Local GenAI LLMs with Ollama and Docker

Local GenAI LLMs with Ollama and Docker

Author: Bret Fisher June 14, 2024 Duration: 50:08

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.

🙌 The Agentic DevOps Guild has launched! It's a training + community + mentorship program for engineers wanting to learn the latest CI/CD automation and dive into Agentic DevOps. Meetups are happening now, with new course videos dropping every few weeks. Join the Guild and become your team's leader in AI for infrastructure automation https://www.bretfisher.com/theguild 🍾

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

  • (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 this podcast 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 Box
Homepage bretfisher.com


Bret Fisher hosts DevOps and Docker Talk: Cloud Native Interviews and Tooling alongside Nirmal Mehta, pulling conversations directly from their live audience sessions. This isn't a theoretical lecture series; it's grounded in the practical, often messy realities of building and running modern systems. Each episode digs into the specific tools and philosophies shaping infrastructure today, from the foundational elements like Docker and container orchestration with Kubernetes or Swarm to the broader cultural shifts of DevOps, SRE, and platform engineering. You'll hear discussions that span the entire software lifecycle, touching on the integration of security with DevSecOps, the automation promises of GitOps, and what "Cloud Native" truly means for development teams. The dialogue stays focused on actionable insights and real-world use cases, offering a genuine sense of what works and what doesn't in the field. For anyone navigating the container and cloud ecosystem, this podcast serves as a regular, insightful check-in with practitioners and experts, hosted by someone deeply embedded in the community. The natural, interview-driven format makes complex topics accessible, ensuring listeners come away with more than just buzzwords-they get context and clarity.
Author: Language: English Episodes: 100

DevOps and Docker Talk: Cloud Native Interviews and Tooling
Podcast Episodes
Software Supply Chain Security with Chainguard [not-audio_url] [/not-audio_url]

Duration: 52:23
Bret is joined by two Chainguard co-founders, CEO Dan Lorenc and Head of Product, Kim Lewandowski, to break down the ins and outs of supply chain security and talk about Chainguard's approach to securing it.
Best of DevOps 2022 [not-audio_url] [/not-audio_url]

Duration: 49:06
Bret is joined by Nirmal Mehta of AWS and engineering consultant Laura Tacho, for the annual Best of DevOps.
Docker: What's New from 2022 [not-audio_url] [/not-audio_url]

Duration: 1:20:48
Bret is joined by Michael Irwin, Sr. Manager for DevRel at Docker, to review and demo our top 2022 new features and announcements from Docker Inc.
Key DevOps Skills for Improving Your Expertise [not-audio_url] [/not-audio_url]

Duration: 1:17:39
Bret is joined by Brian Christner, a Docker Captain and Chief Online Gaming executive for Grand Casino Baden (jackpots.ch), who returns to the show to discuss his top recommended skills for improving your DevOps expertis…
HashiCorp Vault for Kubernetes [not-audio_url] [/not-audio_url]

Duration: 56:59
Bret is joined by Rosemary Wang from HashiCorp to show off Vault for Kubernetes, an open source secrets provider.
Service Mesh in Docker Desktop with Meshery [not-audio_url] [/not-audio_url]

Duration: 52:29
Bret is joined by Lee Calcote and Nic Jackson, co-authors of the Service Mesh Patterns book, to discuss service mesh for Docker Desktop and Compose apps with the new Meshery extension for Docker desktop.
Cilium and eBPF with Liz Rice [not-audio_url] [/not-audio_url]

Duration: 57:26
Bret is joined by Liz Rice, Chief Open Source Officer at Isovalent, the makers of Cilium, to discuss Cilium and eBPF. Cilium is a multi-purpose networking, security, and observability tool for Kubernetes and more.
Kubescape Kubernetes Security with ARMO [not-audio_url] [/not-audio_url]

Duration: 46:53
Bret is joined by Shauli Rozen, CEO and Co-Founder of ARMO, creators of Kubescape. Kubescape is a K8s open-source tool providing a multi-cloud K8s single pane of glass into your Kubernetes security, including risk analys…
Slim and Secure Container Images with Slim.ai [not-audio_url] [/not-audio_url]

Duration: 50:06
Bret is joined by Martin Wimpress and Pieter van Noordennen from Slim.ai to discuss some ways to slim down your Docker images and reduce the attack surface of your containers in the process.
Carvel Tools for Kubernetes [not-audio_url] [/not-audio_url]

Duration: 1:01:48
Bret is joined by Dmitriy Kalinin and John Ryan from VMWare to show off the many Carvel project tools.