phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-05 10:13:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix _client in embedding

Browse source
This commit is contained in:
raspawar 2025-04-01 11:04:54 +00:00
parent af8b4484a3
commit 29b9e819af
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -203,7 +203,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
extra_body["input_type"] = task_type_options[task_type]
try:
response = await self._client.embeddings.create(
response = await self._get_client(model).embeddings.create(
model=model,
input=input,
extra_body=extra_body,