From de8eae20d9b166325051366bd6731ededc7fc3df Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Tue, 20 Aug 2024 22:10:42 -0700 Subject: [PATCH] docs(caching.md): add doc on enabling caching for just rate limiting features --- docs/my-website/docs/proxy/caching.md | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/docs/my-website/docs/proxy/caching.md b/docs/my-website/docs/proxy/caching.md index 2c21b93919..e1901a2e86 100644 --- a/docs/my-website/docs/proxy/caching.md +++ b/docs/my-website/docs/proxy/caching.md @@ -185,6 +185,8 @@ $ litellm --config /path/to/config.yaml + + ## Using Caching - /chat/completions @@ -230,6 +232,22 @@ curl --location 'http://0.0.0.0:4000/embeddings' \ +## Set cache for proxy, but not on the actual llm api call + +Use this if you just want to enable features like rate limiting, and loadbalancing across multiple instances. + +Set `supported_call_types: []` to disable caching on the actual api call. + + +```yaml +litellm_settings: + cache: True + cache_params: + type: redis + supported_call_types: [] +``` + + ## Debugging Caching - `/cache/ping` LiteLLM Proxy exposes a `/cache/ping` endpoint to test if the cache is working as expected