Remove async from function signature to avoid blocking the server

abetlen · abetlen · commit 213cc5c34082 · 2023-04-11T11:54:31.000-04:00
diff --git a/llama_cpp/server/__main__.py b/llama_cpp/server/__main__.py
@@ -196,7 +196,7 @@ class Config:
     "/v1/chat/completions",
     response_model=CreateChatCompletionResponse,
 )
-async def create_chat_completion(
+def create_chat_completion(
     request: CreateChatCompletionRequest,
 ) -> Union[llama_cpp.ChatCompletion, EventSourceResponse]:
     completion_or_chunks = llama.create_chat_completion(

Original file line number	Diff line number	Diff line change
`@@ -196,7 +196,7 @@ class Config:`
`196`	`196`	`"/v1/chat/completions",`
`197`	`197`	`response_model=CreateChatCompletionResponse,`
`198`	`198`	`)`
`199`		`-async def create_chat_completion(`
	`199`	`+def create_chat_completion(`
`200`	`200`	`request: CreateChatCompletionRequest,`
`201`	`201`	`) -> Union[llama_cpp.ChatCompletion, EventSourceResponse]:`
`202`	`202`	`completion_or_chunks = llama.create_chat_completion(`