Tool support in OllamaSharp

Yesterday I talked about OllamaSharp as an alternative (to Semantic Kernel) to talk to your Ollama endpoint using C#. The reason I wanted to directly use Ollama and not use Semantic Kernel was because I wanted to give the recently announced Ollama Tool support a try. And that is exactly what we are going to explore in this post.

Keep reading...

Tool support

Tool support allows a model to answer a given prompt using tools it knows about, making it possible to interact with the outside world and do things like for example calling an API. It makes your model a lot smarter as it can start using information that was not part of the originally trained model and do more things than just returning a response.

Remark: A similar feature exists in Semantic Kernel through the concept of Plugins but as far as I’m aware the Plugins are not using the Ollama tools support (yet). When writing this post I noticed that a new Ollama connector was released for Semantic Kernel which uses OllamaSharp behind the scenes. I’ll have a look if this new connector allows to call the Ollama tool support and update this post with my findings. Promised!

To show the power of tools calling, we first ask some weather information using the example we created yesterday:

The model nicely explains us that it cannot access weather info.

OK. Let’s start creating a tool that allows to return the weather for a location. Important is that we give a good description to the tool and to the parameters expected by the tool:

Now we can update our chat example from yesterday and pass on the tool instance:

Remark: Notice that we also changed the model used. Right now a limited list of models support tools calling.

If we now ask for the weather, we’ll get the following response back:

What wasn’t immediately clear to me is that the Ollama tools support will not invoke the tool for you. So you need to call it yourself based on the provided ToolCall information you get back from the LLM.

Here is an updated version where I call the GetWeather method I have available in my code:

Now we get the following results back:

Nice!

Remark: Be aware that this code is far from production ready but at least you get the idea.

More information

Tool support · Ollama Blog

Introducing new Ollama Connector for Local Models | Semantic Kernel (microsoft.com)

wullemsb/OllamaSharpDemo: Tools demo for OllamaSharp (github.com)

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