Serina.Semantic.Ai.Pipelines 1.0.0

.NET 8.0 This package targets .NET 8.0. The package is compatible with this framework or higher. 
dotnet add package Serina.Semantic.Ai.Pipelines --version 1.0.0
                    


                    

                
NuGet\Install-Package Serina.Semantic.Ai.Pipelines -Version 1.0.0
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package. 
<PackageReference Include="Serina.Semantic.Ai.Pipelines" Version="1.0.0" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
<PackageVersion Include="Serina.Semantic.Ai.Pipelines" Version="1.0.0" />
                    


                            Directory.Packages.props
                        

                    

                
<PackageReference Include="Serina.Semantic.Ai.Pipelines" />
                    


                            Project file
For projects that support Central Package Management (CPM), copy this XML node into the solution Directory.Packages.props file to version the package. 
paket add Serina.Semantic.Ai.Pipelines --version 1.0.0
                    


                    

                
#r "nuget: Serina.Semantic.Ai.Pipelines, 1.0.0"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package. 
#addin nuget:?package=Serina.Semantic.Ai.Pipelines&version=1.0.0
                    


                            Install Serina.Semantic.Ai.Pipelines as a Cake Addin
                        

                    

                
#tool nuget:?package=Serina.Semantic.Ai.Pipelines&version=1.0.0
                    


                            Install Serina.Semantic.Ai.Pipelines as a Cake Tool

Semantic Kernel Pipeline NuGet Package

Overview

The Semantic Kernel Pipeline is a .NET 8 NuGet package that enables flexible AI-driven workflows. It supports memory plugins, service selection, streaming responses, history reducers, and summarizers, making it an ideal solution for conversational AI, intelligent data retrieval, and custom AI workflows.

Features

  • AI Pipeline Creation – Define custom AI processing steps.
  • Memory Plugins – Store and retrieve historical data.
  • Service Selection – Use multiple AI services with dynamic selection.
  • Streaming Support – Process responses as a stream.
  • History Reducers & Summarizers – Efficiently manage conversation history.
  • Media Processing – Handle text, images, and other inputs.
  • Extensible Plugins – Add custom plugins for specialized tasks.

Installation

Install the package via NuGet:

Install-Package SemanticKernel.Pipeline

Or add it to your .csproj file:

<PackageReference Include="SemanticKernel.Pipeline" Version="1.0.0" />

Quick Start

1. Create a Pipeline

var pipeline = new PipelineBuilder()
    .AddStep(new SimpleChatStep())
    .AddStep(new HistoryReducer())
    .AddStep(new Summarizer())
    .Build();

2. Process a Request

var result = await pipeline.ProcessAsync("Tell me a joke");
Console.WriteLine(result);

3. Streaming Responses

await foreach (var chunk in pipeline.ProcessStreamAsync("Generate a story"))
{
    Console.Write(chunk);
}

4. Using a Custom Plugin

public class CustomPlugin : IPipelinePlugin
{
    public async Task<string> ExecuteAsync(string input)
    {
        return $"Processed: {input}";
    }
}

var pipeline = new PipelineBuilder()
    .AddStep(new CustomPlugin())
    .Build();

Advanced Usage

Service Selection

Use RandomServiceSelector to dynamically pick AI models:

var selector = new RandomServiceSelector(["gpt-4", "claude-3"]);
var pipeline = new PipelineBuilder()
    .UseServiceSelector(selector)
    .AddStep(new SimpleChatStep())
    .Build();

Memory Integration

Store conversation history and recall past interactions:

var memory = new InMemoryStorage();
var pipeline = new PipelineBuilder()
    .UseMemory(memory)
    .AddStep(new HistoryReducer())
    .Build();

Summarization & History Reduction

Summarize long conversations to optimize memory:

var pipeline = new PipelineBuilder()
    .AddStep(new Summarizer())
    .AddStep(new HistoryReducer())
    .Build();

Processing Images with Vision Models

Supports multimodal AI pipelines (text + images):

var visionStep = new AIImageProcessor("llama3.2-vision");
var pipeline = new PipelineBuilder()
    .AddStep(visionStep)
    .Build();

var result = await pipeline.ProcessAsync(imageInput);

Extensibility

Create your own steps, filters, and plugins by implementing IPipelinePlugin.

public class MyCustomStep : IPipelinePlugin
{
    public async Task<string> ExecuteAsync(string input)
    {
        return input.ToUpper();
    }
}

Contributing

Contributions are welcome! Feel free to submit issues, feature requests, or pull requests.

https://github.com/pashkovdenis/serina-pipeline

License

This project is licensed under the MIT License. See LICENSE for details.

Product Compatible and additional computed target framework versions.
.NET net8.0 is compatible.  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.  net9.0 was computed.  net9.0-android was computed.  net9.0-browser was computed.  net9.0-ios was computed.  net9.0-maccatalyst was computed.  net9.0-macos was computed.  net9.0-tvos was computed.  net9.0-windows was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages (1)

Showing the top 1 NuGet packages that depend on Serina.Semantic.Ai.Pipelines:

Package Downloads
Serina.TagMemory

Semantic Kernel Tag Memory plugin that use sql database for RAG

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last updated
1.0.0 117 4/3/2025