From b70640e969d34e978033d807b362c532b509fe55 Mon Sep 17 00:00:00 2001
From: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Date: Mon, 2 Oct 2023 12:25:01 -0700
Subject: [PATCH] Update README.md

---
 README.md | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index d1f480079..2aed37263 100644
--- a/README.md
+++ b/README.md
@@ -74,18 +74,31 @@ for chunk in result:
 
 
 ## Caching ([Docs](https://docs.litellm.ai/docs/caching/))
-LiteLLM supports caching `completion()` and `embedding()` calls for all LLMs
+
+LiteLLM supports caching `completion()` and `embedding()` calls for all LLMs. [Hosted Cache LiteLLM API](https://docs.litellm.ai/docs/caching/caching_api)
 ```python
 import litellm
 from litellm.caching import Cache
-litellm.cache = Cache() # init cache to use api.litellm.ai
+import os
 
-# stores this response in cache
+litellm.cache = Cache()
+os.environ['OPENAI_API_KEY'] = ""
+# add to cache
 response1 = litellm.completion(
-    model="gpt-3.5-turbo", 
-    messages=[{"role": "user", "content": "Tell me a joke."}]
+    model="gpt-3.5-turbo",
+    messages=[{"role": "user", "content": "why is LiteLLM amazing?"}], 
     caching=True
 )
+# returns cached response
+response2 = litellm.completion(
+    model="gpt-3.5-turbo", 
+    messages=[{"role": "user", "content": "why is LiteLLM amazing?"}], 
+    caching=True
+)
+
+print(f"response1: {response1}")
+print(f"response2: {response2}")
+
 ```
 
 ## OpenAI Proxy Server ([Docs](https://docs.litellm.ai/docs/proxy_server))