The presentation "Semantic Kernel" covers the Semantic Kernel, an open-source Software Development Kit (SDK) for AI model integration and agent development. It discusses key concepts like plugins, planners, personas, and co-pilots in AI applications, emphasizing their roles in task automation and AI orchestration. The presentation highlights features such as prompt engineering, AI memory management, and embedding storage for enhanced AI performance. It also outlines steps for building AI agents using Semantic Kernel, integrating AI models, and managing memory and context. Additionally, the importance of real-time assistance and user feedback in enhancing AI interactions is discussed, along with supported languages for the Semantic Kernel SDK.
2. About me
• Udaiappa Ramachandran ( Udai )
• CTO/CSO-Akumina, Inc.
• Microsoft Azure MVP
• Cloud Expert
• Microsoft Azure, Amazon Web Services, and Google
• New Hampshire Cloud User Group (http://www.meetup.com/nashuaug )
• https://udai.io
3. Agenda
• Introduction to Semantic Kernel
• Getting Started
• Plugins
• Planner
• Persona
• Co-Pilot
• Demo…Demo…Demo…
5. Overview of Semantic Kernel
• Open-Source SDK: Semantic Kernel is an open-source
Software Development Kit designed to streamline the
integration and orchestration of various AI models.
• AI Model Integration: It enables seamless integration with
AI models from prominent platforms like OpenAI, Azure
OpenAI, and Hugging Face.
• Enhanced AI Agent Development: The SDK focuses on
facilitating the development of sophisticated AI agents,
providing tools and frameworks for effective
implementation.
• Versatility and Flexibility: Semantic Kernel is designed to be
versatile, catering to a wide range of applications and user
requirements in AI development.
• Community and Support: It offers robust community
support, including tutorials, forums, and resources for
developers to collaborate and enhance their AI projects..
https://learn.microsoft.com/en-us/semantic-kernel/overview/
6. Key Features of Semantic Kernel
• AI Agent Creation: Guidelines for developing AI agents tailored to specific needs.
• Prompt Engineering: Techniques for effective AI interaction prompts.
• AI Services Integration: Utilizing various AI services and plugins for enhanced
functionality.
• Automation with Planners: Leveraging planners for improved automation
capabilities.
• AI Memories Management: Utilizing vector databases for contextual information
storage.
• Responsible AI Practices: Adherence to ethical standards in AI development.
https://learn.microsoft.com/en-us/semantic-kernel/overview/
7. Building AI agents with Semantic Kernel
• Initialization: Start by initializing Semantic Kernel, setting up the basic framework for the
AI agent.
• Model Integration: Integrate various AI models from platforms like OpenAI and Hugging
Face, customizing the agent to specific tasks.
• Plugin Utilization: Enhance the agent's capabilities by incorporating plugins that offer
additional functionalities and integrations.
• Memory and Context Management: Implement AI memory features for context retention,
ensuring the agent maintains a coherent conversation history or task memory.
• Customization and Testing: Customize the AI agent based on specific use cases and
perform thorough testing to ensure optimal performance and reliability.
https://learn.microsoft.com/en-us/semantic-kernel/overview/
8. Semantic Kernel Plugins
• Extensibility: Plugins extend the core
capabilities of Semantic Kernel, enabling custom
features tailored to specific needs.
• Integration: They allow for the integration of
external services and APIs, enhancing the AI
agent's functionality and data access.
• Flexibility: Plugins provide the flexibility to
adapt the AI agent to various domains and
applications.
• Custom Development: Developers can create
their own plugins to incorporate unique
features or connect to proprietary systems.
• Community Contributions: Leverage plugins
developed by the community for a wide range
of functionalities, fostering collaborative
improvements and innovation.
https://learn.microsoft.com/en-us/semantic-kernel/overview/
9. Semantic Kernel Planners
• Task Automation: Planners in Semantic Kernel
automate complex tasks, streamlining
workflows and reducing manual intervention.
• Efficiency Improvement: They enhance
efficiency by orchestrating various
components and processes within the AI
agent.
• Customizable Workflows: Planners allow for
the customization of workflows to suit
specific automation needs.
• Adaptability: They are adaptable to different
scenarios, ensuring optimal task execution
under varying conditions.
• Integration of AI Models: Planners effectively
integrate different AI models to handle
complex decision-making processes.
10. Semantic Kernel Prompts
• Importance of Prompts: Prompts are crucial for
directing AI model behavior, serving as inputs or
queries that elicit specific responses.
• Prompt Engineering: This emerging field requires
creativity and attention to detail in selecting
words, phrases, and formats to guide AI model
output generation.
• Experimentation with Prompts: The document
emphasizes experimenting with different prompts
and parameters to achieve desired outcomes.
• Examples of Prompts: It includes examples
showing how varying prompt structures lead to
different AI responses.
• Tips for Effective Prompt Engineering: The
document provides tips and strategies for
mastering prompt engineering, highlighting its
significance in AI model manipulation.
https://learn.microsoft.com/en-us/semantic-kernel/overview/
11. Semantic Kernel Memory and Embeddings
• Context Retention: AI Memory in Semantic Kernel is crucial for maintaining
conversation context, enhancing the continuity and relevance of interactions.
• Embedding Storage: The system stores embeddings, which are numerical
representations of data, to facilitate quick and accurate retrieval of information.
• Improved Understanding: These embeddings help in better understanding and
processing of user queries and interactions.
• Dynamic Learning: AI Memory enables dynamic learning from interactions,
adapting to new information and user preferences.
• Enhanced Performance: The combination of AI Memory and embeddings
significantly enhances the overall performance and responsiveness of AI agents.
https://learn.microsoft.com/en-us/semantic-kernel/overview/
12. Copilot feature in Semantic Kernel
• Real-time Assistance: Chat Copilot provides real-time assistance by integrating AI-
driven responses into conversations.
• Customization: It offers extensive customization options to tailor the AI's responses
according to specific user needs or scenarios.
• Enhanced User Interaction: This feature enhances user interactions, making them
more engaging and informative.
• Seamless Integration: Chat Copilot seamlessly integrates with existing systems,
ensuring a smooth user experience.
• User Feedback Incorporation: It has capabilities to learn from user feedback,
continually improving the relevance and accuracy of its responses.
https://learn.microsoft.com/en-us/semantic-kernel/overview/
how it actually work?
planners --the magic that combines plugins together to accoplish a user's goal
with planner you can build your own AI app
apps (plugin extensibility | copilots) -- AI orchestration -- Foundation models | AI infrastructure
At the core of every copilot is a planner -- planner tell a copilot what it should do next with the tools it has, SK has 3 OOTB planners => Action Planner (one action), Sequential planner (several action), Stepwise planner (multiple actions)
how it actually work?
planners --the magic that combines plugins together to accoplish a user's goal
with planner you can build your own AI app
apps (plugin extensibility | copilots) -- AI orchestration -- Foundation models | AI infrastructure
At the core of every copilot is a planner -- planner tell a copilot what it should do next with the tools it has, SK has 3 OOTB planners => Action Planner (one action), Sequential planner (several action), Stepwise planner (multiple actions)