Local GenAI LLMs with Ollama and Docker

Bret and Nirmal are joined by friend of the show, Matt Williams, to learn how to run your own local ChatGPT clone and GitHub Copilot clone with Ollama and Docker's "GenAI Stack," to build apps on top of open source LLMs.

We've designed this conversation for tech people like myself, who are no strangers to using LLMs in web products like chat GPT, but are curious about running open source generative AI models locally and how they might set up their Docker environment to develop things on top of these open source LLMs.

Matt Williams is walking us through all the parts of this solution, and with detailed explanations, shows us how Ollama can make it easier on Mac, Windows, and Linux to set up LLM stacks.

Be sure to check out the video version of this episode for any demos.

This episode is from our YouTube Live show on April 18, 2024 (Stream 262).

★Topics★

Creators & Guests

• Cristi Cotovan - Editor
• Beth Fisher - Producer
• Bret Fisher - Host
• Matt Williams - Host
• Nirmal Mehta - Host

• (00:00) - Intro
• (01:32) - Understanding LLMs and Ollama
• (03:16) - Ollama's Elevator Pitch
• (08:40) - Installing and Extending Ollama
• (17:17) - HuggingFace and Other Libraries
• (19:24) - Which Model Should You Use?
• (26:28) - Ollama and Its Applications
• (28:57) - Retrieval Augmented Generation (RAG)
• (36:44) - Deploying Models and API Endpoints
• (40:38) - DockerCon Keynote and LLM Demo
• (47:44) - Getting Started with Ollama

You can also support my free material by subscribing to my YouTube channel and my weekly newsletter at bret.news!

Grab the best coupons for my Docker and Kubernetes courses.Join my cloud native DevOps community on Discord.Grab some merch at Bret's Loot BoxHomepage bretfisher.com