phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 04:23:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: OpenAI API - together.ai extra usage chunks

Browse source 
This fixes an issue where, with some models (ie the Llama 4 models),
together.ai is sending a final usage chunk for streaming responses
even if the user didn't ask to include usage.

With this change, the OpenAI API verification tests now pass 100% when
using Llama Stack as your API server and together.ai as the backend
provider.

As part of this, I also cleaned up the streaming/non-streaming return
types of the `openai_chat_completion` method to keep type checking happy.

Signed-off-by: Ben Browning <bbrownin@redhat.com>
This commit is contained in:
Ben Browning 2025-04-12 17:27:43 -04:00
parent a4b573d750
commit c014571258
12 changed files with 153 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

20
llama_stack/apis/inference/inference.py
View file

@ -674,6 +674,24 @@ class OpenAIChatCompletion(BaseModel):
model: str
@json_schema_type
class OpenAIChatCompletionChunk(BaseModel):
"""Chunk from a streaming response to an OpenAI-compatible chat completion request.
:param id: The ID of the chat completion
:param choices: List of choices
:param object: The object type, which will be "chat.completion.chunk"
:param created: The Unix timestamp in seconds when the chat completion was created
:param model: The model that was used to generate the chat completion
"""
id: str
choices: List[OpenAIChoice]
object: Literal["chat.completion.chunk"] = "chat.completion.chunk"
created: int
model: str
@json_schema_type
class OpenAICompletionLogprobs(BaseModel):
"""The log probabilities for the tokens in the message from an OpenAI-compatible completion response.
@ -954,7 +972,7 @@ class Inference(Protocol):
top_logprobs: Optional[int] = None,
top_p: Optional[float] = None,
user: Optional[str] = None,
) -> OpenAIChatCompletion:
) -> Union[OpenAIChatCompletion, AsyncIterator[OpenAIChatCompletionChunk]]:
"""Generate an OpenAI-compatible chat completion for the given messages using the specified model.
:param model: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint.