phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: remove double routes

Browse source 
We didn't follow the double route approach when we moved from
`v1/openai/v1` to `/v1`. In order to remain consistent, let's abandon
the double routes. Even if that breaks for 0.3.0. We will do the right
announcements.

Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-10-01 15:33:41 +02:00
parent 42414a1a1b
commit 084d8400b1
No known key found for this signature in database
4 changed files with 12 additions and 1396 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/apis/eval/eval.py
View file

@ -133,12 +133,6 @@ class Eval(Protocol):
"""
...
@webmethod(
route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}",
method="DELETE",
level=LLAMA_STACK_API_V1,
deprecated=True,
)
@webmethod(route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}", method="DELETE", level=LLAMA_STACK_API_V1ALPHA)
async def job_cancel(self, benchmark_id: str, job_id: str) -> None:
"""Cancel a job.
@ -148,12 +142,6 @@ class Eval(Protocol):
"""
...
@webmethod(
route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result",
method="GET",
level=LLAMA_STACK_API_V1,
deprecated=True,
)
@webmethod(
route="/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result", method="GET", level=LLAMA_STACK_API_V1ALPHA
)