scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-08 22:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

(feat) working semantic cache on proxy

Browse source
This commit is contained in:
ishaan-jaff 2024-02-06 08:55:25 -08:00 • committed by Krrish Dholakia
parent c8d5714e59
commit e0d5c953d6
1 changed files with 6 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
litellm/proxy/proxy_config.yaml
View file

@ -73,10 +73,12 @@ litellm_settings:
max_budget: 1.5000
models: ["azure-gpt-3.5"]
duration: None
upperbound_key_generate_params:
max_budget: 100
duration: "30d"
# cache: True
cache: True # set cache responses to True
cache_params:
type: "redis-semantic"
similarity_threshold: 0.8
redis_semantic_cache_use_async: True
# cache: True
# setting callback class
# callbacks: custom_callbacks.proxy_handler_instance # sets litellm.callbacks = [proxy_handler_instance]