phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 13:49:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

address feedback

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-12-11 16:24:37 -08:00
parent e167e9eb93
commit 5821ec9ef3
12 changed files with 61 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/inline/inference/meta_reference/inference.py
View file

@ -84,7 +84,7 @@ class MetaReferenceInferenceImpl(
async def register_model(self, model: Model) -> Model:
model = await self.model_registry_helper.register_model(model)
if model.model_type == ModelType.embedding_model:
self._get_embedding_model(model.provider_resource_id)
self._load_sentence_transformer_model(model.provider_resource_id)
return model
async def completion(

6
llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py
View file

@ -48,7 +48,7 @@ class SentenceTransformersInferenceImpl(
)
async def register_model(self, model: Model) -> None:
_ = self._get_embedding_model(model.provider_resource_id)
_ = self._load_sentence_transformer_model(model.provider_resource_id)
return model
async def unregister_model(self, model_id: str) -> None:
@ -63,7 +63,7 @@ class SentenceTransformersInferenceImpl(
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> Union[CompletionResponse, AsyncGenerator]:
raise NotImplementedError("Sentence transformers don't support completion")
raise ValueError("Sentence transformers don't support completion")
async def chat_completion(
self,
@ -77,4 +77,4 @@ class SentenceTransformersInferenceImpl(
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
raise NotImplementedError("Sentence transformers don't support chat completion")
raise ValueError("Sentence transformers don't support chat completion")