Multimodal and Specialized Agents Based on Local AI

you own this product
prerequisites
Intermediate command line • Basic Docker and Docker Model Runner • Basic pi agent setup , Basic JSON and HTML, a free Token Station account
skills learned
Send images to a local multimodal model • OCR and translation in one call • build a web page from a sketch with an agent • run a domain-specialized model (MedGemma) • hybrid local-and-cloud inference through Token Station

pro $24.99 per month

  • access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
  • choose one free eBook per month to keep
  • exclusive 50% discount on all purchases
  • renews monthly, pause or cancel renewal anytime

lite $19.99 per month

  • access to all Manning books, including MEAPs!

team

5, 10 or 20 seats+ for your team - learn more


Look inside

Socratic liveProjects pair you with an AI tutor to help you learn by doing, in real time.

In this liveProject, you’ll take the company’s local AI rollout to the next level by giving its agents the ability to work with images as well as text. You’ll enhance prebuilt agents to process site photos, printed notices, and whiteboard sketches, turning visual information into useful answers and working web pages. You’ll also explore how fine-tuned open-weight models can be adapted for specialized business knowledge, and how local and cloud models can work together in a hybrid setup. By the end, you’ll have a practical path for combining private, specialized local AI with cloud models when additional capabilities are needed.

This project is a part of the series Open LLMs on Your Own Computer.
This project is designed for learning purposes and is not a complete, production-ready application or solution.

project authors

Michael Yuan
Dr. Michael Yuan is the maintainer of the open-source WasmEdge project, the most popular WebAssembly (Wasm) sandboxes for edge applications and AI agents. He is a Docker Captain and the creator of the VibeKeys series of agentic devices. Dr. Yuan holds a PhD in Astrophysics from the University of Texas at Austin.
Tony Yuan
Tony Yuan is a student at Liberal Arts and Science Academy in Austin, Texas, who loves technology and AI. He serves as the VP for the Student Council and represents the school in national Quiz Bowl and History Bowl competitions. He leads the Map Wars club to teach geopolitics to high school students. He enjoys listening to rock music and reading history books when he's not programming or studying.

prerequisites

This liveProject is for developers and IT professionals who want to use a local model’s vision capabilities and see how a small open weights model can be specialized for domain knowledge. To begin this liveProject, you will need to know the following:

TOOLS
  • Basics of JSON
  • Basics of HTML
TECHNIQUES
  • Basics of LLMs and agents

features

Self-paced
You choose the schedule and decide how much time to invest as you build your project.
Project roadmap
Each project is divided into several achievable steps.
Get Help
While within the liveProject platform, get help from fellow participants and even more help with paid sessions with our expert mentors.
Compare with others
For each step, compare your deliverable to the solutions by the author and other participants.
books included as resources
Get full access to select books for 90 days. Permanent access to excerpts from Manning products are also included, as well as references to other resources.
choose your plan

team

monthly
annual
$49.99
$499.99
only $41.67 per month
  • five seats for your team
  • access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
  • choose another free product every time you renew
  • choose twelve free products per year
  • exclusive 50% discount on all purchases
  • renews monthly, pause or cancel renewal anytime
  • renews annually, pause or cancel renewal anytime
  • Multimodal and Specialized Agents Based on Local AI project for free