phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 19:24:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(refactor) - caching use separate files for each cache class (#6251)

Browse source 
* fix remove qdrant semantic caching to it's own folder

* refactor use 1 file for s3 caching

* fix use sep files for in mem and redis caching

* fix refactor caching

* add readme.md for caching folder
This commit is contained in:
Ishaan Jaff 2024-10-16 13:17:21 +05:30 • committed by GitHub
parent 773795e981
commit e79136f481
11 changed files with 2339 additions and 2159 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/caching/caching_handler.py
View file

@ -7,6 +7,10 @@ This exposes two methods:
This file is a wrapper around caching.py
This class is used to handle caching logic specific for LLM API requests (completion / embedding / text_completion / transcription etc)
It utilizes the (RedisCache, s3Cache, RedisSemanticCache, QdrantSemanticCache, InMemoryCache, DiskCache) based on what the user has setup
In each method it will call the appropriate method from caching.py
"""