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(caching.py): fix print statements

Browse source
This commit is contained in:
Krrish Dholakia 2024-03-14 12:58:34 -07:00
parent bdd2004691
commit d6537a05ca
3 changed files with 23 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

11
litellm/caching.py
View file

@ -142,7 +142,9 @@ class RedisCache(BaseCache):
)
except Exception as e:
# NON blocking - notify users Redis is throwing an exception
print_verbose("LiteLLM Caching: set() - Got exception from REDIS : ", e)
print_verbose(
f"LiteLLM Redis Caching: async set() - Got exception from REDIS : {str(e)}"
)
async def async_set_cache_pipeline(self, cache_list, ttl=None):
"""
@ -905,8 +907,11 @@ class Cache:
# for streaming, we use preset_cache_key. It's created in wrapper(), we do this because optional params like max_tokens, get transformed for bedrock -> max_new_tokens
if kwargs.get("litellm_params", {}).get("preset_cache_key", None) is not None:
print_verbose(f"\nReturning preset cache key: {cache_key}")
return kwargs.get("litellm_params", {}).get("preset_cache_key", None)
_preset_cache_key = kwargs.get("litellm_params", {}).get(
"preset_cache_key", None
)
print_verbose(f"\nReturning preset cache key: {_preset_cache_key}")
return _preset_cache_key
# sort kwargs by keys, since model: [gpt-4, temperature: 0.2, max_tokens: 200] == [temperature: 0.2, max_tokens: 200, model: gpt-4]
completion_kwargs = [