phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-01 15:20:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

more idiomatic REST API

Browse source
This commit is contained in:
Dinesh Yeduguru 2025-01-14 14:52:32 -08:00
parent d0a25dd453
commit b438dad8d2
29 changed files with 2144 additions and 1917 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/apis/inference/inference.py
View file

@ -291,7 +291,7 @@ class ModelStore(Protocol):
class Inference(Protocol):
model_store: ModelStore
@webmethod(route="/inference/completion")
@webmethod(route="/inference/completion", method="POST")
async def completion(
self,
model_id: str,
@ -302,7 +302,7 @@ class Inference(Protocol):
logprobs: Optional[LogProbConfig] = None,
) -> Union[CompletionResponse, AsyncIterator[CompletionResponseStreamChunk]]: ...
@webmethod(route="/inference/chat-completion")
@webmethod(route="/inference/chat-completion", method="POST")
async def chat_completion(
self,
model_id: str,
@ -319,7 +319,7 @@ class Inference(Protocol):
ChatCompletionResponse, AsyncIterator[ChatCompletionResponseStreamChunk]
]: ...
@webmethod(route="/inference/embeddings")
@webmethod(route="/inference/embeddings", method="POST")
async def embeddings(
self,
model_id: str,