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

feat: introduce API leveling, post_training to v1alpha

Browse source 
Rather than have a single `LLAMA_STACK_VERSION`, we need to have a `_V1`, `_V1ALPHA`, and `_V1BETA` constant.

This also necessitated addition of `level` to the `WebMethod` so that routing can be handeled properly.

For backwards compat, the `v1` routes are being kept around and marked as `deprecated`. When used, the server will log a deprecation warning.

move:

post_training to v1alpha as it is under heavy development and not near its final state
eval: job scheduling is not implemented. Relies heavily on the datasetio API which is under development missing implementations of specific routes indicating the structure of those routes might change. Additionally eval depends on the inference API which is going to be deprecated, eval will likely need a major API surface change to conform to using completions properly

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-09-12 13:23:57 -04:00
parent a50b63906c
commit 03399cebf3
35 changed files with 1507 additions and 260 deletions
Download patch file Download diff file Expand all files Collapse all files

23
llama_stack/apis/inference/inference.py
View file

@ -21,6 +21,7 @@ from llama_stack.apis.common.content_types import ContentDelta, InterleavedConte
from llama_stack.apis.common.responses import Order
from llama_stack.apis.models import Model
from llama_stack.apis.telemetry import MetricResponseMixin
from llama_stack.apis.version import LLAMA_STACK_API_V1
from llama_stack.models.llama.datatypes import (
BuiltinTool,
StopReason,
@ -1026,7 +1027,7 @@ class InferenceProvider(Protocol):
model_store: ModelStore | None = None
@webmethod(route="/inference/completion", method="POST")
@webmethod(route="/inference/completion", method="POST", level=LLAMA_STACK_API_V1)
async def completion(
self,
model_id: str,
@ -1049,7 +1050,7 @@ class InferenceProvider(Protocol):
"""
...
@webmethod(route="/inference/batch-completion", method="POST", experimental=True)
@webmethod(route="/inference/batch-completion", method="POST", experimental=True, level=LLAMA_STACK_API_V1)
async def batch_completion(
self,
model_id: str,
@ -1070,7 +1071,7 @@ 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")
@webmethod(route="/inference/chat-completion", method="POST", level=LLAMA_STACK_API_V1)
async def chat_completion(
self,
model_id: str,
@ -1110,7 +1111,7 @@ class InferenceProvider(Protocol):
"""
...
@webmethod(route="/inference/batch-chat-completion", method="POST", experimental=True)
@webmethod(route="/inference/batch-chat-completion", method="POST", experimental=True, level=LLAMA_STACK_API_V1)
async def batch_chat_completion(
self,
model_id: str,
@ -1135,7 +1136,7 @@ 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")
@webmethod(route="/inference/embeddings", method="POST", level=LLAMA_STACK_API_V1)
async def embeddings(
self,
model_id: str,
@ -1155,7 +1156,7 @@ class InferenceProvider(Protocol):
"""
...
@webmethod(route="/inference/rerank", method="POST", experimental=True)
@webmethod(route="/inference/rerank", method="POST", experimental=True, level=LLAMA_STACK_API_V1)
async def rerank(
self,
model: str,
@ -1174,7 +1175,7 @@ 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")
@webmethod(route="/openai/v1/completions", method="POST", level=LLAMA_STACK_API_V1)
async def openai_completion(
self,
# Standard OpenAI completion parameters
@ -1225,7 +1226,7 @@ class InferenceProvider(Protocol):
"""
...
@webmethod(route="/openai/v1/chat/completions", method="POST")
@webmethod(route="/openai/v1/chat/completions", method="POST", level=LLAMA_STACK_API_V1)
async def openai_chat_completion(
self,
model: str,
@ -1281,7 +1282,7 @@ class InferenceProvider(Protocol):
"""
...
@webmethod(route="/openai/v1/embeddings", method="POST")
@webmethod(route="/openai/v1/embeddings", method="POST", level=LLAMA_STACK_API_V1)
async def openai_embeddings(
self,
model: str,
@ -1310,7 +1311,7 @@ class Inference(InferenceProvider):
- Embedding models: these models generate embeddings to be used for semantic search.
"""
@webmethod(route="/openai/v1/chat/completions", method="GET")
@webmethod(route="/openai/v1/chat/completions", method="GET", level=LLAMA_STACK_API_V1)
async def list_chat_completions(
self,
after: str | None = None,
@ -1328,7 +1329,7 @@ class Inference(InferenceProvider):
"""
raise NotImplementedError("List chat completions is not implemented")
@webmethod(route="/openai/v1/chat/completions/{completion_id}", method="GET")
@webmethod(route="/openai/v1/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.