Merge branch 'main' into vectordb_name

llama_stack/providers/remote/inference/cerebras/config.py

@@ -26,8 +26,8 @@ class CerebrasImplConfig(BaseModel):
     )
 
     @classmethod
-    def sample_run_config(cls, **kwargs) -> dict[str, Any]:
+    def sample_run_config(cls, api_key: str = "${env.CEREBRAS_API_KEY}", **kwargs) -> dict[str, Any]:
         return {
             "base_url": DEFAULT_BASE_URL,
-            "api_key": "${env.CEREBRAS_API_KEY}",
+            "api_key": api_key,
         }

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

@@ -13,13 +13,9 @@ DEFAULT_OLLAMA_URL = "http://localhost:11434"
 
 class OllamaImplConfig(BaseModel):
     url: str = DEFAULT_OLLAMA_URL
-    raise_on_connect_error: bool = True
 
     @classmethod
-    def sample_run_config(
-        cls, url: str = "${env.OLLAMA_URL:=http://localhost:11434}", raise_on_connect_error: bool = True, **kwargs
-    ) -> dict[str, Any]:
+    def sample_run_config(cls, url: str = "${env.OLLAMA_URL:=http://localhost:11434}", **kwargs) -> dict[str, Any]:
         return {
             "url": url,
-            "raise_on_connect_error": raise_on_connect_error,
         }

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

@@ -84,7 +84,7 @@ MODEL_ENTRIES = [
         CoreModelId.llama_guard_3_1b.value,
     ),
     ProviderModelEntry(
-        provider_model_id="all-minilm:latest",
+        provider_model_id="all-minilm:l6-v2",
         aliases=["all-minilm"],
         model_type=ModelType.embedding,
         metadata={

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

@@ -94,7 +94,6 @@ class OllamaInferenceAdapter(
     def __init__(self, config: OllamaImplConfig) -> None:
         self.register_helper = ModelRegistryHelper(MODEL_ENTRIES)
         self.url = config.url
-        self.raise_on_connect_error = config.raise_on_connect_error
 
     @property
     def client(self) -> AsyncClient:
@@ -108,10 +107,7 @@ class OllamaInferenceAdapter(
         logger.debug(f"checking connectivity to Ollama at `{self.url}`...")
         health_response = await self.health()
         if health_response["status"] == HealthStatus.ERROR:
-            if self.raise_on_connect_error:
-                raise RuntimeError("Ollama Server is not running, start it using `ollama serve` in a separate terminal")
-            else:
-                logger.warning("Ollama Server is not running, start it using `ollama serve` in a separate terminal")
+            raise RuntimeError("Ollama Server is not running, start it using `ollama serve` in a separate terminal")
 
     async def health(self) -> HealthResponse:
         """

llama_stack/providers/remote/inference/passthrough/config.py

@@ -24,8 +24,10 @@ class PassthroughImplConfig(BaseModel):
     )
 
     @classmethod
-    def sample_run_config(cls, **kwargs) -> dict[str, Any]:
+    def sample_run_config(
+        cls, url: str = "${env.PASSTHROUGH_URL}", api_key: str = "${env.PASSTHROUGH_API_KEY}", **kwargs
+    ) -> dict[str, Any]:
         return {
-            "url": "${env.PASSTHROUGH_URL}",
-            "api_key": "${env.PASSTHROUGH_API_KEY}",
+            "url": url,
+            "api_key": api_key,
         }

llama_stack/providers/remote/inference/runpod/config.py

@@ -26,5 +26,5 @@ class RunpodImplConfig(BaseModel):
     def sample_run_config(cls, **kwargs: Any) -> dict[str, Any]:
         return {
             "url": "${env.RUNPOD_URL:=}",
-            "api_token": "${env.RUNPOD_API_TOKEN:=}",
+            "api_token": "${env.RUNPOD_API_TOKEN}",
         }

llama_stack/providers/remote/inference/tgi/config.py

@@ -17,7 +17,11 @@ class TGIImplConfig(BaseModel):
     )
 
     @classmethod
-    def sample_run_config(cls, url: str = "${env.TGI_URL}", **kwargs):
+    def sample_run_config(
+        cls,
+        url: str = "${env.TGI_URL}",
+        **kwargs,
+    ):
         return {
             "url": url,
         }

llama_stack/providers/remote/inference/tgi/tgi.py

@@ -327,7 +327,6 @@ class InferenceEndpointAdapter(_HfAdapter):
         # Get the inference endpoint details
         api = HfApi(token=config.api_token.get_secret_value())
         endpoint = api.get_inference_endpoint(config.endpoint_name)
-
         # Wait for the endpoint to be ready (if not already)
         endpoint.wait(timeout=60)
 

llama_stack/providers/remote/inference/together/config.py

@@ -26,5 +26,5 @@ class TogetherImplConfig(BaseModel):
     def sample_run_config(cls, **kwargs) -> dict[str, Any]:
         return {
             "url": "https://api.together.xyz/v1",
-            "api_key": "${env.TOGETHER_API_KEY:=}",
+            "api_key": "${env.TOGETHER_API_KEY}",
         }