From 3289b9b7be17f8428c511cc78488cd4421cfdb62 Mon Sep 17 00:00:00 2001
From: "russell@unturf.com" <russell@unturf.com>
Date: Mon, 16 Feb 2026 18:03:35 -0500
Subject: [PATCH] Add qwen and qwen-vl endpoints to inference page, remove
 ai.unturf.com block

---
 public/inference.html | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/public/inference.html b/public/inference.html
index 1cfe03e..8e07fdb 100644
--- a/public/inference.html
+++ b/public/inference.html
@@ -110,11 +110,10 @@ python -m vllm.entrypoints.openai.api_server --model adamo1139/Hermes-3-Llama-3.
         <h3 id="proxy-setup">Proxy Setup</h3>
         <p>If you want to see how we setup the proxy, check out <a href="https://git.unturf.com/-/snippets/3" target="_blank">/etc/caddy/Caddyfile</a></p>
 
-        <pre><code>ai.unturf.com {
-    root * /opt/www
-    file_server
+        <pre><code>hermes.ai.unturf.com {
+    reverse_proxy &lt;removed&gt;:18888
     log {
-        output file /var/log/caddy/ai.unturf.com.log {
+        output file /var/log/caddy/hermes.ai.unturf.com.log {
             roll_size 50mb
             roll_keep 5
         }
@@ -124,10 +123,23 @@ python -m vllm.entrypoints.openai.api_server --model adamo1139/Hermes-3-Llama-3.
     }
 }
 
-hermes.ai.unturf.com {
-    reverse_proxy &lt;removed&gt;:18888
+qwen.ai.unturf.com {
+    reverse_proxy &lt;removed&gt;:18889
     log {
-        output file /var/log/caddy/hermes.ai.unturf.com.log {
+        output file /var/log/caddy/qwen.ai.unturf.com.log {
+            roll_size 50mb
+            roll_keep 5
+        }
+    }
+    tls {
+        on_demand
+    }
+}
+
+qwen-vl.ai.unturf.com {
+    reverse_proxy &lt;removed&gt;:18890
+    log {
+        output file /var/log/caddy/qwen-vl.ai.unturf.com.log {
             roll_size 50mb
             roll_keep 5
         }
@@ -157,6 +169,8 @@ speech.ai.unturf.com {
         <h4>Swagger Documentation</h4>
         <p>Access the interactive API docs at the <code>/docs</code> endpoint:</p>
         <p><a href="https://hermes.ai.unturf.com/docs" target="_blank">hermes.ai.unturf.com/docs</a> - Hermes endpoint Swagger docs</p>
+        <p><a href="https://qwen.ai.unturf.com/docs" target="_blank">qwen.ai.unturf.com/docs</a> - Qwen endpoint Swagger docs</p>
+        <p><a href="https://qwen-vl.ai.unturf.com/docs" target="_blank">qwen-vl.ai.unturf.com/docs</a> - Qwen VL endpoint Swagger docs</p>
         <p>The Swagger UI lets you explore all available endpoints, see request/response schemas, and test API calls directly in your browser.</p>
 
         <h4>Model Discovery</h4>
@@ -164,10 +178,12 @@ speech.ai.unturf.com {
         <ul>
             <li><a href="https://hermes.ai.unturf.com/v1/models" target="_blank">hermes.ai.unturf.com/v1/models</a> - Hermes models</li>
             <li><a href="https://qwen.ai.unturf.com/v1/models" target="_blank">qwen.ai.unturf.com/v1/models</a> - Qwen models</li>
+            <li><a href="https://qwen-vl.ai.unturf.com/v1/models" target="_blank">qwen-vl.ai.unturf.com/v1/models</a> - Qwen VL (vision) models</li>
         </ul>
         <p>Or via curl:</p>
         <pre><code class="language-bash">curl https://hermes.ai.unturf.com/v1/models
 curl https://qwen.ai.unturf.com/v1/models
+curl https://qwen-vl.ai.unturf.com/v1/models
 </code></pre>
 
         <p>Example response:</p>