diff --git a/doc/source/conf.py b/doc/source/conf.py
index 2d477c6387fd..d1641e665063 100644
--- a/doc/source/conf.py
+++ b/doc/source/conf.py
@@ -243,7 +243,6 @@ def __init__(self, version: str):
     "ray-overview/examples/llamafactory-llm-fine-tune/README.ipynb",
     "ray-overview/examples/llamafactory-llm-fine-tune/**/*.ipynb",
     "serve/tutorials/asynchronous-inference/content/asynchronous-inference.ipynb",
-    "serve/tutorials/asynchronous-inference/content/README.md",
     # Legacy/backward compatibility
     "ray-overview/examples/**/README.md",
     "train/examples/**/README.md",
diff --git a/doc/source/serve/tutorials/asynchronous-inference/content/README.md b/doc/source/serve/tutorials/asynchronous-inference/content/README.md
index 1d3fad1e1082..fb85c632099b 100644
--- a/doc/source/serve/tutorials/asynchronous-inference/content/README.md
+++ b/doc/source/serve/tutorials/asynchronous-inference/content/README.md
@@ -1,3 +1,6 @@
+---
+orphan: true
+---
 # Asynchronous Inference with Ray Serve
 
 **⏱️ Time to complete:** 30 minutes
@@ -54,14 +57,14 @@ Redis serves as both the message broker (task queue) and result backend.
 **Install and start Redis (Google Colab compatible):**
 
 
-```python
+```bash
 # Install and start Redis server
-!sudo apt-get update -qq
-!sudo apt-get install -y redis-server
-!redis-server --port 6399 --save "" --appendonly no --daemonize yes
+sudo apt-get update -qq
+sudo apt-get install -y redis-server
+redis-server --port 6399 --save "" --appendonly no --daemonize yes
 
 # Verify Redis is running
-!redis-cli -p 6399 ping
+redis-cli -p 6399 ping
 ```
 
 **Alternative methods:**
@@ -74,7 +77,7 @@ Redis serves as both the message broker (task queue) and result backend.
 
 
 ```python
-!pip install -q ray[serve-async-inference]>=2.50.0 requests>=2.31.0 PyPDF2>=3.0.0 celery[redis]
+pip install -q ray[serve-async-inference]>=2.50.0 requests>=2.31.0 PyPDF2>=3.0.0 celery[redis]
 ```
 
 ## Step 3: Start the Ray Serve Application