From e9d00a92edafa8ddbddd24e0176348f30080a039 Mon Sep 17 00:00:00 2001
From: ishaan-jaff <ishaanjaffer0324@gmail.com>
Date: Tue, 6 Feb 2024 08:55:25 -0800
Subject: [PATCH] (feat) working semantic cache on proxy

---
 litellm/proxy/proxy_config.yaml | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/litellm/proxy/proxy_config.yaml b/litellm/proxy/proxy_config.yaml
index bd844bd7ba..41c3b41828 100644
--- a/litellm/proxy/proxy_config.yaml
+++ b/litellm/proxy/proxy_config.yaml
@@ -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]