Building an Image 2 Text LLM System with MiniCPM & LLaVA | Easy No-Code Ollama + Docker + Open WebUI

In this video, I dive into the world of multimodal Large Language Models (LLMs) with a focus on two powerful models: MiniCPM (8B parameters) and LLaVA (13B parameters). I start by explaining how multimodal LLMs work and explore some of their key use cases in various industries, including construction.

I then introduce the system I’m building, structured around three key pillars:
1. Ollama – A versatile platform for deploying LLMs.
2. Docker Desktop – A containerization tool that simplifies application deployment.
3. Open WebUI – A user-friendly interface for running different LLMs.

In the video, I walk you through the step-by-step installation of each component. First, I show you how to install Ollama on Linux, then cover how to set up Docker Desktop on Linux by installing Docker Engine. Next, I explain how to install Open WebUI, including how to load models from HuggingFace and Ollama, and how to start a chat with various LLMs.

In the final part of the video, I showcase the deployment of the entire system. I demonstrate the performance of both multimodal LLMs in interpreting text from images and understanding the image context. I also explore some useful applications within the construction industry.

This system is low-code to no-code, making it easy for anyone to deploy without any coding experience. Plus, it’s free to use!

🔍 Agenda:
⚫00:13 Intro
⚫00:52 Use Cases
⚫01:34 Installing Ollama
⚫03:22 Installing Docker
⚫07:17 Installing Open WebUI
⚫12:39 System Deployment
⚫19:38 Outro

👨‍💻 Whether you're an LLM developer or an APC candidate, this video breaks down the entire process from dataset conversion to model deployment, helping you achieve accurate, fine-tuned results.

👍 Don’t forget to subscribe to APC Mastery Path on YouTube for more insights, tips, and tutorials on mastering your APC journey!

🔔 Don’t forget to like, subscribe, and hit the notification bell to stay updated with the latest tutorials and insights into AI, APC exam preparation, and LLM development!
🔗 General Links & Resources:

📽️Useful videos:

📝Prerequisites & Dependencies:

📚Github & Huggingface repositories:

#MultimodalLLMs #MiniCPM #LLaVA #Ollama #Docker #OpenWebUI #LowCode #NoCode #AIinConstruction #AIinConstruction #LLMFineTuning #RICSAPC #Unsloth #Mistral7b #Gemma2 #Llama31 #AIMastery #APCMasteryPath #OpenWebUI #APCTraining #Llama3.1 #Unsloth #LLMFineTuning #OpenWebUI #Huggingface #RICSAPC #BoQCodification #NRM1 #ChatbotDevelopment #AITraining #QuantitySurveying