fix api to work with openapi generator

llama_toolchain/inference/api/api.py

@@ -85,6 +85,8 @@ class CompletionRequest(BaseModel):
 
 @json_schema_type
 class CompletionResponse(BaseModel):
+    """Completion response."""
+
     completion_message: CompletionMessage
     logprobs: Optional[List[TokenLogProbs]] = None
 
@@ -108,6 +110,8 @@ class BatchCompletionRequest(BaseModel):
 
 @json_schema_type
 class BatchCompletionResponse(BaseModel):
+    """Batch completion response."""
+
     completion_message_batch: List[CompletionMessage]
 
 
@@ -137,6 +141,8 @@ class ChatCompletionResponseStreamChunk(BaseModel):
 
 @json_schema_type
 class ChatCompletionResponse(BaseModel):
+    """Chat completion response."""
+
     completion_message: CompletionMessage
     logprobs: Optional[List[TokenLogProbs]] = None
 

llama_toolchain/telemetry/api/api.py

@@ -125,7 +125,7 @@ Event = Annotated[
 
 class Telemetry(Protocol):
     @webmethod(route="/telemetry/log_event")
-    async def log_event(self, event: Event): ...
+    async def log_event(self, event: Event) -> None: ...
 
     @webmethod(route="/telemetry/get_trace", method="GET")
     async def get_trace(self, trace_id: str) -> Trace: ...