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

Merge remote-tracking branch 'origin/main' into resp_branching

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-02 09:44:48 -07:00
commit c1c06e6e2f
65 changed files with 56610 additions and 61 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -1064,6 +1064,7 @@ 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,
@ -1115,6 +1116,7 @@ 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,
@ -1171,6 +1173,7 @@ 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,
@ -1200,6 +1203,7 @@ 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,
@ -1218,6 +1222,9 @@ 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.