phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-09 13:14:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

test

Browse source 
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-10-08 13:46:44 -07:00
parent 96886afaca
commit 0424e33172
205 changed files with 71717 additions and 2042 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/utils/inference/litellm_openai_mixin.py
View file

@ -299,6 +299,7 @@ class LiteLLMOpenAIMixin(
top_logprobs: int | None = None,
top_p: float | None = None,
user: str | None = None,
**kwargs: Any,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
# Add usage tracking for streaming when telemetry is active
from llama_stack.providers.utils.telemetry.tracing import get_current_span
@ -335,6 +336,7 @@ class LiteLLMOpenAIMixin(
user=user,
api_key=self.get_api_key(),
api_base=self.api_base,
**kwargs,
)
return await litellm.acompletion(**params)

6
llama_stack/providers/utils/inference/openai_mixin.py
View file

@ -313,6 +313,7 @@ class OpenAIMixin(NeedsRequestProviderData, ABC, BaseModel):
top_logprobs: int | None = None,
top_p: float | None = None,
user: str | None = None,
**kwargs: Any,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
"""
Direct OpenAI chat completion API call.
@ -361,7 +362,10 @@ class OpenAIMixin(NeedsRequestProviderData, ABC, BaseModel):
user=user,
)
resp = await self.client.chat.completions.create(**params)
# Pass any additional provider-specific parameters as extra_body
extra_body = kwargs if kwargs else {}
resp = await self.client.chat.completions.create(**params, extra_body=extra_body)
return await self._maybe_overwrite_id(resp, stream) # type: ignore[no-any-return]