SlideShare une entreprise Scribd logo
1  sur  26
Building AI-Driven Apps using
Semantic Kernel
Udaiappa Ramachandran ( Udai )
https://udai.io
Boston Code Camp 36 - Thanks to our Sponsors!
• Platinum
• Gold
• Silver
• In-Kind Donations
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
Agenda
• Introduction to Semantic Kernel
• Getting Started
• Plugins
• Planner
• Persona
• Demo…Demo…Demo…
Building AI Applications
• Azure AI Studio with Prompt flow
• Co-Pilot studio
• Semantic Kernel
AI Application Terminology
• Plugins
• Skills
• Planner
• Persona
• Co-Pilot
• Agent
• Vector Embedding
• Prompt Engineering
• Semantic Kernel
Overview of Semantic Kernel
• Open-Source SDK
• Seamless AI Model Integration
• Enhanced AI Agent Development
• Versatility and Flexibility
• Support multiple languages C#, Python, Java
• Community and Support
https://learn.microsoft.com/en-us/semantic-kernel/overview/
Building AI Apps with Semantic Kernel
• Initialization
• Prompt creation
• Model Integration
• Plugin Utilization
• Automation with Plugin
• Memory and Context Management
• Responsible AI Practices
• Customization and Testing
https://learn.microsoft.com/en-us/semantic-kernel/overview/
Semantic Kernel Plugins
• Code-based extensions
• Domain-specific
• Technical implementations
• Examples:
• An Email plugin
• A calendar plugin
• Plugin providing access to specialized knowledge
bases or APIIs
https://learn.microsoft.com/en-us/semantic-kernel/overview/
Semantic Kernel Planners
• Task Automation
• Efficiency Boost
• Customizable Workflows
• Dynamic problem-Solving
• Powerful AI Integration
• Planner Generation
• Action Planner
• Sequential Planner
• Stepwise Planner
https://learn.microsoft.com/en-us/semantic-kernel/overview/
Semantic Kernel Prompts
• Prompts are crucial for directing AI model
behavior
• Types
• Meta prompt
• System prompt
• User Prompt
https://learn.microsoft.com/en-us/semantic-kernel/overview/
Semantic Kernel Memory and Embeddings
• Context Retention
• Embedding Storage
• Improved Understanding
• Dynamic Learning
• Enhanced Performance
Copilot feature in Semantic Kernel
• Real-time Assistance
• Customization
• Enhanced User Interaction
• Seamless Integration
• User Feedback Incorporation
Plugin/Planner/Agent/Co-Pilot
AI Component Functionalities
Plugin Task based (Ex., Image manipulation, Text translation, etc.,)
Planner Workflow (Ex., Decision-making, Action optimization)
Persona Identity given to AI system (Ex., customer chatbot persona)
Agent Perceives environment, takes goal-oriented actions
Co-Pilot Completes tasks under direction (ex., Github co pilot), all co-pilots are planner
Plugin/Planner/Agent/Co-Pilot
Semantic Kernel – Planner/Plugin
https://learn.microsoft.com/en-us/semantic-kernel/overview/
Getting Started
• Semantic Kernel Supported Language: C#, Python and Java
• Semantic Kernel SDK is available in C#, Python, and Java
• Semantic Kernel : https://github.com/microsoft/semantic-kernel
• Semantic Kernel Starters: https://github.com/microsoft/semantic-kernel-starters
• Semantic Kernel in C#
• https://github.com/microsoft/semantic-kernel/blob/main/dotnet/README.md
• Using Semantic Kernel in Python
• https://github.com/microsoft/semantic-kernel/blob/main/python/README.md
• Using Semantic Kernel in Java
• https://github.com/microsoft/semantic-kernel/blob/main/java/README.md
Supported AI Services
https://learn.microsoft.com/en-us/semantic-kernel/overview/
Supported AI Endpoints
https://learn.microsoft.com/en-us/semantic-kernel/overview/
Supported Core Plugins
https://learn.microsoft.com/en-us/semantic-kernel/overview/
Supported Plugins
https://learn.microsoft.com/en-us/semantic-kernel/overview/
Supported Planners
https://learn.microsoft.com/en-us/semantic-kernel/overview/
Supported Connectors
https://learn.microsoft.com/en-us/semantic-kernel/overview/
Demo
• Semantic Kernel
Reference
• https://learn.microsoft.com/en-us/semantic-kernel/
• Semantic Kernel Starters: https://github.com/microsoft/semantic-kernel-starters
• Chat Application
• https://github.com/microsoft/chat-copilot
• Semantic Kernel in C#
• https://github.com/microsoft/semantic-kernel/blob/main/dotnet/README.md
• Using Semantic Kernel in Python
• https://github.com/microsoft/semantic-kernel/blob/main/python/README.md
• Using Semantic Kernel in Java
• https://github.com/microsoft/semantic-kernel/blob/main/java/README.md
Thanks for your time and trust!
Boston Code Camp (BCC36)

Contenu connexe

Similaire à Building AI-Driven Apps Using Semantic Kernel.pptx

Architecting for Hyper Growth and Great Engineering Culture
Architecting for Hyper Growth and Great Engineering CultureArchitecting for Hyper Growth and Great Engineering Culture
Architecting for Hyper Growth and Great Engineering Culture
ifnu bima
 
Liyakathulla AEM Consultant
Liyakathulla AEM ConsultantLiyakathulla AEM Consultant
Liyakathulla AEM Consultant
Liyakathulla R
 

Similaire à Building AI-Driven Apps Using Semantic Kernel.pptx (20)

Working Software Over Comprehensive Documentation
Working Software Over Comprehensive DocumentationWorking Software Over Comprehensive Documentation
Working Software Over Comprehensive Documentation
 
Architecting for Huper Growth and Great Engineering Culture
Architecting for Huper Growth and Great Engineering CultureArchitecting for Huper Growth and Great Engineering Culture
Architecting for Huper Growth and Great Engineering Culture
 
Architecting for Hyper Growth and Great Engineering Culture
Architecting for Hyper Growth and Great Engineering CultureArchitecting for Hyper Growth and Great Engineering Culture
Architecting for Hyper Growth and Great Engineering Culture
 
Udvid din test portefølje med coded ui test og cloud load test
Udvid din test portefølje med coded ui test og cloud load testUdvid din test portefølje med coded ui test og cloud load test
Udvid din test portefølje med coded ui test og cloud load test
 
IncQuery Server for Teamwork Cloud - Talk at IW2019
IncQuery Server for Teamwork Cloud - Talk at IW2019IncQuery Server for Teamwork Cloud - Talk at IW2019
IncQuery Server for Teamwork Cloud - Talk at IW2019
 
Introduction to SharePoint Framework
Introduction to SharePoint FrameworkIntroduction to SharePoint Framework
Introduction to SharePoint Framework
 
How to build a serverless helmet detection system
How to build a serverless helmet detection systemHow to build a serverless helmet detection system
How to build a serverless helmet detection system
 
LUIS and Bots
LUIS and BotsLUIS and Bots
LUIS and Bots
 
Resume
ResumeResume
Resume
 
The Greatest Introduction to SharePoint Framework (SPFx) on earth!
The Greatest Introduction to SharePoint Framework (SPFx) on earth!The Greatest Introduction to SharePoint Framework (SPFx) on earth!
The Greatest Introduction to SharePoint Framework (SPFx) on earth!
 
Selenium for everyone
Selenium for everyoneSelenium for everyone
Selenium for everyone
 
Free Online SharePoint Framework Webinar
Free Online SharePoint Framework WebinarFree Online SharePoint Framework Webinar
Free Online SharePoint Framework Webinar
 
Liyakathulla AEM Consultant
Liyakathulla AEM ConsultantLiyakathulla AEM Consultant
Liyakathulla AEM Consultant
 
dotNet Miami - May 17th, 2012: Will Tartak: Designing for Mobile Development
dotNet Miami - May 17th, 2012: Will Tartak: Designing for Mobile DevelopmentdotNet Miami - May 17th, 2012: Will Tartak: Designing for Mobile Development
dotNet Miami - May 17th, 2012: Will Tartak: Designing for Mobile Development
 
Azure functions serverless
Azure functions serverlessAzure functions serverless
Azure functions serverless
 
A guide to hiring a great developer to build your first app (redacted version)
A guide to hiring a great developer to build your first app (redacted version)A guide to hiring a great developer to build your first app (redacted version)
A guide to hiring a great developer to build your first app (redacted version)
 
Portal and Intranets
Portal and Intranets Portal and Intranets
Portal and Intranets
 
AzureOpenAI.pptx
AzureOpenAI.pptxAzureOpenAI.pptx
AzureOpenAI.pptx
 
Google Cloud Developer Challenge - GDG Belgaum
Google Cloud Developer Challenge - GDG BelgaumGoogle Cloud Developer Challenge - GDG Belgaum
Google Cloud Developer Challenge - GDG Belgaum
 
PuppetConf 2017: Unlocking Azure with Puppet Enterprise- Keiran Sweet, Source...
PuppetConf 2017: Unlocking Azure with Puppet Enterprise- Keiran Sweet, Source...PuppetConf 2017: Unlocking Azure with Puppet Enterprise- Keiran Sweet, Source...
PuppetConf 2017: Unlocking Azure with Puppet Enterprise- Keiran Sweet, Source...
 

Plus de Udaiappa Ramachandran

Plus de Udaiappa Ramachandran (20)

RAG Patterns and Vector Search in Generative AI
RAG Patterns and Vector Search in Generative AIRAG Patterns and Vector Search in Generative AI
RAG Patterns and Vector Search in Generative AI
 
Level up your security using Intune.pptx
Level up your security using Intune.pptxLevel up your security using Intune.pptx
Level up your security using Intune.pptx
 
DOTNET8.pptx
DOTNET8.pptxDOTNET8.pptx
DOTNET8.pptx
 
AzureSynapse.pptx
AzureSynapse.pptxAzureSynapse.pptx
AzureSynapse.pptx
 
Vector Search using OpenAI in Azure Cognitive Search.pptx
Vector Search using OpenAI in Azure Cognitive Search.pptxVector Search using OpenAI in Azure Cognitive Search.pptx
Vector Search using OpenAI in Azure Cognitive Search.pptx
 
SecureAzureServicesUsingADAuthentication.pptx
SecureAzureServicesUsingADAuthentication.pptxSecureAzureServicesUsingADAuthentication.pptx
SecureAzureServicesUsingADAuthentication.pptx
 
OpenAI-Copilot-ChatGPT.pptx
OpenAI-Copilot-ChatGPT.pptxOpenAI-Copilot-ChatGPT.pptx
OpenAI-Copilot-ChatGPT.pptx
 
DiagnoseAndSolveproblems.pptx
DiagnoseAndSolveproblems.pptxDiagnoseAndSolveproblems.pptx
DiagnoseAndSolveproblems.pptx
 
MAUI.pptx
MAUI.pptxMAUI.pptx
MAUI.pptx
 
CosmosDB.pptx
CosmosDB.pptxCosmosDB.pptx
CosmosDB.pptx
 
.NET7.pptx
.NET7.pptx.NET7.pptx
.NET7.pptx
 
AzureDevOps
AzureDevOpsAzureDevOps
AzureDevOps
 
AzureCostManagementAndBilling
AzureCostManagementAndBillingAzureCostManagementAndBilling
AzureCostManagementAndBilling
 
.NET6.pptx
.NET6.pptx.NET6.pptx
.NET6.pptx
 
Azure Automation and Update Management
Azure Automation and Update ManagementAzure Automation and Update Management
Azure Automation and Update Management
 
Azure staticwebapps
Azure staticwebappsAzure staticwebapps
Azure staticwebapps
 
Azure privatelink
Azure privatelinkAzure privatelink
Azure privatelink
 
Azure Security Center
Azure Security CenterAzure Security Center
Azure Security Center
 
Azure signalr service
Azure signalr serviceAzure signalr service
Azure signalr service
 
Azure governance
Azure governanceAzure governance
Azure governance
 

Dernier

CORS (Kitworks Team Study 양다윗 발표자료 240510)
CORS (Kitworks Team Study 양다윗 발표자료 240510)CORS (Kitworks Team Study 양다윗 발표자료 240510)
CORS (Kitworks Team Study 양다윗 발표자료 240510)
Wonjun Hwang
 
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
panagenda
 

Dernier (20)

Easier, Faster, and More Powerful – Notes Document Properties Reimagined
Easier, Faster, and More Powerful – Notes Document Properties ReimaginedEasier, Faster, and More Powerful – Notes Document Properties Reimagined
Easier, Faster, and More Powerful – Notes Document Properties Reimagined
 
How to Check GPS Location with a Live Tracker in Pakistan
How to Check GPS Location with a Live Tracker in PakistanHow to Check GPS Location with a Live Tracker in Pakistan
How to Check GPS Location with a Live Tracker in Pakistan
 
AI mind or machine power point presentation
AI mind or machine power point presentationAI mind or machine power point presentation
AI mind or machine power point presentation
 
TEST BANK For, Information Technology Project Management 9th Edition Kathy Sc...
TEST BANK For, Information Technology Project Management 9th Edition Kathy Sc...TEST BANK For, Information Technology Project Management 9th Edition Kathy Sc...
TEST BANK For, Information Technology Project Management 9th Edition Kathy Sc...
 
الأمن السيبراني - ما لا يسع للمستخدم جهله
الأمن السيبراني - ما لا يسع للمستخدم جهلهالأمن السيبراني - ما لا يسع للمستخدم جهله
الأمن السيبراني - ما لا يسع للمستخدم جهله
 
CORS (Kitworks Team Study 양다윗 발표자료 240510)
CORS (Kitworks Team Study 양다윗 발표자료 240510)CORS (Kitworks Team Study 양다윗 발표자료 240510)
CORS (Kitworks Team Study 양다윗 발표자료 240510)
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontology
 
Introduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDMIntroduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDM
 
Design Guidelines for Passkeys 2024.pptx
Design Guidelines for Passkeys 2024.pptxDesign Guidelines for Passkeys 2024.pptx
Design Guidelines for Passkeys 2024.pptx
 
Cyber Insurance - RalphGilot - Embry-Riddle Aeronautical University.pptx
Cyber Insurance - RalphGilot - Embry-Riddle Aeronautical University.pptxCyber Insurance - RalphGilot - Embry-Riddle Aeronautical University.pptx
Cyber Insurance - RalphGilot - Embry-Riddle Aeronautical University.pptx
 
State of the Smart Building Startup Landscape 2024!
State of the Smart Building Startup Landscape 2024!State of the Smart Building Startup Landscape 2024!
State of the Smart Building Startup Landscape 2024!
 
UiPath manufacturing technology benefits and AI overview
UiPath manufacturing technology benefits and AI overviewUiPath manufacturing technology benefits and AI overview
UiPath manufacturing technology benefits and AI overview
 
AI in Action: Real World Use Cases by Anitaraj
AI in Action: Real World Use Cases by AnitarajAI in Action: Real World Use Cases by Anitaraj
AI in Action: Real World Use Cases by Anitaraj
 
Event-Driven Architecture Masterclass: Challenges in Stream Processing
Event-Driven Architecture Masterclass: Challenges in Stream ProcessingEvent-Driven Architecture Masterclass: Challenges in Stream Processing
Event-Driven Architecture Masterclass: Challenges in Stream Processing
 
Portal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russePortal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russe
 
Intro to Passkeys and the State of Passwordless.pptx
Intro to Passkeys and the State of Passwordless.pptxIntro to Passkeys and the State of Passwordless.pptx
Intro to Passkeys and the State of Passwordless.pptx
 
Oauth 2.0 Introduction and Flows with MuleSoft
Oauth 2.0 Introduction and Flows with MuleSoftOauth 2.0 Introduction and Flows with MuleSoft
Oauth 2.0 Introduction and Flows with MuleSoft
 
Microsoft CSP Briefing Pre-Engagement - Questionnaire
Microsoft CSP Briefing Pre-Engagement - QuestionnaireMicrosoft CSP Briefing Pre-Engagement - Questionnaire
Microsoft CSP Briefing Pre-Engagement - Questionnaire
 
Frisco Automating Purchase Orders with MuleSoft IDP- May 10th, 2024.pptx.pdf
Frisco Automating Purchase Orders with MuleSoft IDP- May 10th, 2024.pptx.pdfFrisco Automating Purchase Orders with MuleSoft IDP- May 10th, 2024.pptx.pdf
Frisco Automating Purchase Orders with MuleSoft IDP- May 10th, 2024.pptx.pdf
 
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
 

Building AI-Driven Apps Using Semantic Kernel.pptx

Notes de l'éditeur

  1. 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)
  2. 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)
  3. 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..
  4. 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.
  5. Skills: Modularized Knowledge and Behavior: Skills represent self-contained units of functionality that are accessible to the AI. Think of them as pre-packed abilities or knowledge modules. Conversational Emphasis: Skills frequently focus on enabling more natural and engaging conversations. They can introduce personality, dialogue variations, or the ability to handle specific conversation topics Less Technical (Often): Developing skills can sometimes be done using no-code tools or simplified scripting languages, lowering the barrier or less technical users Examples: A “joke telling” skill providing the AI with the ability to tell jokes. A “movie trivia” skill containing knowledge about movies and handling relevant questions. A skill providing conversational templates for handling small talk Plugins often expand technical capabilities; Skills often expand conversational abilities.
  6. 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.
  7. 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. Metaprompts are instructions that guide AI models on how to effectively interpret, generate, and refine prompts for optimal task completion. System prompts provide an AI model with specific instructions, context, and desired output format for a particular task. A user prompt is a direct query or input provided by a user to an AI model, designed to elicit a specific response or action.
  8. 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.
  9. 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.
  10. AGENT: Automated Driving System (ADS) as an Agent Perceives its environment using sensors like cameras, radars, constantly gathers data about its surroundings (vechicle, pedestrians, traffic, lights, etc.,) Take Actions (steering, acceleration, breaking ) to maintain a safe tracectory Learns from experience: advanced ADS may collect and analyze data over time to improve its decision-making capabilities Plugin: Object Detection Lane Detection Traffic Sign Recognition Planner: Navigate Routes: the planner uses a map database and real-time traffic information to determine the optimal route to the destination. Plan Maneuvers: the planner calculates safe and efficient maneuvers (lane changes, overtaking, merging) based on the perceived environment Respond to Emergencies: The planner can activate emergency breaking or evasive maneuvers in response to sudden obstacles
  11. AGENT: Automated Driving System (ADS) as an Agent Perceives its environment using sensors like cameras, radars, constantly gathers data about its surroundings (vechicle, pedestrians, traffic, lights, etc.,) Take Actions (steering, acceleration, breaking ) to maintain a safe tracectory Learns from experience: advanced ADS may collect and analyze data over time to improve its decision-making capabilities Plugin: Object Detection Lane Detection Traffic Sign Recognition Planner: Navigate Routes: the planner uses a map database and real-time traffic information to determine the optimal route to the destination. Plan Maneuvers: the planner calculates safe and efficient maneuvers (lane changes, overtaking, merging) based on the perceived environment Respond to Emergencies: The planner can activate emergency breaking or evasive maneuvers in response to sudden obstacles ADS: Perceives its environment using Sensors like Cameras, Radars, data about surroundings and take actions