Skip to main content

Run LLMs locally using Podman AI Lab

So far I’ve always used Ollama as a way to run LLM's locally on my development machine. However recently I discovered the Podman AI Lab extension as an alternative solution to work with Large Language Models on your local machine.

In this post I’ll share my experience when trying the Podman AI lab extension.

Remark: I assume you already have Podman Desktop up and running on your machine. (If not check one of my previous posts; Kubernetes–Setup a local cluster through Podman Desktop)

Installation

You need to have at least the following versions to get started:

If the prerequisites are ok, installing the extension should be really easy. Based on the documentation it should be sufficient to click on the installation link to get going. Unfortunately this didn’t work on my machine and I got the following error message instead:

Turns out that the update had failed for an unknown reason and that I was still running an older Podman Desktop version. After updating, I could go to the Extension Catalog and install the Podman AI lab extension:

After installation, an extra icon appears on the left:

Interact with an LLM locally

Now that the extension itself is up and running, we can download a model. Therefore go to the model catalog and click on the download icon next to one of the listed models:

Downloading a model can take some time, so the ideal moment to grab a coffee…

Once the model is downloaded you can start a model service. A model service is an inference server that is running in a container and exposes the model through a REST api.

Go to the Services tab and click on the New Model Service on the top right:

Choose the downloaded model from the list and click on Create Service:

Once the service is started you can generate a code snippet to interact with the model:


Model playground

If you want to interact with the model directly without writing your own code, you can use the built-in playground.

Therefore go to Playgrounds and click on New Playground on the top right:

Choose the downloaded model and click on Create Playground:

Once the playground is ready, you get a chat interface to interact with the model:

Nice!

More information

Running large language models locally using Ollama (bartwullems.blogspot.com)

Podman AI Lab | Podman Desktop (podman-desktop.io)


Labels:

Popular posts from this blog

.NET 8–Keyed/Named Services

A feature that a lot of IoC container libraries support but that was missing in the default DI container provided by Microsoft is the support for Keyed or Named Services. This feature allows you to register the same type multiple times using different names, allowing you to resolve a specific instance based on the circumstances. Although there is some controversy if supporting this feature is a good idea or not, it certainly can be handy. To support this feature a new interface IKeyedServiceProvider got introduced in .NET 8 providing 2 new methods on our ServiceProvider instance: object? GetKeyedService(Type serviceType, object? serviceKey); object GetRequiredKeyedService(Type serviceType, object? serviceKey); To use it, we need to register our service using one of the new extension methods: Resolving the service can be done either through the FromKeyedServices attribute: or by injecting the IKeyedServiceProvider interface and calling the GetRequiredKeyedServic...
Read more

Azure DevOps/ GitHub emoji

I’m really bad at remembering emoji’s. So here is cheat sheet with all emoji’s that can be used in tools that support the github emoji markdown markup: All credits go to rcaviers who created this list.
Read more

Kubernetes–Limit your environmental impact

Reducing the carbon footprint and CO2 emission of our (cloud) workloads, is a responsibility of all of us. If you are running a Kubernetes cluster, have a look at Kube-Green . kube-green is a simple Kubernetes operator that automatically shuts down (some of) your pods when you don't need them. A single pod produces about 11 Kg CO2eq per year( here the calculation). Reason enough to give it a try! Installing kube-green in your cluster The easiest way to install the operator in your cluster is through kubectl. We first need to install a cert-manager: kubectl apply -f https://github.com/cert-manager/cert-manager/releases/download/v1.14.5/cert-manager.yaml Remark: Wait a minute before you continue as it can take some time before the cert-manager is up & running inside your cluster. Now we can install the kube-green operator: kubectl apply -f https://github.com/kube-green/kube-green/releases/latest/download/kube-green.yaml Now in the namespace where we want t...
Read more