phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 23:13:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

query_available_models() -> list[str] -> check_model_availability(model) -> bool

Browse source
This commit is contained in:
Matthew Farrellee 2025-07-14 19:20:15 -04:00
parent c2ab8988e6
commit f69ae45127
2 changed files with 10 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -89,9 +89,14 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
self._config = config
async def query_available_models(self) -> list[str]:
"""Query available models from the NVIDIA API."""
return [model.id async for model in self._get_client().models.list()]
async def check_model_availability(self, model: str) -> bool:
"""Check if a specific model is available from the NVIDIA API."""
try:
await self._get_client().models.retrieve(model)
return True
except Exception:
# If we can't retrieve the model, it's not available
return False
@lru_cache # noqa: B019
def _get_client(self, provider_model_id: str | None = None) -> AsyncOpenAI: