async def _nonstream_chat_completion(
         self, request_batch: list[ChatCompletionRequest]
     ) -> list[ChatCompletionResponse]:

llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py

@@ -12,6 +12,9 @@ from llama_stack.apis.inference import (
     InterleavedContent,
     LogProbConfig,
     Message,
+    OpenAIChatCompletionContentPartImageParam,
+    OpenAIChatCompletionContentPartTextParam,
+    RerankResponse,
     ResponseFormat,
     SamplingParams,
     ToolChoice,
@@ -122,3 +125,12 @@ class SentenceTransformersInferenceImpl(
         logprobs: LogProbConfig | None = None,
     ):
         raise NotImplementedError("Batch chat completion is not supported for Sentence Transformers")
+
+    async def rerank(
+        self,
+        model: str,
+        query: str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam,
+        items: list[str | OpenAIChatCompletionContentPartTextParam | OpenAIChatCompletionContentPartImageParam],
+        max_num_results: int | None = None,
+    ) -> RerankResponse:
+        raise NotImplementedError("Reranking is not supported for Sentence Transformers")