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

update

Browse source
This commit is contained in:
Jiayi 2025-08-20 22:08:45 -07:00
parent b58d8d8c90
commit d3782f0e3b
2 changed files with 18 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

16
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -7,7 +7,7 @@
import warnings
from collections.abc import AsyncIterator
from openai import NOT_GIVEN, APIConnectionError, BadRequestError
from openai import NOT_GIVEN, APIConnectionError
from llama_stack.apis.common.content_types import (
InterleavedContent,
@ -197,15 +197,11 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference, ModelRegistryHelper):
}
extra_body["input_type"] = task_type_options[task_type]
try:
response = await self.client.embeddings.create(
model=provider_model_id,
input=input,
extra_body=extra_body,
)
except BadRequestError as e:
raise ValueError(f"Failed to get embeddings: {e}") from e
response = await self.client.embeddings.create(
model=provider_model_id,
input=input,
extra_body=extra_body,
)
#
# OpenAI: CreateEmbeddingResponse(data=[Embedding(embedding=list[float], ...)], ...)
# ->