phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(router.py): adding support for async completion calls

Browse source 
https://github.com/BerriAI/litellm/issues/676
This commit is contained in:
Krrish Dholakia 2023-10-24 17:20:19 -07:00
parent da1defb7cf
commit 3477486886
2 changed files with 46 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

16
litellm/router.py
View file

@ -54,7 +54,6 @@ class Router:
messages: List[Dict[str, str]],
is_retry: Optional[bool] = False,
is_fallback: Optional[bool] = False,
is_async: Optional[bool] = False,
**kwargs):
"""
Example usage:
@ -68,6 +67,19 @@ class Router:
data["caching"] = self.cache_responses
# call via litellm.completion()
return litellm.completion(**{**data, **kwargs})
async def acompletion(self,
model: str,
messages: List[Dict[str, str]],
is_retry: Optional[bool] = False,
is_fallback: Optional[bool] = False,
**kwargs):
# pick the one that is available (lowest TPM/RPM)
deployment = self.get_available_deployment(model=model, messages=messages)
data = deployment["litellm_params"]
data["messages"] = messages
data["caching"] = self.cache_responses
return await litellm.acompletion(**{**data, **kwargs})
def text_completion(self,
model: str,
@ -83,6 +95,7 @@ class Router:
data = deployment["litellm_params"]
data["prompt"] = prompt
data["caching"] = self.cache_responses
# call via litellm.completion()
return litellm.text_completion(**{**data, **kwargs})
@ -96,6 +109,7 @@ class Router:
data = deployment["litellm_params"]
data["input"] = input
data["caching"] = self.cache_responses
# call via litellm.embedding()
return litellm.embedding(**{**data, **kwargs})