SemanticKernel.Assistants
1.31.2
dotnet add package SemanticKernel.Assistants --version 1.31.2
NuGet\Install-Package SemanticKernel.Assistants -Version 1.31.2
<PackageReference Include="SemanticKernel.Assistants" Version="1.31.2" />
paket add SemanticKernel.Assistants --version 1.31.2
#r "nuget: SemanticKernel.Assistants, 1.31.2"
// Install SemanticKernel.Assistants as a Cake Addin #addin nuget:?package=SemanticKernel.Assistants&version=1.31.2 // Install SemanticKernel.Assistants as a Cake Tool #tool nuget:?package=SemanticKernel.Assistants&version=1.31.2
Assistants for Semantic Kernel
This is assistant support for the Semantic Kernel.
This enables the usage of assistants for the Semantic Kernel without relying on OpenAI Assistant APIs. It runs locally planners and plugins for the assistants.
It provides different scenarios for the usage of assistants such as:
- Assistant with Semantic Kernel plugins
- Multi-Assistant conversation
As the assistants are using the Semantic Kernel, you can use your own model for the assistants and host them locally (see: Bring you own model for more details.).
Usage
- Create you agent description file in yaml:
name: Mathematician description: A mathematician that resolves given maths problems. instructions: | You are a mathematician. Given a math problem, you must answer it with the best calculation formula. No need to show your work, just give the answer to the math problem. Use calculation results. input_parameter: default_value: "" description: | The word mathematics problem to solve in 2-3 sentences. Make sure to include all the input variables needed along with their values and units otherwise the math function will not be able to solve it. execution_settings: planner: Handlebars prompt_settings: temperature: 0.0 top_p: 1 max_tokens: 2000
- Instanciate your assistant in your code:
string azureOpenAIChatCompletionDeployment = configuration["AzureOpenAIDeploymentName"]!; string azureOpenAIEndpoint = configuration["AzureOpenAIEndpoint"]!; string azureOpenAIKey = configuration["AzureOpenAIAPIKey"]!; var mathKernel = Kernel.CreateBuilder() .AddAzureOpenAIChatCompletion(azureOpenAIChatCompletionDeployment, azureOpenAIEndpoint, azureOpenAIKey) .Build(); mathKernel.ImportPluginFromObject(new MathPlugin()); var mathematician = AssistantBuilder.FromTemplate("./Assistants/Mathematician.yaml") .WithKernel(mathKernel) .Build();
var thread = mathematician.CreateThread(); await thread.InvokeAsync("Your ask to the assistant.");
Bring you own model ?
As the assistants are using the Semantic Kernel, you can use your own model for the assistants. For example, you can use the Ollama model for the assistants.
This could be achieved by using the Ollama connector for the Semantic Kernel:
using Codeblaze.SemanticKernel.Connectors.Ollama;
string ollamaEndpoint = configuration["OllamaEndpoint"]!;
var butlerKernel = Kernel.CreateBuilder()
.AddOllamaChatCompletion("phi:latest", ollamaEndpoint)
.Build();
assistant = AssistantBuilder.FromTemplate("./Assistants/Butler.yaml")
.WithKernel(butlerKernel)
.Build();
License
This project is licensed under the MIT License.
Product | Versions Compatible and additional computed target framework versions. |
---|---|
.NET | net5.0 was computed. net5.0-windows was computed. net6.0 was computed. net6.0-android was computed. net6.0-ios was computed. net6.0-maccatalyst was computed. net6.0-macos was computed. net6.0-tvos was computed. net6.0-windows was computed. net7.0 was computed. net7.0-android was computed. net7.0-ios was computed. net7.0-maccatalyst was computed. net7.0-macos was computed. net7.0-tvos was computed. net7.0-windows was computed. net8.0 was computed. net8.0-android was computed. net8.0-browser was computed. net8.0-ios was computed. net8.0-maccatalyst was computed. net8.0-macos was computed. net8.0-tvos was computed. net8.0-windows was computed. |
.NET Core | netcoreapp2.0 was computed. netcoreapp2.1 was computed. netcoreapp2.2 was computed. netcoreapp3.0 was computed. netcoreapp3.1 was computed. |
.NET Standard | netstandard2.0 is compatible. netstandard2.1 was computed. |
.NET Framework | net461 was computed. net462 was computed. net463 was computed. net47 was computed. net471 was computed. net472 was computed. net48 was computed. net481 was computed. |
MonoAndroid | monoandroid was computed. |
MonoMac | monomac was computed. |
MonoTouch | monotouch was computed. |
Tizen | tizen40 was computed. tizen60 was computed. |
Xamarin.iOS | xamarinios was computed. |
Xamarin.Mac | xamarinmac was computed. |
Xamarin.TVOS | xamarintvos was computed. |
Xamarin.WatchOS | xamarinwatchos was computed. |
-
.NETStandard 2.0
- Handlebars.Net (>= 2.1.6)
- Microsoft.Extensions.Configuration (>= 8.0.0)
- Microsoft.Extensions.Configuration.Abstractions (>= 8.0.0)
- Microsoft.Extensions.Logging (>= 8.0.1)
- Microsoft.SemanticKernel (>= 1.31.0)
- Microsoft.SemanticKernel.Abstractions (>= 1.31.0)
- Microsoft.SemanticKernel.Agents.Abstractions (>= 1.31.0-alpha)
- Microsoft.SemanticKernel.Agents.Core (>= 1.31.0-alpha)
- Microsoft.SemanticKernel.Core (>= 1.31.0)
- Microsoft.SemanticKernel.Planners.Handlebars (>= 1.31.0-preview)
- Microsoft.SemanticKernel.Planners.OpenAI (>= 1.31.0-preview)
- Microsoft.SemanticKernel.Yaml (>= 1.31.0)
- YamlDotNet (>= 15.3.0)
NuGet packages (1)
Showing the top 1 NuGet packages that depend on SemanticKernel.Assistants:
Package | Downloads |
---|---|
SemanticKernel.Assistants.AutoGen
This enables the usage of AutoGen assistants for the Semantic Kernel. It provides different scenarios for the usage of assistants such as: - **Assistant with Semantic Kernel plugins** - **Multi-Assistant conversation** - **AutoGen conversation** (see [AutoGen](#autogen) for more details) |
GitHub repositories
This package is not used by any popular GitHub repositories.
Version | Downloads | Last updated |
---|---|---|
1.31.2 | 118 | 12/3/2024 |
1.31.1 | 91 | 12/2/2024 |
1.31.0 | 89 | 12/2/2024 |
1.21.1 | 215 | 10/1/2024 |
1.17.1 | 249 | 8/14/2024 |
1.17.0 | 123 | 8/8/2024 |
1.14.0 | 552 | 6/5/2024 |
1.13.1 | 139 | 6/2/2024 |
1.13.0 | 207 | 5/21/2024 |
1.12.0 | 124 | 5/17/2024 |
1.10.1 | 161 | 5/1/2024 |
1.10.0 | 100 | 5/1/2024 |
1.7.3 | 150 | 4/8/2024 |
1.7.2 | 143 | 4/8/2024 |
1.7.1 | 153 | 4/7/2024 |
1.6.3 | 176 | 3/24/2024 |
1.6.2 | 158 | 3/24/2024 |
1.5.3 | 204 | 3/3/2024 |
1.5.2 | 169 | 3/3/2024 |
1.5.1 | 135 | 3/3/2024 |
1.5.0 | 153 | 3/2/2024 |
1.3.3 | 205 | 2/10/2024 |
1.3.1 | 126 | 2/6/2024 |
1.3.0 | 120 | 2/1/2024 |
1.2.0-preview | 91 | 1/27/2024 |
1.1.1-peview | 103 | 1/22/2024 |
1.1.0-preview | 95 | 1/18/2024 |
1.0.4-preview | 113 | 1/5/2024 |
1.0.3-preview | 139 | 12/20/2023 |
1.0.2-preview | 114 | 12/19/2023 |
1.0.1-rc4 | 119 | 12/16/2023 |
1.0.1-rc3 | 120 | 12/11/2023 |
1.0.1-preview | 125 | 12/19/2023 |
1.0.0-rc3 | 122 | 12/10/2023 |
0.0.1-alpha | 147 | 1/5/2024 |