fix(parallel_request_limiter.py): return remaining tpm/rpm in openai-compatible way

Fixes https://github.com/BerriAI/litellm/issues/5957
This commit is contained in:
Krrish Dholakia 2024-09-28 15:56:12 -07:00
parent c0cdc6e496
commit 5222fc8e1b
4 changed files with 166 additions and 2 deletions

View file

@ -35,7 +35,13 @@ from typing_extensions import overload
import litellm
import litellm.litellm_core_utils
import litellm.litellm_core_utils.litellm_logging
from litellm import EmbeddingResponse, ImageResponse, ModelResponse, get_litellm_params
from litellm import (
EmbeddingResponse,
ImageResponse,
ModelResponse,
Router,
get_litellm_params,
)
from litellm._logging import verbose_proxy_logger
from litellm._service_logger import ServiceLogging, ServiceTypes
from litellm.caching import DualCache, RedisCache