tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-27 18:31:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

(feat) working semantic cache on proxy

Browse Source
This commit is contained in:
ishaan-jaff
2024-02-06 13:30:59 -08:00
committed by Krrish Dholakia
parent ef32a5da1b
commit e9d00a92ed
1 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/proxy/proxy_config.yaml
+6 -4
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]