Ollama C# Playground

This project is designed to be opened in GitHub Codespaces as an easy way for anyone to try out SLMs (small language models) entirely in the browser. This project is based on the Ollama Python Playground

1. Create a new Codespace using the Code button at the top of the repository.

2. Once the Codespace is loaded, it should have ollama pre-installed as well as .NET 8.

3. Ask Ollama to run the SLM of your choice. For example, to run the Phi-3.5 model:

   ollama run phi3.5:mini

   That will take a few minutes to download the model into the Codespace.

4. Once you see "success" in the output, you can send a message to that model from the prompt.

   >>> Write a joke about kittens

1. After several seconds, you should see a response stream in from the model.

2. To learn about different techniques used with language models, check the sample projects in the .\src folder:

Project	Description
Sample01	This is a sample project that uses a the Phi-3 hosted in ollama model to answer a question.
Sample02	This is a sample project that implement a Console chat using Semantic Kernel.
Sample03	This is a sample project that implement a RAG using local embeddings and Semantic Kernel. Check the details of the local RAG here
Sample04	This is a sample console project that implement a Console chat using Semantic Kernel. It also uses Aspire Dashboard to track telemetry. Check the Aspire Dashboard in the references sections to learn more.
Sample05	This is a sample project that adds Aspire Service Telemetry project to a Console chat and show how to use Aspire Dashboard to track telemetry. Check the Aspire Dashboard in the references sections to learn more.

How to run a sample

1. Open a terminal and navigate to the desired project. In example, let's run Sample02, the console chat.

   cd .\src\Sample02\

2. Run the project with the command

   dotnet run

3. The project Sample02, defines a custom system message:

   var history = new ChatHistory();
   history.AddSystemMessage("You are a useful chatbot. If you don't know an answer, say 'I don't know!'. Always reply in a funny ways. Use emojis if possible.");

4. So when the user ask a question, like What is the capital of Italy?, the chat replies using the local mode.

   The output is similar to this one:

   

Video Tutorials

If you want to learn more about how to use this repo, check the following videos:

Overview of Ollama C# Playground Repository.

Retrieval-Augmented Generation (RAG) with .NET 8: A Full Local Resource Guide

Test Aspire Dashboard using Codespaces

Add Aspire Service Defaults to a Console Chat App

References

• Phi-3 Microsoft Blog
• Phi-3 Technical Report
• Phi-3 Cookbook
• Generative AI for beginners
• Semantic Kernel main repository
• Smart Components - Local Embeddings
• Aspire Dashboard

Author

👤 Bruno Capuano

• Website: https://elbruno.com
• Twitter: @elbruno
• Github: @elbruno
• LinkedIn: @elbruno

🤝 Contributing

Contributions, issues and feature requests are welcome!

Feel free to check issues page.

Show your support

Give a ⭐️ if this project helped you!

📝 License

Copyright © 2024 Bruno Capuano.

This project is MIT licensed.

---