phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 19:54:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(feat) support azure deployments for embeddings

Browse source
This commit is contained in:
ishaan-jaff 2024-02-09 16:47:01 -08:00
parent 7a194de52b
commit da4441b1fc
1 changed files with 8 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

8
litellm/proxy/proxy_server.py
View file

@ -2433,8 +2433,15 @@ async def chat_completion(
response_class=ORJSONResponse, response_class=ORJSONResponse,
tags=["embeddings"], tags=["embeddings"],
) )
@router.post(
"/openai/deployments/{model:path}/embeddings",
dependencies=[Depends(user_api_key_auth)],
response_class=ORJSONResponse,
tags=["embeddings"],
) # azure compatible endpoint
async def embeddings( async def embeddings(
request: Request, request: Request,
model: Optional[str] = None,
user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth), user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
background_tasks: BackgroundTasks = BackgroundTasks(), background_tasks: BackgroundTasks = BackgroundTasks(),
): ):
@ -2458,6 +2465,7 @@ async def embeddings(
data["model"] = ( data["model"] = (
general_settings.get("embedding_model", None) # server default general_settings.get("embedding_model", None) # server default
or user_model # model name passed via cli args or user_model # model name passed via cli args
or model # for azure deployments
or data["model"] # default passed in http request or data["model"] # default passed in http request
) )
if user_model: if user_model: