Semantic Kernel Workflow Copilot Demo and Code Walkthrough
Welcome back to my series on building intelligent applications with .NET !
In this video, we're diving deep into how you can leverage Semantic Kernel to add significant value to multi-step workflows.
Have you ever wanted an AI that isn't just a simple chat, but is deeply contextual? We'll explore how to ensure that each step in your workflow understands its goal and the content being processed.
This video will focus on:
Using Semantic Kernel to guide users in a multi-stage process.
Adding context to each step of the workflow, making the AI more helpful
How to serialize your objects into a json schema to pass along in Semantic Kernel and return structured data back from the LLM
Looking at the code to see exactly how this works under the hood
This practical demonstration showcases how Semantic Kernel enables us to build truly intelligent, context-aware applications that go beyond just a single AI interaction. Whether you're new to Semantic Kernel or looking for advanced techniques, this video is packed with insights you won't want to miss!
Examples for Windsurf
I have added
docs.example_autofunctioncall_will_arguments_and_streaming.txt
to the Demo.Grounding folder
https://github.com/bgarnr/WindsurfDocs
What I encourage you to do is to download Windsurf, open the repo and chat with the grounding files. The sample project in there you can also have windsurf use as a template to make you a demo for the recommendation example provided.
If you like this content I would love to have your comments and subscribe for more content.
Stay tuned for more as we explore the cutting edge of AI integration in .NET development!
En esta página del sitio puede ver el video en línea Semantic Kernel Workflow Copilot Demo and Code Walkthrough de Duración hora minuto segunda en buena calidad , que subió el usuario Brett Garnier 19 diciembre 2024, comparta el enlace con amigos y conocidos, en youtube este video ya ha sido visto 90 veces y le gustó 1 a los espectadores. Disfruta viendo!
