<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
  xmlns:content="http://purl.org/rss/1.0/modules/content/"
  xmlns:dc="http://purl.org/dc/elements/1.1/"
  xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Browser Use Web UI - Virtually Everything: Your Guide to Virtualization</title>
    <link>https://virtualg.uk/tag/browser-use-web-ui/</link>
    <atom:link href="https://virtualg.uk/tag/browser-use-web-ui/feed/" rel="self" type="application/rss+xml" />
    <description>Browser Use Web UI</description>
    <language>en-GB</language>
    <lastBuildDate>Mon, 27 Jan 2025 01:44:35 +0000</lastBuildDate>
    <item>
      <title>Using AI to perform boring VMware vSphere tasks</title>
      <link>https://virtualg.uk/using-ai-to-perform-boring-vmware-vsphere-tasks/</link>
      <guid isPermaLink="true">https://virtualg.uk/using-ai-to-perform-boring-vmware-vsphere-tasks/</guid>
      <pubDate>Mon, 27 Jan 2025 01:44:35 +0000</pubDate>
      <dc:creator><![CDATA[Graham Barker]]></dc:creator>
      <description><![CDATA[Recently I have been thinking more and more about AI and I wondered if it was possible to use AI to automate boring administrative tasks in vSphere.First I though to use some…]]></description>
      <content:encoded><![CDATA[<p>Recently I have been thinking more and more about AI and I wondered if it was possible to use AI to automate boring administrative tasks in vSphere.<br>First I though to use some Generative AI to provide instruction on how to perform the task, but I had no way to actually get something to perform them for me.</p>



<p>Then today I discovered than you can use a tool called browser-use, combined with a model to perform tasks within a browser. </p>



<p>They way this works is you setup the browser-use system with your model of choice and API key. Then you simply provide a prompt such as "login to this URL with user X and password Y" It then launches a browser session and scans the page then injects your form details. </p>



<p>This is all basic stuff though, so I tried something more complex. I used these tools to login to the vSphere client and interact with my virtual machines but I think if you get the prompts right, you could even get vMotion to work and far more complex things including advanced configuration.<br><br>Before I run through how to set this up, take a look at the quick demo which logs into the vSphere client, deals with an SSL error, navigated around a bunch of errors in the client and then powers on a VM. The prompt for this is in the instructions below.</p>



<h2 class="wp-block-heading" id="Demo">Demo <a class="hash" href="#Demo" aria-label="Link to this section"></a></h2>



<figure class="wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio"><div class="wp-block-embed__wrapper">
https://youtu.be/DiKIQBMnrIY
</div></figure>



<h2 class="wp-block-heading" id="Setting_up_the_environment">Setting up the environment <a class="hash" href="#Setting_up_the_environment" aria-label="Link to this section"></a></h2>



<h3 class="wp-block-heading" id="Install_Python">Install Python <a class="hash" href="#Install_Python" aria-label="Link to this section"></a></h3>



<ul class="wp-block-list">
<li>Download and Install Python: <a href="https://www.python.org/downloads/" target="_blank" rel="noopener" title="">Download Python | Python.org</a></li>
</ul>



<h3 class="wp-block-heading" id="Install_Browser_Use_Web_UI">Install Browser Use Web UI <a class="hash" href="#Install_Browser_Use_Web_UI" aria-label="Link to this section"></a></h3>



<ul class="wp-block-list">
<li>Download or clone from: <a href="https://github.com/browser-use/web-ui" target="_blank" rel="noopener" title="">GitHub - browser-use/web-ui: Run AI Agent in your browser</a></li>



<li>Extract and change into the folder directory</li>



<li>Follow the instructions for <a href="https://github.com/browser-use/web-ui?tab=readme-ov-file#installation-options" target="_blank" rel="noopener" title="Option 1: Local Installation">Option 1: Local Installation</a></li>



<li>If you're using PowerShell, when instructed to run: <br><code>source .venv/bin/activate</code> <br>you will need to actually run<em>: </em><br><code><em>.venv/bin/activate</em> </code></li>
</ul>



<h3 class="wp-block-heading" id="Launch">Launch  <a class="hash" href="#Launch" aria-label="Link to this section"></a></h3>



<ul class="wp-block-list">
<li>From the same directory you have been working in, run:<br><code>python webui.py --ip 127.0.0.1 --port 7788</code></li>



<li>Open a web browser to:<br>http://127.0.0.1:7788</li>
</ul>



<figure class="wp-block-image size-large"><img src="https://virtualg.uk/wp-content/uploads/2025/01/Image-5.png" alt="" class="wp-image-23647" loading="eager" decoding="async"><figcaption class="wp-element-caption">Browser Use WebUI</figcaption></figure>



<h3 class="wp-block-heading" id="Configure_Browser_Use_Web_UI">Configure Browser Use Web UI <a class="hash" href="#Configure_Browser_Use_Web_UI" aria-label="Link to this section"></a></h3>



<ul class="wp-block-list">
<li>Open the LLM Configuration and select your model. I am using the DeepSeek Reasoner Model.</li>



<li>Locate your model's API keys</li>



<li>This will vary depending on the model you are using. 
<ul class="wp-block-list">
<li>For DeepSeek, Navigate to <a href="https://www.deepseek.com/" target="_blank" rel="noopener" title="">DeepSeek</a> and then API platform. </li>



<li>Create a new account </li>



<li>Top up  up the account with $2 to get started</li>



<li>Next go to API keys and generate a new API key</li>
</ul>
</li>



<li>Add your API key to Web UI (Under LLM Configuration)</li>



<li>Enter the Base URL for the model. For DeepSeek, this is:<br><code>https://api.deepseek.com/v1</code></li>



<li>Under Agent Settings, it is recommended to disable "Use Vision" due to compatibility issues with DeepSeek</li>
</ul>



<figure class="wp-block-image size-large"><img src="https://virtualg.uk/wp-content/uploads/2025/01/Image-3.png" alt="" class="wp-image-23645" loading="lazy" decoding="async"><figcaption class="wp-element-caption">Browser Use WebUI - LLM Configuration</figcaption></figure>



<figure class="wp-block-image size-large"><img src="https://virtualg.uk/wp-content/uploads/2025/01/Image-4.png" alt="" class="wp-image-23646" loading="lazy" decoding="async"><figcaption class="wp-element-caption">Browser Use WebUI - Agent Settings</figcaption></figure>



<h3 class="wp-block-heading" id="Performing_vSphere_Tasks">Performing vSphere Tasks <a class="hash" href="#Performing_vSphere_Tasks" aria-label="Link to this section"></a></h3>



<p>Now onto the good bit!</p>



<ul class="wp-block-list">
<li>Go to Run Agent and enter your prompt.</li>



<li>Be sure to provide the URL, user and password plus what you want it to do.</li>
</ul>



<p><strong>Task Description<br></strong>1. Open the vSphere client<br>2. Wait for the licensing banner to load<br>3. Close the licensing error banner with the x on the top right of the browser<br>4. Power on the VM using the power on icon</p>



<p><strong>Additional Information<br></strong>The vSphere client URL is: https://vcf-m01-vc01.lab.local/ui/<br>The vSphere client username is: administrator@vsphere.local<br>The vSphere client password is: Password12345!<br>The VM name is: vcf-m01-nsx01a</p>



<p>What's interesting here is in the console window you can see what the model is trying to do in plain English, then it tries that. <br>I also though it was interesting how it tried a few ways to bypass the SSL error until it finally found a good way to do it. Also sometimes it does the wrong thing (opens the wrong menu for example) but it will then close that menu and try again, a little like how a human would make a mistake and correct it.</p>



<h2 class="wp-block-heading" id="Share_your_prompts">Share your prompts! <a class="hash" href="#Share_your_prompts" aria-label="Link to this section"></a></h2>



<p>If you manage to get something interesting working such as live vMotion, advanced configurations or even a host upgrade using this method, please let me know. </p>



<p>I'd be happy to put together a library of prompts and credit you for your work.</p>



<h2 class="wp-block-heading" id="A_note_on_using_LLMs">A note on using LLMs <a class="hash" href="#A_note_on_using_LLMs" aria-label="Link to this section"></a></h2>



<p>I highly recommend doing your own research before using DeepSeek's LLMs, especially for work purposes outside of China.</p>



<p>I would also avoid this use of LLMs to orchestrate tasks in your production environment due to the obvious risks associated with it.<br></p>



<h2 class="wp-block-heading" id="One_more_thing">One more thing <a class="hash" href="#One_more_thing" aria-label="Link to this section"></a></h2>



<p>If you have found this post useful, consider joining my newsletter for updates and other useful downloads and guides &gt;&gt;&nbsp;<a href="https://virtualg.uk/subscribe/">Subscribe to the newsletter</a></p>]]></content:encoded>
    </item>
  </channel>
</rss>
