https://github.com/luisquintanilla/ragdotnetaifundamentals

This sample shows how to apply vanilla / simple RAG pattern using .NET fundamentals in the AI ecosystem
https://github.com/luisquintanilla/ragdotnetaifundamentals

Last synced: about 1 month ago
JSON representation

This sample shows how to apply vanilla / simple RAG pattern using .NET fundamentals in the AI ecosystem

• Host: GitHub
• URL: https://github.com/luisquintanilla/ragdotnetaifundamentals
• Owner: luisquintanilla
• Created: 2024-10-23T19:22:10.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2024-10-23T20:39:43.000Z (2 months ago)
• Last Synced: 2024-10-24T06:02:12.480Z (2 months ago)
• Language: C#
• Size: 10.7 KB
• Stars: 3
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# RAG Sample using .NET AI Fundamentals

This sample shows how to apply vanilla / simple RAG pattern using .NET fundamentals in the AI ecosystem such as:

- [Microsoft.ML.Tokenizers](https://www.nuget.org/packages/Microsoft.ML.Tokenizers/)

- [System.Numerics.Tensors](https://www.nuget.org/packages/System.Numerics.Tensors/)

- [Microsoft.Extensions.AI](https://www.nuget.org/packages/Microsoft.Extensions.AI/)

- [Microsoft.Extensions.VectorData.Abstractions](https://www.nuget.org/packages/Microsoft.Extensions.VectorData.Abstractions/)

- [ML.NET](https://www.nuget.org/packages/Microsoft.ML/)

- [ONNX Runtime](https://www.nuget.org/packages/Microsoft.ML.OnnxTransformer/)

Given a list of movies, this sample implements semantic search, a building block for RAG patterns. 

The project structure is as follows:

- **Domain.cs** - Contains the data models used by ML.NET and the vector store

- **MLNETONNXEmbeddingGenerator** - Implementation of `IEmbeddingGenerator` Microsoft.Extensions.AI interface. The implementation creates an ML.NET pipeline which uses the BertTokenizer from Microsoft.ML.Tokenizers and an the e5-small-v2 ONNX embedding model to generate embeddings.

- **Program.cs** - Uses an `InMemoryVectorStore` Semantic Kernel to store and query movie data containg embeddings generated by the `MLNETONNXEmbeddingGenerator`.

## Prerequisites

- [.NET 9 SDK](https://dotnet.microsoft.com/en-us/download/dotnet/9.0)

- Visual Studio or Visual Studio Code

## Quick Start

1. Open in GitHub Codespaces

    [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/luisquintanilla/RAGDotnetAIFundamentals)

1. Download the [e5-small-v2 model](https://huggingface.co/intfloat/e5-small-v2/resolve/main/model.onnx?download=true) and save it to the *assets* directory. If you rename the file, make sure to update the model path used by the `generator` in *Program.cs*.

## Setup

1. Download the [e5-small-v2 model](https://huggingface.co/intfloat/e5-small-v2/resolve/main/model.onnx?download=true) and save it to the *assets* directory. If you rename the file, make sure to update the model path used by the `generator` in *Program.cs*.

## Run the application

1. Open the terminal and run the following command.

```csharp

dotnet run

```