Unleashing the Power of Microsoft Semantic Kernel in API Communication - A Deep Dive into the GPT-4

Microsoft Semantic Kernel (SK) is a new technology that enables the integration of AI Large Language Models (LLMs) with conventional programming languages like C#, Python and Java. SK brings together several key components to provide planning and execution capabilities. These components include a robust kernel that provides the foundation for all other components, plugins (formerly known as skills) for performing specific tasks, connectors for interfacing with external systems, memories for storing information about past events, steps for defining individual actions, and pipelines for organizing complex multi-stage plans.

What about if we go beyond those clicks and build a semantic interface (code in C#) for an existing API (controlling a Car Robot)?

Talk To Your Code Using Microsoft Semantic Kernel

Microsoft Semantic Kernel (SK) is a new technology that enables the integration of AI Large Language Models (LLMs) with conventional programming languages.
SK is a powerful system that brings together several key components to provide planning and execution capabilities. These components include ASK (Active Semantic Knowledge) for understanding the user’s goals and context, GET (Goal Execution Technology) for creating and executing plans, and a robust Kernel that provides the foundation for all other components. SK also includes Skills for performing specific tasks, Connectors for interfacing with external systems, Memories for storing information about past events, Steps for defining individual actions, and Pipelines for organizing complex multi-stage plans.
We will explore several use-cases using multi-modal prompts and show how SK can be used to create and execute complex plans using a combination of natural language and conventional programming language like C#.

AI powered car robot using IoT Libraries and ML.NET

In this talk, we will showcase how to build an AI-powered car robot using IoT libraries and ML.NET. We will start by discussing the hardware components such as Raspberry Pi, video camera and sensor required to build the robot. Then, we will delve into the software side of things, covering the integration of IoT libraries and ML.NET to enable object detection and deep learning capabilities for the robot. We will demonstrate how to use ML.NET to train and deploy object detection models, and how to use IoT libraries to control the robot's movement and receive sensor data. Whether you are a hobbyist or an experienced developer, this talk will provide you with practical tips and techniques to build your own AI-powered car robot using IoT libraries and ML.NET.

OpenAI Assistants orchestrated with Semantic Kernel Agents

Creating agents with the Microsoft Semantic Kernel using OpenAI Assistants is an intriguing approach for handling complex problem-solving tasks. It uses AI to coordinate the work among multiple assistants. Each assistant has its own persona and tools, operating as separate GPTs. The days of manually managing conversation states and chat threads are behind us. Now, with the support of these assistants, we can have conversations that remember their context.

In this session I explore how these assistants can interact in three different scenarios:
- hierarchical chat agents (interactive chat)
- joint chat agents (interactive chat)
- agent powered by agents as plugins chat (one prompt chat)

For this, I have created four agents, each representing a different hero: Jack Sparrow, Don Quixote, Shakespeare, and Yoda. Additionally, I have a dialogue writer agent that takes a dialogue script and brings these heroes to life.

Well, let's see what happens when Jack Sparrow is messing up with Don Quixote!

OpenAI, Azure OpenAI, Visual Studio Code, C#
For developers.