Forget using public generative AI resources like ChatGPT. Use local large language models (LLMs) instead which allows you to create a private AI server. In the video, we step through setting up a private AI server in Windows Subsystem for Linux and a few hacks that need to happen so that your API can be accessible to the open source frontend called Open WebUI.

Written post on the steps: https://www.virtualizationhowto.com/2...

Ollama download: https://ollama.com/download
LM Studio: https://lmstudio.ai/

★ Subscribe to the channel:    / @virtualizationhowto  
★ My blog: https://www.virtualizationhowto.com
★ Twitter:   / vspinmaster  
★ LinkedIn:   / brandonleevht  
★ Github: https://github.com/brandonleegit
★ Facebook:   / 100092747277326  
★ Discord:   / discord  
★ Pinterest:   / brandonleevht  

Introduction 0:00
What are Large Language Models (LLMs) 0:45
Advantages of hosting LLMs locally 1:30
Hardware to run LLMs on your own hardware 2:30
Setting up Ollama 3:18
Looking at the Linux script for Ollama 3:40
Downloading and running popular LLM models 4:18
Command to download LLAMA3 language model 4:31
Initiating a chat session from the WSL terminal 5:16
Looking at Hugging Face open source models 5:46
Open WebUI web frontend for private AI servers 6:20
Looking at the Docker run command for Open WebUI 6:50
Accessing, signing up, and tweaking settings in Open WebUI 7:22
Reviewing the architecture of the private AI solution 7:38
Talking about a hack for WSL to allow traffic from outside WSL to connect 7:54
Looking at the netsh command for the port proxy 8:24
Chatting with the LLM using Open WebUI 9:00
Writing an Ansible Playbook 9:20
PowerCLI scripts 9:29
Overview of LM Studio 9:42
Business use cases for local LLMs 10:16
Wrapping up and final thoughts 10:51