docs: Note about how/when AI requests execute

Author: theboxer

Writerside/topics/Configuration_Overview.md

@@ -53,4 +53,4 @@ Each field that you attach modAI to can have settings overrides. This means that
     <category ref="related">
         <a href="Supported-Providers.md" />
     </category>
-</seealso>
+</seealso>

Writerside/topics/Supported-Providers.md

@@ -1,10 +1,15 @@
 # Supported Providers
 
+### Executing AI requests
 <warning id="key-warning">
-    Your keys will be exposed to manager users over network requests, so it is recommended to use a site-specific key 
+    By default your keys will be exposed to manager users over network requests, so it is recommended to use a site-specific key 
     that can be easily revoked.
 </warning>
 
+Enabling system setting `modai.api.execute_on_server` will move the execution to the server side, hiding the network traffic.
+
+It can be enabled per service using `modai.api.{service}.execute_on_server}` format, for example, to enable this only for chatgpt, the setting would be: `modai.api.chatgpt.execute_on_server`.
+
 ## ChatGPT (OpenAI)
 
 ChatGPT is the default model assumed. Fill out the `modai.api.chatgpt.key` and adjust any models as desired.
@@ -58,4 +63,4 @@ Then, you for each model you want to use, set the corresponding "model" field wi
        <a href="https://docs.anthropic.com/en/docs/">Anthropic Docs</a>
        <a href="https://docs.openwebui.com">Open WebUI Docs</a>
    </category>
-</seealso>
+</seealso>