fixes (#3571)

Author: tomek-labuk

app/_kong_plugins/ai-proxy/examples/azure-chat-route.yaml

@@ -24,16 +24,16 @@ weight: 900
 
 config:
   model_name_header: false
-  route_type: llm/v1/batches
+  route_type: llm/v1/chat
   auth:
     header_name: Authorization
     header_value: Bearer ${azure_key}
   model:
     provider: azure
-  options:
-    azure_api_version: "2025-01-01-preview"
-    azure_instance: ${azure_instance}
-    azure_deployment_id: ${azure_deployment}
+    options:
+      azure_api_version: "2025-01-01-preview"
+      azure_instance: ${azure_instance}
+      azure_deployment_id: ${azure_deployment}
 variables:
   azure_key:
     value: "$AZURE_OPENAI_API_KEY"

app/_landing_pages/ai-gateway.yaml

@@ -581,7 +581,7 @@ rows:
         - type: card
           config:
             title: Save LLM usage costs with semantic load balancing
-            description: Use semantic load balancing to optimize LLM usage and reduce costs by intelligently routing chat requests across multiple OpenAI models based on [semantic similarity](/ai-gateway/semantic-similarity/).
+            description: Use semantic load balancing to optimize LLM usage and reduce costs by intelligently routing chat requests across multiple OpenAI models based on semantic similarity.
             icon: /assets/icons/money.svg
             cta:
               url: /how-to/use-semantic-load-balancing