phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

formatting

Browse source
This commit is contained in:
Dalton Flanagan 2024-08-14 14:22:25 -04:00
parent 94dfa293a6
commit b6ccaf1778
33 changed files with 110 additions and 97 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama_toolchain/inference/api/endpoints.py
View file

@ -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:
...