chore: remove deprecated inference.chat_completion implementations

vllm -
 - requires max_tokens be set, use config value
 - set tool_choice to none if no tools provided

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

@@ -4,21 +4,19 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from collections.abc import AsyncGenerator
+from collections.abc import AsyncIterator
 from typing import Any
 
 from llama_stack.apis.inference import (
     InferenceProvider,
-    LogProbConfig,
-    Message,
-    ResponseFormat,
-    SamplingParams,
-    ToolChoice,
-    ToolConfig,
-    ToolDefinition,
-    ToolPromptFormat,
 )
-from llama_stack.apis.inference.inference import OpenAICompletion
+from llama_stack.apis.inference.inference import (
+    OpenAIChatCompletion,
+    OpenAIChatCompletionChunk,
+    OpenAICompletion,
+    OpenAIMessageParam,
+    OpenAIResponseFormatParam,
+)
 from llama_stack.apis.models import ModelType
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
@@ -73,21 +71,6 @@ class SentenceTransformersInferenceImpl(
     async def unregister_model(self, model_id: str) -> None:
         pass
 
-    async def chat_completion(
-        self,
-        model_id: str,
-        messages: list[Message],
-        sampling_params: SamplingParams | None = None,
-        response_format: ResponseFormat | None = None,
-        tools: list[ToolDefinition] | None = None,
-        tool_choice: ToolChoice | None = ToolChoice.auto,
-        tool_prompt_format: ToolPromptFormat | None = None,
-        stream: bool | None = False,
-        logprobs: LogProbConfig | None = None,
-        tool_config: ToolConfig | None = None,
-    ) -> AsyncGenerator:
-        raise ValueError("Sentence transformers don't support chat completion")
-
     async def openai_completion(
         self,
         # Standard OpenAI completion parameters
@@ -115,3 +98,31 @@ class SentenceTransformersInferenceImpl(
         suffix: str | None = None,
     ) -> OpenAICompletion:
         raise NotImplementedError("OpenAI completion not supported by sentence transformers provider")
+
+    async def openai_chat_completion(
+        self,
+        model: str,
+        messages: list[OpenAIMessageParam],
+        frequency_penalty: float | None = None,
+        function_call: str | dict[str, Any] | None = None,
+        functions: list[dict[str, Any]] | None = None,
+        logit_bias: dict[str, float] | None = None,
+        logprobs: bool | None = None,
+        max_completion_tokens: int | None = None,
+        max_tokens: int | None = None,
+        n: int | None = None,
+        parallel_tool_calls: bool | None = None,
+        presence_penalty: float | None = None,
+        response_format: OpenAIResponseFormatParam | None = None,
+        seed: int | None = None,
+        stop: str | list[str] | None = None,
+        stream: bool | None = None,
+        stream_options: dict[str, Any] | None = None,
+        temperature: float | None = None,
+        tool_choice: str | dict[str, Any] | None = None,
+        tools: list[dict[str, Any]] | None = None,
+        top_logprobs: int | None = None,
+        top_p: float | None = None,
+        user: str | None = None,
+    ) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
+        raise NotImplementedError("OpenAI chat completion not supported by sentence transformers provider")