pre-commit fixes

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

@@ -5,10 +5,11 @@
 # the root directory of this source tree.
 
 from .config import RunpodImplConfig
-from .runpod import RunpodInferenceAdapter
 
 
 async def get_adapter_impl(config: RunpodImplConfig, _deps):
+    from .runpod import RunpodInferenceAdapter
+
     assert isinstance(config, RunpodImplConfig), f"Unexpected config type: {type(config)}"
     impl = RunpodInferenceAdapter(config)
     await impl.initialize()

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

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import Optional
+from typing import Any, Dict, Optional
 
 from pydantic import BaseModel, Field
 
@@ -21,3 +21,10 @@ class RunpodImplConfig(BaseModel):
         default=None,
         description="The API token",
     )
+
+    @classmethod
+    def sample_run_config(cls, **kwargs: Any) -> Dict[str, Any]:
+        return {
+            "url": "${env.RUNPOD_URL:}",
+            "api_token": "${env.RUNPOD_API_TOKEN:}",
+        }

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

@@ -8,7 +8,6 @@ from typing import AsyncGenerator
 from openai import OpenAI
 
 from llama_stack.apis.inference import *  # noqa: F403
-from llama_stack.models.llama.datatypes import Message
 
 # from llama_stack.providers.datatypes import ModelsProtocolPrivate
 from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
@@ -54,7 +53,7 @@ class RunpodInferenceAdapter(ModelRegistryHelper, Inference):
         self,
         model: str,
         content: InterleavedContent,
-        sampling_params: Optional[SamplingParams] = SamplingParams(),
+        sampling_params: Optional[SamplingParams] = None,
         response_format: Optional[ResponseFormat] = None,
         stream: Optional[bool] = False,
         logprobs: Optional[LogProbConfig] = None,
@@ -65,7 +64,7 @@ class RunpodInferenceAdapter(ModelRegistryHelper, Inference):
         self,
         model: str,
         messages: List[Message],
-        sampling_params: Optional[SamplingParams] = SamplingParams(),
+        sampling_params: Optional[SamplingParams] = None,
         response_format: Optional[ResponseFormat] = None,
         tools: Optional[List[ToolDefinition]] = None,
         tool_choice: Optional[ToolChoice] = ToolChoice.auto,
@@ -74,6 +73,8 @@ class RunpodInferenceAdapter(ModelRegistryHelper, Inference):
         logprobs: Optional[LogProbConfig] = None,
         tool_config: Optional[ToolConfig] = None,
     ) -> AsyncGenerator:
+        if sampling_params is None:
+            sampling_params = SamplingParams()
         request = ChatCompletionRequest(
             model=model,
             messages=messages,