---
title: "Comment by VP on \"APEX in the AI era\" | Hashnode"
description: "Hello, This is an awesome post. I tried it but stuck in the Ngrok part. The Ngrok base URL is not running in Postman. getting 403 - forbidden error. Can we run"
url: "https://hashnode.com/posts/apex-in-the-ai-era/6675441af23a55ec76b77357/comment/667bc1c0fc96802cf9a0dd4e"
---

[Discussion](https://hashnode.com/posts/apex-in-the-ai-era/6675441af23a55ec76b77357)

Comment [APEX in the AI era](https://hashnode.com/posts/apex-in-the-ai-era/6675441af23a55ec76b77357)

[VP](https://hashnode.com/@vandanapatel12)

[Jun 26, 2024](https://hashnode.com/posts/apex-in-the-ai-era/6675441af23a55ec76b77357/comment/667bc1c0fc96802cf9a0dd4e)

Hello, This is an awesome post. I tried it but stuck in the Ngrok part. The Ngrok base URL is not running in Postman. getting 403 - forbidden error. Can we run the Base URL of Ngrok in POSTMAN? In the APEX part, I configured it and then created a button to invoke the Chatbox. Invoking is working fine but when we enter a Prompt then it gives this error "Generative Al Service with given ID or static ID not found."

[Plamen Mushkov](https://hashnode.com/@plamen9)

[Jun 28, 2024](https://hashnode.com/posts/apex-in-the-ai-era/6675441af23a55ec76b77357/comment/667bc1c0fc96802cf9a0dd4e#reply-667e8e9294c3a42bf4cd2200)

The Ngrok setup first:

Try adding the `host_header` when starting Ngrok: `ngrok http [127.0.0.1](http://127.0.0.1:11434/) --host-header '127.0.0.1:11434'`

After starting the tunnel, open the Ngrok URL in the browser and when displayed a default page, click on "**Visit Site**" button. It only need to be done once.

If the above doesn't work, you can try to run it using a **.yml** file - here is the documentation ([ngrok.com/docs/guides/site-to-site-apis-mtls](https://ngrok.com/docs/guides/site-to-site-apis-mtls/#update-ngrokyml)).

The file will look like this:

```
version: 2
authtoken: YOUR-AUTH-TOKEN
tunnels:
  ollama:
    proto: http
    addr: http://127.0.0.1:11434/
    host_header: 127.0.0.1:11434
```

Pay attention to the `host_header` part - it should fix your 403 error.

As to Ollama, run `ollama list` in the Terminal. You will get a list of your models. You can get the Model name from there and use it in your APEX AI Services configuration. This should resolve your second problem. When using the newly configured AI Service for the AI Assistant component for example, it is a drop down menu, you can't enter a wrong name.