formatting

llama_toolchain/inference/api/endpoints.py

@@ -97,27 +97,30 @@ class BatchChatCompletionResponse(BaseModel):
 
 
 class Inference(Protocol):
-
     @webmethod(route="/inference/completion")
     async def completion(
         self,
         request: CompletionRequest,
-    ) -> Union[CompletionResponse, CompletionResponseStreamChunk]: ...
+    ) -> Union[CompletionResponse, CompletionResponseStreamChunk]:
+        ...
 
     @webmethod(route="/inference/chat_completion")
     async def chat_completion(
         self,
         request: ChatCompletionRequest,
-    ) -> Union[ChatCompletionResponse, ChatCompletionResponseStreamChunk]: ...
+    ) -> Union[ChatCompletionResponse, ChatCompletionResponseStreamChunk]:
+        ...
 
     @webmethod(route="/inference/batch_completion")
     async def batch_completion(
         self,
         request: BatchCompletionRequest,
-    ) -> BatchCompletionResponse: ...
+    ) -> BatchCompletionResponse:
+        ...
 
     @webmethod(route="/inference/batch_chat_completion")
     async def batch_chat_completion(
         self,
         request: BatchChatCompletionRequest,
-    ) -> BatchChatCompletionResponse: ...
+    ) -> BatchChatCompletionResponse:
+        ...

llama_toolchain/inference/event_logger.py

@@ -7,8 +7,8 @@
 from termcolor import cprint
 
 from llama_toolchain.inference.api import (
-    ChatCompletionResponseEventType, 
-    ChatCompletionResponseStreamChunk
+    ChatCompletionResponseEventType,
+    ChatCompletionResponseStreamChunk,
 )
 
 

llama_toolchain/inference/meta_reference/inference.py

@@ -45,7 +45,6 @@ SEMAPHORE = asyncio.Semaphore(1)
 
 
 class MetaReferenceInferenceImpl(Inference):
-
     def __init__(self, config: MetaReferenceImplConfig) -> None:
         self.config = config
         model = resolve_model(config.model)

llama_toolchain/inference/ollama/ollama.py

@@ -54,7 +54,6 @@ async def get_provider_impl(
 
 
 class OllamaInference(Inference):
-
     def __init__(self, config: OllamaImplConfig) -> None:
         self.config = config
 
@@ -66,7 +65,9 @@ class OllamaInference(Inference):
         try:
             await self.client.ps()
         except httpx.ConnectError:
-            raise RuntimeError("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 shutdown(self) -> None:
         pass