phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(utils.py): exclude s3 caching from individual item caching for embedding list

Browse source 
can't bulk upload to s3, so this will slow down calls

https://github.com/BerriAI/litellm/pull/1417
This commit is contained in:
Krrish Dholakia 2024-01-13 16:19:30 +05:30
parent fb53d18d6a
commit 3c02ad8b95
2 changed files with 14 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

14
litellm/utils.py
View file

@ -53,6 +53,7 @@ from .integrations.litedebugger import LiteDebugger
from .proxy._types import KeyManagementSystem
from openai import OpenAIError as OriginalError
from openai._models import BaseModel as OpenAIObject
from .caching import S3Cache
from .exceptions import (
AuthenticationError,
BadRequestError,
@ -2338,6 +2339,10 @@ def client(original_function):
call_type == CallTypes.aembedding.value
and cached_result is not None
and isinstance(cached_result, list)
and litellm.cache is not None
and not isinstance(
litellm.cache.cache, S3Cache
) # s3 doesn't support bulk writing. Exclude.
):
remaining_list = []
non_null_list = []
@ -2458,8 +2463,13 @@ def client(original_function):
if isinstance(result, litellm.ModelResponse) or isinstance(
result, litellm.EmbeddingResponse
):
if isinstance(result, EmbeddingResponse) and isinstance(
kwargs["input"], list
if (
isinstance(result, EmbeddingResponse)
and isinstance(kwargs["input"], list)
and litellm.cache is not None
and not isinstance(
litellm.cache.cache, S3Cache
) # s3 doesn't support bulk writing. Exclude.
):
asyncio.create_task(
litellm.cache.async_add_cache_pipeline(