phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 10:44:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(main.py): support custom pricing for embedding calls

Browse source
This commit is contained in:
Krrish Dholakia 2024-01-22 12:10:53 -08:00
parent 39a1b4c3b5
commit 2ce4258cc0
2 changed files with 34 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/utils.py
View file

@ -2371,7 +2371,9 @@ def client(original_function):
result._hidden_params["model_id"] = kwargs.get("model_info", {}).get(
"id", None
)
if isinstance(result, ModelResponse):
if isinstance(result, ModelResponse) or isinstance(
result, EmbeddingResponse
):
result._response_ms = (
end_time - start_time
).total_seconds() * 1000 # return response latency in ms like openai