Merge branch 'meta-llama:main' into feat/litellm_sambanova_usage

llama_stack/providers/remote/inference/ollama/ollama.py

@@ -42,7 +42,11 @@ from llama_stack.apis.inference import (
 from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
 from llama_stack.apis.models import Model, ModelType
 from llama_stack.log import get_logger
-from llama_stack.providers.datatypes import ModelsProtocolPrivate
+from llama_stack.providers.datatypes import (
+    HealthResponse,
+    HealthStatus,
+    ModelsProtocolPrivate,
+)
 from llama_stack.providers.utils.inference.model_registry import (
     ModelRegistryHelper,
 )
@@ -87,8 +91,19 @@ class OllamaInferenceAdapter(
 
     async def initialize(self) -> None:
         logger.info(f"checking connectivity to Ollama at `{self.url}`...")
+        await self.health()
+
+    async def health(self) -> HealthResponse:
+        """
+        Performs a health check by verifying connectivity to the Ollama server.
+        This method is used by initialize() and the Provider API to verify that the service is running
+        correctly.
+        Returns:
+            HealthResponse: A dictionary containing the health status.
+        """
         try:
             await self.client.ps()
+            return HealthResponse(status=HealthStatus.OK)
         except httpx.ConnectError as e:
             raise RuntimeError(
                 "Ollama Server is not running, start it using `ollama serve` in a separate terminal"
@@ -437,6 +452,28 @@ class OllamaInferenceAdapter(
         }
         return await self.openai_client.chat.completions.create(**params)  # type: ignore
 
+    async def batch_completion(
+        self,
+        model_id: str,
+        content_batch: List[InterleavedContent],
+        sampling_params: Optional[SamplingParams] = None,
+        response_format: Optional[ResponseFormat] = None,
+        logprobs: Optional[LogProbConfig] = None,
+    ):
+        raise NotImplementedError("Batch completion is not supported for Ollama")
+
+    async def batch_chat_completion(
+        self,
+        model_id: str,
+        messages_batch: List[List[Message]],
+        sampling_params: Optional[SamplingParams] = None,
+        tools: Optional[List[ToolDefinition]] = None,
+        tool_config: Optional[ToolConfig] = None,
+        response_format: Optional[ResponseFormat] = None,
+        logprobs: Optional[LogProbConfig] = None,
+    ):
+        raise NotImplementedError("Batch chat completion is not supported for Ollama")
+
 
 async def convert_message_to_openai_dict_for_ollama(message: Message) -> List[dict]:
     async def _convert_content(content) -> dict:

llama_stack/providers/remote/inference/vllm/vllm.py

@@ -526,3 +526,25 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
             user=user,
         )
         return await self.client.chat.completions.create(**params)  # type: ignore
+
+    async def batch_completion(
+        self,
+        model_id: str,
+        content_batch: List[InterleavedContent],
+        sampling_params: Optional[SamplingParams] = None,
+        response_format: Optional[ResponseFormat] = None,
+        logprobs: Optional[LogProbConfig] = None,
+    ):
+        raise NotImplementedError("Batch completion is not supported for Ollama")
+
+    async def batch_chat_completion(
+        self,
+        model_id: str,
+        messages_batch: List[List[Message]],
+        sampling_params: Optional[SamplingParams] = None,
+        tools: Optional[List[ToolDefinition]] = None,
+        tool_config: Optional[ToolConfig] = None,
+        response_format: Optional[ResponseFormat] = None,
+        logprobs: Optional[LogProbConfig] = None,
+    ):
+        raise NotImplementedError("Batch chat completion is not supported for Ollama")