phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-05 04:17:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore(apis): unpublish deprecated /v1/inference apis

Browse source
This commit is contained in:
Matthew Farrellee 2025-01-09 02:03:04 -05:00
parent 478b4ff1e6
commit 26f4f3fe14
6 changed files with 1286 additions and 3770 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/apis/inference/inference.py
View file

@ -1026,7 +1026,6 @@ class InferenceProvider(Protocol):
model_store: ModelStore | None = None
@webmethod(route="/inference/completion", method="POST")
async def completion(
self,
model_id: str,
@ -1049,7 +1048,6 @@ class InferenceProvider(Protocol):
"""
...
@webmethod(route="/inference/batch-completion", method="POST", experimental=True)
async def batch_completion(
self,
model_id: str,
@ -1070,7 +1068,6 @@ class InferenceProvider(Protocol):
raise NotImplementedError("Batch completion is not implemented")
return # this is so mypy's safe-super rule will consider the method concrete
@webmethod(route="/inference/chat-completion", method="POST")
async def chat_completion(
self,
model_id: str,
@ -1110,7 +1107,6 @@ class InferenceProvider(Protocol):
"""
...
@webmethod(route="/inference/batch-chat-completion", method="POST", experimental=True)
async def batch_chat_completion(
self,
model_id: str,
@ -1135,7 +1131,6 @@ class InferenceProvider(Protocol):
raise NotImplementedError("Batch chat completion is not implemented")
return # this is so mypy's safe-super rule will consider the method concrete
@webmethod(route="/inference/embeddings", method="POST")
async def embeddings(
self,
model_id: str,