phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 15:42:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

implement embedding generation in supported inference providers

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-12-09 12:48:56 -08:00
parent b896be2311
commit e167e9eb93
16 changed files with 383 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -203,4 +203,14 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
model_id: str,
contents: List[InterleavedTextMedia],
) -> EmbeddingsResponse:
raise NotImplementedError()
model = await self.model_store.get_model(model_id)
kwargs = {}
if model.metadata.get("embedding_dimensions"):
kwargs["dimensions"] = model.metadata.get("embedding_dimensions")
response = self.client.embeddings.create(
model=model.provider_resource_id, input=contents, **kwargs
)
embeddings = [data.embedding for data in response.data]
return EmbeddingsResponse(embeddings=embeddings)