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

feat(proxy_server.py): enable cache controls per key + no-store cache flag

Browse source
This commit is contained in:
Krrish Dholakia 2024-01-30 20:46:50 -08:00
parent 37de964da4
commit f9acad87dc
8 changed files with 108 additions and 42 deletions
Download patch file Download diff file Expand all files Collapse all files

11
litellm/utils.py
View file

@ -2217,7 +2217,7 @@ def client(original_function):
litellm.cache is not None
and str(original_function.__name__)
in litellm.cache.supported_call_types
):
) and (kwargs.get("cache", {}).get("no-store", False) != True):
litellm.cache.add_cache(result, *args, **kwargs)
# LOG SUCCESS - handle streaming success logging in the _next_ object, remove `handle_success` once it's deprecated
@ -2430,9 +2430,12 @@ def client(original_function):
# [OPTIONAL] ADD TO CACHE
if (
litellm.cache is not None
and str(original_function.__name__)
in litellm.cache.supported_call_types
(litellm.cache is not None)
and (
str(original_function.__name__)
in litellm.cache.supported_call_types
)
and (kwargs.get("cache", {}).get("no-store", False) != True)
):
if isinstance(result, litellm.ModelResponse) or isinstance(
result, litellm.EmbeddingResponse