phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

further fixes according to investigation and PR comments

Browse source
This commit is contained in:
r-bit-rry 2025-11-30 17:31:07 +02:00
parent 9b3c041af0
commit c3c9edf981
14 changed files with 212 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

14
src/llama_stack/providers/utils/inference/openai_mixin.py
View file

@ -248,30 +248,28 @@ class OpenAIMixin(NeedsRequestProviderData, ABC, BaseModel):
return model_obj.provider_resource_id
async def _maybe_overwrite_id(self, resp: Any, stream: bool | None) -> Any:
if not self.overwrite_completion_id:
return resp
new_id = f"cltsd-{uuid.uuid4()}"
if stream:
new_id = f"cltsd-{uuid.uuid4()}" if self.overwrite_completion_id else None
async def _gen():
async for chunk in resp:
chunk.id = new_id
if new_id:
chunk.id = new_id
yield chunk
return _gen()
else:
resp.id = new_id
if self.overwrite_completion_id:
resp.id = f"cltsd-{uuid.uuid4()}"
return resp
async def openai_completion(
self,
params: OpenAICompletionRequestWithExtraBody,
) -> OpenAICompletion:
) -> OpenAICompletion | AsyncIterator[OpenAICompletion]:
"""
Direct OpenAI completion API call.
"""
# TODO: fix openai_completion to return type compatible with OpenAI's API response
provider_model_id = await self._get_provider_model_id(params.model)
self._validate_model_allowed(provider_model_id)