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

More idiomatic REST API (#765)

Browse source 
# What does this PR do?

This PR changes our API to follow more idiomatic REST API approaches of
having paths being resources and methods indicating the action being
performed.

Changes made to generator:
1) removed the prefix check of "get" as its not required and is actually
needed for other method types too
2) removed _ check on path since variables can have "_"



## Test Plan

LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v
tests/client-sdk/agents/test_agents.py
This commit is contained in:
Dinesh Yeduguru 2025-01-15 13:20:09 -08:00 • committed by GitHub
parent 6deef1ece0
commit 7fb2c1c48d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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,