Get Ready for My WCUS 2025 Workshop: Set Up Your Local AI-Powered WordPress Environment

A man and woman sitting at a desk

If you’re joining my Scalable, Ethical AI workshop at WordCamp US 2025, we’re going hands-on with building privacy-friendly, locally-powered AI workflows right inside WordPress.  By the end of the workshop, you’ll leave knowing how to own both your content and your AI.

This guide will help you prepare your laptop ahead of time so you can spend less time troubleshooting and more time experimenting with tools like ClassifAI and Ollama.  By doing this setup in advance, you’ll spend more time exploring the features and asking questions and less time downloading files during the workshop.

Step 1. Set Up Your Local WordPress Environment

The fastest way to get started is with tools like WordPress Studio, LocalWP, or DevKinsta that spin up a fully functional local site in minutes.  If you’ve got something else you like/use, then by all means use that!

  • Download and install WordPress 6.8 (PHP 8.1 or newer recommended)
  • Create a new local site
  • Confirm you can log into your WordPress dashboard

Step 2. Install the ClassifAI Plugin

ClassifAI is the AI integration plugin we’ll use throughout the workshop.

  • Download it from classifaiplugin.com
  • Or grab it directly from GitHub
  • Upload and install via Plugins → Add New
  • We’ll activate and configure it together during the workshop, but feel free to test it out before then!

Step 3. Install Ollama for Local AI Models

We’ll use Ollama to run AI models locally, keeping your content private and your workflows fully under your control.

  1. Download and install Ollama for your operating system.
  2. Pre-pull the four models we’ll use in the workshop:
ollama pull qwen2.5:3b-instruct-q4_0
ollama pull phi3:mini
ollama pull all-minilm:l6-v2
ollama pull moondream:v2

Step 4. (Optional) Configure ClassifAI to Use Ollama

We’ll work through this during the workshop, but if you’re wanting to get ahead of things then feel free to set up these features.  Once ClassifAI and Ollama are installed, we’ll connect each feature to a local model:

FeatureModelPurpose
Content Generationqwen2.5:3b-instruct-q4_0Drafts high-quality content locally
Title Generationphi3:miniSEO-friendly, engaging post titles
Excerpt Generationphi3:miniClean, concise summaries
Content Resizingphi3:miniExpand or condense paragraphs on demand
Key Takeawaysphi3:miniExtract key insights automatically
Classificationall-minilm:l6-v2Suggests categories and tags locally
Alt Text Generationmoondream:v2Privacy-safe image descriptions

Step 5. Test Your Setup

To confirm everything is working:

ollama run phi3:mini "Hello from WCUS workshop setup"

The above should respond with a simple message from Ollama (via the phi3:mini model), though in my testing it will almost certainly NOT get the WCUS acronym correct ;).

If you did the optional ClassifAI configurations in Step 4, then test those are working as expected:

  1. Create a new draft post in WordPress.
  2. Use Title Generation or Content Generation from ClassifAI.
  3. Verify that a response comes back successfully.
  4. If something isn’t working, try restarting Ollama:
ollama run

Step 6. (Optional) Load Sample Content

If you’d like extra material to test during the workshop, you can download the sample content that I’ve assembled.  I’ll provide USB drives with this sample posts, images, and taxonomy terms on the day of the workshop as well.

To load them:

  • Go to Tools → Import → WordPress
  • Upload the provided XML file
  • Import posts, pages, and media assets

Additional Resources

  • ClassifAI – Local Media HTTP: a small ClassifAI extension to serve attachments over http on .local sites
  • ClassifAI – Ollama Timeout: a small ClassifAI extension to increase the HTTP timeout for requests to Ollama on localhost
  • WordPress AI team: whether you’re an engineer, designer, researcher, or just curious about AI, we’d love to have you involved as we shape the future of AI in WordPress

See You at WCUS!

I can’t wait to connect with folks in-person at WordCamp US 2025 and dig into how we can own our content and our AI using WordPress, ClassifAI, and locally-powered workflows.

Whether you’re a developer, editor, or site owner, you’ll hopefully leave the workshop with a hands-on understanding of how to bring scalable, ethical AI into your publishing stack without handing your data over to external platforms.

Likes, Bookmarks, and Reposts

  • James

Comments

4 responses to “Get Ready for My WCUS 2025 Workshop: Set Up Your Local AI-Powered WordPress Environment”

  1. Thanks to everyone who came to my workshop at WordCamp US 2025, Scalable, Ethical AI: How to Own Your Content and Your AI with WordPress.…

  2. […] missed the workshop or had troubles following along (sorry!), then below are my slides as well as a reference to the prerequisite setup steps to be prepared for the […]

  3. Deepak Gupta

    I ran a few tests and found that Ollama’s response time on my local machine was too slow, often leading to timeout errors during content generation.

    To keep things reliable, I moved to Ollama’s cloud setup and switched from qwen2.5:3b-instruct-q4_0 to the much larger qwen3-next:80b-cloud model, which delivers significantly faster and more consistent results for my workflow.

    1. jeffpaul

      Deepak – Note that the models I used at WCUS 2025 were purposely smaller to make downloading locally reasonable and thus are going to be underperformant compared to larger models, let along the time since WCUS 2025 will mean that newer, larger models will almost certainly show faster, better results.  If you have any feedback on the Ollama cloud connection, I’d love input on https://github.com/10up/classifai/issues/891 to help drive insights in how we can best support that within ClassifAI.

Leave a Reply to Deepak GuptaCancel reply