phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore!: add double routes for v1/openai/v1 (#3636)

Browse source 
So that users get a warning in 0.3.0 and we remove them in 0.4.0.

Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-10-02 16:11:05 +02:00 • committed by Raghotham Murthy
parent 67fa616c51
commit 856de66231
11 changed files with 12768 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/apis/inference/inference.py
View file

@ -1066,6 +1066,7 @@ class InferenceProvider(Protocol):
raise NotImplementedError("Reranking is not implemented")
return # this is so mypy's safe-super rule will consider the method concrete
@webmethod(route="/openai/v1/completions", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
@webmethod(route="/completions", method="POST", level=LLAMA_STACK_API_V1)
async def openai_completion(
self,
@ -1117,6 +1118,7 @@ class InferenceProvider(Protocol):
"""
...
@webmethod(route="/openai/v1/chat/completions", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
@webmethod(route="/chat/completions", method="POST", level=LLAMA_STACK_API_V1)
async def openai_chat_completion(
self,
@ -1173,6 +1175,7 @@ class InferenceProvider(Protocol):
"""
...
@webmethod(route="/openai/v1/embeddings", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
@webmethod(route="/embeddings", method="POST", level=LLAMA_STACK_API_V1)
async def openai_embeddings(
self,
@ -1202,6 +1205,7 @@ class Inference(InferenceProvider):
- Embedding models: these models generate embeddings to be used for semantic search.
"""
@webmethod(route="/openai/v1/chat/completions", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
@webmethod(route="/chat/completions", method="GET", level=LLAMA_STACK_API_V1)
async def list_chat_completions(
self,
@ -1220,6 +1224,9 @@ class Inference(InferenceProvider):
"""
raise NotImplementedError("List chat completions is not implemented")
@webmethod(
route="/openai/v1/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True
)
@webmethod(route="/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1)
async def get_chat_completion(self, completion_id: str) -> OpenAICompletionWithInputMessages:
"""Describe a chat completion by its ID.