phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 21:43:55 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update way of checking available models

Browse source
This commit is contained in:
jhpiedrahitao 2025-07-10 10:30:50 -05:00
parent f844e18d47
commit d739fe77a9
2 changed files with 23 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

20
llama_stack/providers/remote/inference/sambanova/sambanova.py
View file

@ -178,6 +178,7 @@ class SambaNovaInferenceAdapter(LiteLLMOpenAIMixin):
def __init__(self, config: SambaNovaImplConfig):
self.config = config
self.environment_available_models = []
LiteLLMOpenAIMixin.__init__(
self,
model_entries=MODEL_ENTRIES,
@ -250,15 +251,18 @@ class SambaNovaInferenceAdapter(LiteLLMOpenAIMixin):
async def register_model(self, model: Model) -> Model:
model_id = self.get_provider_model_id(model.provider_resource_id)
list_models_url = self.config.url + "/models"
try:
response = requests.get(list_models_url)
response.raise_for_status()
except requests.exceptions.RequestException as e:
raise RuntimeError(f"Request to {list_models_url} failed") from e
available_models = [model.get("id") for model in response.json().get("data", {})]
if len(available_models) == 0 or model_id.split("sambanova/")[-1] not in available_models:
logger.warning(f"Model {model_id} not available in {self.config.url}/models")
if len(self.environment_available_models) == 0:
try:
response = requests.get(list_models_url)
response.raise_for_status()
except requests.exceptions.RequestException as e:
raise RuntimeError(f"Request to {list_models_url} failed") from e
self.environment_available_models = [model.get("id") for model in response.json().get("data", {})]
if model_id.split("sambanova/")[-1] not in self.environment_available_models:
logger.warning(f"Model {model_id} not available in {list_models_url}")
return model
async def initialize(self):