[APIM] Update llm cache example

Author: dlepow

articles/api-management/llm-semantic-cache-lookup-policy.md

@@ -71,7 +71,7 @@ Use the `llm-semantic-cache-lookup` policy to perform cache lookup of responses
 
 ### Example with corresponding llm-semantic-cache-store policy
 
-[!INCLUDE [api-management-semantic-cache-example](../../includes/api-management-semantic-cache-example.md)]
+[!INCLUDE [api-management-llm-semantic-cache-example](../../includes/api-management-llm-semantic-cache-example.md)]
 
 ## Related policies
 

articles/api-management/llm-semantic-cache-store-policy.md

@@ -54,7 +54,7 @@ The `llm-semantic-cache-store` policy caches responses to chat completion API an
 
 ### Example with corresponding llm-semantic-cache-lookup policy
 
-[!INCLUDE [api-management-semantic-cache-example](../../includes/api-management-semantic-cache-example.md)]
+[!INCLUDE [api-management-llm-semantic-cache-example](../../includes/api-management-llm-semantic-cache-example.md)]
 
 ## Related policies
 

includes/api-management-llm-semantic-cache-example.md

@@ -0,0 +1,27 @@
+---
+author: dlepow
+ms.service: azure-api-management
+ms.custom:
+  - build-2024
+ms.topic: include
+ms.date: 08/21/2024
+ms.author: danlep
+---
+
+```xml
+<policies>
+    <inbound>
+        <base />
+        <llm-semantic-cache-lookup
+            score-threshold="0.05"
+            embeddings-backend-id ="azure-openai-backend"
+            embeddings-backend-auth ="system-assigned" >
+            <vary-by>@(context.Subscription.Id)</vary-by>
+        </azure-openai-semantic-cache-lookup>
+    </inbound>
+    <outbound>
+        <azure-openai-semantic-cache-store duration="60" />
+        <base />
+    </outbound>
+</policies>
+```