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): dual cache async_batch_get_cache fix + testing

Browse source 
this fixes a bug in usage-based-routing-v2 which was caused b/c of how the result was being returned from dual cache async_batch_get_cache. it also adds unit testing for that function (and it's sync equivalent)
This commit is contained in:
Krrish Dholakia 2024-04-19 15:03:25 -07:00
parent 3c6b6355c7
commit 01a1a8f731
8 changed files with 149 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

7
litellm/caching.py
View file

@ -1216,7 +1216,7 @@ class DualCache(BaseCache):
self.in_memory_cache.set_cache(key, redis_result[key], **kwargs)
for key, value in redis_result.items():
result[sublist_keys.index(key)] = value
result[keys.index(key)] = value
print_verbose(f"async batch get cache: cache result: {result}")
return result
@ -1266,7 +1266,6 @@ class DualCache(BaseCache):
keys, **kwargs
)
print_verbose(f"in_memory_result: {in_memory_result}")
if in_memory_result is not None:
result = in_memory_result
if None in result and self.redis_cache is not None and local_only == False:
@ -1290,9 +1289,9 @@ class DualCache(BaseCache):
key, redis_result[key], **kwargs
)
for key, value in redis_result.items():
result[sublist_keys.index(key)] = value
index = keys.index(key)
result[index] = value
print_verbose(f"async batch get cache: cache result: {result}")
return result
except Exception as e:
traceback.print_exc()