modified: index.html

index.html

@@ -202,6 +202,40 @@ pip install vllm
 python -m vllm.entrypoints.openai.api_server --model NousResearch/Hermes-3-Llama-3.1-8B --host 0.0.0.0 --port 18888 --max-model-len 16000
         </code></pre>
 
+	<p>If you want to see how we setup the proxy, check out <a href="https://git.unturf.com/-/snippets/3">/etc/caddy/Caddyfile</a></p>
+
+        <pre><code>
+
+ai.unturf.com {
+    root * /opt/www
+    file_server
+    log {
+        output file /var/log/caddy/ai.unturf.com.log {
+            roll_size 50mb
+            roll_keep 5
+        }
+    }
+    tls {
+        on_demand
+    }
+}
+
+hermes.ai.unturf.com {
+    reverse_proxy <removed>:18888
+    log {
+        output file /var/log/caddy/hermes.ai.unturf.com.log {
+            roll_size 50mb
+            roll_keep 5
+        }
+    }
+    tls {
+        on_demand
+    }
+}
+
+	</code></pre>
+
+        <p>We will likely implement a rate limit based on client IP address.</p>
 
 	<h2 id="client-side">Client Side Only Example, chat with this page.</h2>