Microsoft.Extensions.AI–Part VIII–Evaluations

Back from holiday with charged batteries, we continue our journey exploring the Microsoft.Extensions.AI library. Today we have a look at evaluating AI models.

This post is part of a blog series. Other posts so far:

What is Microsoft.Extensions.AI.Evaluation?

Microsoft.Extensions.AI.Evaluation is a set of libraries with one common goal; simplifying the process of evaluating the quality and accuracy of responses generated by AI models. Measuring the quality of your AI apps is challenging, you need to evaluate metrics like:

Relevance: How effective is the response for a given prompt?
Truthfulness: Is the response factually correct?
Coherence: Is the response logically structured and consistent?
Completeness: Is the response a sufficient answer?
And many more…

The evaluation libraries handle this for you through a list of available evaluators that can easily be integrated in your existing test infrastructure and framework.

But enough talking, let’s give it a try…

Integrate AI quality validation for our chat application

Start by adding a new test project to your solution using the framework of your choice. I'll be using XUnit in this post but the library itself is completely test framework agnostic.

Add a reference to the Microsoft.Extensions.AI.Evaluation.Quality library:

dotnet package add Microsoft.Extensions.AI.Evaluation.Quality

Now we first need to bootstrap our ChatConfiguration:

And also build up our prompt:

Once these 2 things are in place, we can setup the evaluator(s) for our test, invoke our LLM and evaluate the results:

Of course, this test fails as the AI suggested the moon as a good holiday location.

Tomorrow we further extend this example and have a look at caching of the model responses and reporting of the evaluations.

More information

The Microsoft.Extensions.AI.Evaluation libraries - .NET | Microsoft Learn

ai-samples/src/microsoft-extensions-ai-evaluation/api/README.md at main · dotnet/ai-samples

Exploring new Agent Quality and NLP evaluators for .NET AI applications - .NET Blog

Podman– Command execution failed with exit code 125

After updating WSL on one of the developer machines, Podman failed to work. When we took a look through Podman Desktop, we noticed that Podman had stopped running and returned the following error message: Error: Command execution failed with exit code 125 Here are the steps we tried to fix the issue: We started by running podman info to get some extra details on what could be wrong: >podman info OS: windows/amd64 provider: wsl version: 5.3.1 Cannot connect to Podman. Please verify your connection to the Linux system using `podman system connection list`, or try `podman machine init` and `podman machine start` to manage a new Linux VM Error: unable to connect to Podman socket: failed to connect: dial tcp 127.0.0.1:2655: connectex: No connection could be made because the target machine actively refused it. That makes sense as the podman VM was not running. Let’s check the VM: >podman machine list NAME ...

Cache stampede: when our cache turned against us

While investigating some performance issues, we ran into an ASP.NET Core API that cached a fairly expensive aggregation query for 60 seconds. Under normal load, that was fine: one request rebuilds the cache, everyone else reads from it. Under peak load, dozens of requests would arrive in that same expiry window, all see a cache miss, and all fire the same expensive query in parallel. The database didn't like that. That was the moment when our caching layer stopped helping and started hurting. A burst of requests comes in at the same time, all miss the cache, and all go hammer the database or the downstream API at once. That's a cache stampede . The cache was supposed to protect our backend, and for a few hundred milliseconds it did the opposite. Why this happens IMemoryCache.GetOrCreate (and its async sibling) looks like it protects you, but it doesn't add any locking on its own. Look at the naive version: public async Task<Report> GetReportAsync(string key) ...

A complex system designed from scratch never works

A few years ago, I worked as an architect on a big mainframe rewrite. I still count it as one of my failures. Not because the technology was wrong, but because I couldn't convince the management team to simplify the approach. Years later, the organization is still struggling to get the new system up and running. I left the project at the time, because I couldn't put my name behind an approach that would take very long and cost a lot of money without a working system to show for it along the way. Gall’s Law That memory keeps coming back to me, because it's a textbook case of Gall's Law playing out in real life. Gall's Law , from John Gall's Systemantics , states it plainly: A complex system that works is invariably found to have evolved from a simple system that worked. A complex system designed from scratch never works, and it cannot be patched to make it work. You have to start over with a simple system that works. What does that mean in practice,...

The art of simplicity

Search This Blog