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 /v1/inference/completion and implementations

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-30 03:46:07 -04:00
parent 606f4cf281
commit 4b641d7127
78 changed files with 16143 additions and 17755 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -1008,28 +1008,7 @@ class InferenceProvider(Protocol):
model_store: ModelStore | None = None
async def completion(
self,
model_id: str,
content: InterleavedContent,
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
) -> CompletionResponse | AsyncIterator[CompletionResponseStreamChunk]:
"""Generate a completion for the given content using the specified model.
:param model_id: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint.
:param content: The content to generate a completion for.
:param sampling_params: (Optional) Parameters to control the sampling strategy.
:param response_format: (Optional) Grammar specification for guided (structured) decoding.
:param stream: (Optional) If True, generate an SSE event stream of the response. Defaults to False.
:param logprobs: (Optional) If specified, log probabilities for each token position will be returned.
:returns: If stream=False, returns a CompletionResponse with the full completion.
If stream=True, returns an SSE event stream of CompletionResponseStreamChunk.
"""
...
@webmethod(route="/inference/chat-completion", method="POST", level=LLAMA_STACK_API_V1)
async def chat_completion(
self,
model_id: str,