phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

feat(proxy/utils.py): return api base for request hanging alerts

Browse source
This commit is contained in:
Krrish Dholakia 2024-04-06 15:58:53 -07:00
parent b49e47b634
commit 6110d32b1c
7 changed files with 180 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

14
litellm/router.py
View file

@ -77,6 +77,13 @@ class LiteLLM_Params(BaseModel):
)
max_retries: int = 2 # follows openai default of 2
organization: Optional[str] = None # for openai orgs
## VERTEX AI ##
vertex_project: Optional[str] = None
vertex_location: Optional[str] = None
## AWS BEDROCK / SAGEMAKER ##
aws_access_key_id: Optional[str] = None
aws_secret_access_key: Optional[str] = None
aws_region_name: Optional[str] = None
def __init__(self, max_retries: Optional[Union[int, str]] = None, **params):
if max_retries is None:
@ -2263,6 +2270,13 @@ class Router:
self.model_names.append(deployment.model_name)
return
def get_deployment(self, model_id: str):
for model in self.model_list:
if "model_info" in model and "id" in model["model_info"]:
if model_id == model["model_info"]["id"]:
return model
return None
def get_model_ids(self):
ids = []
for model in self.model_list: