phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-01 04:24:32 +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

4
llama_stack/apis/batch_inference/batch_inference.py
View file

@ -54,7 +54,7 @@ class BatchChatCompletionResponse(BaseModel):
@runtime_checkable
class BatchInference(Protocol):
@webmethod(route="/batch-inference/completion")
@webmethod(route="/batch-inference/completion", method="POST")
async def batch_completion(
self,
model: str,
@ -63,7 +63,7 @@ class BatchInference(Protocol):
logprobs: Optional[LogProbConfig] = None,
) -> BatchCompletionResponse: ...
@webmethod(route="/batch-inference/chat-completion")
@webmethod(route="/batch-inference/chat-completion", method="POST")
async def batch_chat_completion(
self,
model: str,