# edgeai-for-beginners **Repository Path**: mirrors_microsoft/edgeai-for-beginners ## Basic Information - **Project Name**: edgeai-for-beginners - **Description**: This course is designed to guide beginners through the exciting world of Edge AI, covering fundamental concepts, popular models, inference techniques, device-specific applications, model optimization, and the development of intelligent Edge AI agents. - **Primary Language**: Unknown - **License**: MIT - **Default Branch**: main - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2025-09-27 - **Last Updated**: 2025-10-04 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # EdgeAI for Beginners ![Course cover image](./imgs/cover.png) [![GitHub contributors](https://img.shields.io/github/contributors/microsoft/edgeai-for-beginners.svg)](https://GitHub.com/microsoft/edgeai-for-beginners/graphs/contributors) [![GitHub issues](https://img.shields.io/github/issues/microsoft/edgeai-for-beginners.svg)](https://GitHub.com/microsoft/edgeai-for-beginners/issues) [![GitHub pull-requests](https://img.shields.io/github/issues-pr/microsoft/edgeai-for-beginners.svg)](https://GitHub.com/microsoft/edgeai-for-beginners/pulls) [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) [![GitHub watchers](https://img.shields.io/github/watchers/microsoft/edgeai-for-beginners.svg?style=social&label=Watch)](https://GitHub.com/microsoft/edgeai-for-beginners/watchers) [![GitHub forks](https://img.shields.io/github/forks/microsoft/edgeai-for-beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/edgeai-for-beginners/fork) [![GitHub stars](https://img.shields.io/github/stars/microsoft/edgeai-for-beginners?style=social&label=Star)](https://GitHub.com/microsoft/edgeai-for-beginners/stargazers) [![Microsoft Azure AI Foundry Discord](https://dcbadge.limes.pink/api/server/ByRwuEEgH4)](https://discord.com/invite/ByRwuEEgH4) Follow these steps to get started using these resources: 1. **Fork the Repository**: Click [![GitHub forks](https://img.shields.io/github/forks/microsoft/edgeai-for-beginners.svg?style=social&label=Fork)](https://GitHub.com/microsoft/edgeai-for-beginners/fork) 2. **Clone the Repository**: `git clone https://github.com/microsoft/edgeai-for-beginners.git` 3. [**Join The Azure AI Foundry Discord and meet experts and fellow developers**](https://discord.com/invite/ByRwuEEgH4) ### 🌐 Multi-Language Support #### Supported via GitHub Action (Automated & Always Up-to-Date) [Arabic](./translations/ar/README.md) | [Bengali](./translations/bn/README.md) | [Bulgarian](./translations/bg/README.md) | [Burmese (Myanmar)](./translations/my/README.md) | [Chinese (Simplified)](./translations/zh/README.md) | [Chinese (Traditional, Hong Kong)](./translations/hk/README.md) | [Chinese (Traditional, Macau)](./translations/mo/README.md) | [Chinese (Traditional, Taiwan)](./translations/tw/README.md) | [Croatian](./translations/hr/README.md) | [Czech](./translations/cs/README.md) | [Danish](./translations/da/README.md) | [Dutch](./translations/nl/README.md) | [Finnish](./translations/fi/README.md) | [French](./translations/fr/README.md) | [German](./translations/de/README.md) | [Greek](./translations/el/README.md) | [Hebrew](./translations/he/README.md) | [Hindi](./translations/hi/README.md) | [Hungarian](./translations/hu/README.md) | [Indonesian](./translations/id/README.md) | [Italian](./translations/it/README.md) | [Japanese](./translations/ja/README.md) | [Korean](./translations/ko/README.md) | [Malay](./translations/ms/README.md) | [Marathi](./translations/mr/README.md) | [Nepali](./translations/ne/README.md) | [Norwegian](./translations/no/README.md) | [Persian (Farsi)](./translations/fa/README.md) | [Polish](./translations/pl/README.md) | [Portuguese (Brazil)](./translations/br/README.md) | [Portuguese (Portugal)](./translations/pt/README.md) | [Punjabi (Gurmukhi)](./translations/pa/README.md) | [Romanian](./translations/ro/README.md) | [Russian](./translations/ru/README.md) | [Serbian (Cyrillic)](./translations/sr/README.md) | [Slovak](./translations/sk/README.md) | [Slovenian](./translations/sl/README.md) | [Spanish](./translations/es/README.md) | [Swahili](./translations/sw/README.md) | [Swedish](./translations/sv/README.md) | [Tagalog (Filipino)](./translations/tl/README.md) | [Thai](./translations/th/README.md) | [Turkish](./translations/tr/README.md) | [Ukrainian](./translations/uk/README.md) | [Urdu](./translations/ur/README.md) | [Vietnamese](./translations/vi/README.md) **If you wish to have additional translations languages supported are listed [here](https://github.com/Azure/co-op-translator/blob/main/getting_started/supported-languages.md)** ## Introduction Welcome to **EdgeAI for Beginners** – your comprehensive journey into the transformative world of Edge Artificial Intelligence. This course bridges the gap between powerful AI capabilities and practical, real-world deployment on edge devices, empowering you to harness AI's potential directly where data is generated and decisions need to be made. ### What You'll Master This course takes you from fundamental concepts to production-ready implementations, covering: - **Small Language Models (SLMs)** optimized for edge deployment - **Hardware-aware optimization** across diverse platforms - **Real-time inference** with privacy-preserving capabilities - **Production deployment** strategies for enterprise applications ### Why EdgeAI Matters Edge AI represents a paradigm shift that addresses critical modern challenges: - **Privacy & Security**: Process sensitive data locally without cloud exposure - **Real-time Performance**: Eliminate network latency for time-critical applications - **Cost Efficiency**: Reduce bandwidth and cloud computing expenses - **Resilient Operations**: Maintain functionality during network outages - **Regulatory Compliance**: Meet data sovereignty requirements ### Edge AI Edge AI refers to running AI algorithms and language models locally on hardware, close to where data is generated without relying on cloud resources for inference. It reduces latency, enhances privacy, and enables real-time decision-making. ### Core Principles: - **On-device inference**: AI models run on edge devices (phones, routers, microcontrollers, industrial PCs) - **Offline capability**: Functions without persistent internet connectivity - **Low latency**: Immediate responses suited for real-time systems - **Data sovereignty**: Keeps sensitive data local, improving security and compliance ### Small Language Models (SLMs) SLMs like Phi-4, Mistral-7B, and Gemma are optimized versions of larger LLMsβ€”trained or distilled for: - **Reduced memory footprint**: Efficient use of limited edge device memory - **Lower compute demand**: Optimized for CPU and edge GPU performance - **Faster startup times**: Quick initialization for responsive applications They unlock powerful NLP capabilities while meeting the constraints of: - **Embedded systems**: IoT devices and industrial controllers - **Mobile devices**: Smartphones and tablets with offline capabilities - **IoT Devices**: Sensors and smart devices with limited resources - **Edge servers**: Local processing units with limited GPU resources - **Personal Computers**: Desktop and laptop deployment scenarios ## Course Modules & Navigation | Module | Topic | Focus Area | Key Content | Level | Duration | |--------|-------|------------|-------------|--------|----------| | [πŸ“– 00 ](./introduction.md) | [Introduction to EdgeAI](./introduction.md) | Foundation & Context | EdgeAI Overview β€’ Industry Applications β€’ SLM Introduction β€’ Learning Objectives | Beginner | 1-2 hrs | | [πŸ“š 01](./Module01/) | [EdgeAI Fundamentals](./Module01/README.md) | Cloud vs Edge AI comparison | EdgeAI Fundamentals β€’ Real World Case Studies β€’ Implementation Guide β€’ Edge Deployment | Beginner | 3-4 hrs | | [🧠 02](./Module02/) | [SLM Model Foundations](./Module02/README.md) | Model families & architecture | Phi Family β€’ Qwen Family β€’ Gemma Family β€’ BitNET β€’ ΞΌModel β€’ Phi-Silica | Beginner | 4-5 hrs | | [πŸš€ 03](./Module03/) | [SLM Deployment Practice](./Module03/README.md) | Local & cloud deployment | Advanced Learning β€’ Local Environment β€’ Cloud Deployment | Intermediate | 4-5 hrs | | [βš™οΈ 04](./Module04/) | [Model Optimization Toolkit](./Module04/README.md) | Cross-platform optimization | Introduction β€’ Llama.cpp β€’ Microsoft Olive β€’ OpenVINO β€’ Apple MLX β€’ Workflow Synthesis | Intermediate | 5-6 hrs | | [πŸ”§ 05](./Module05/) | [SLMOps Production](./Module05/README.md) | Production operations | SLMOps Introduction β€’ Model Distillation β€’ Fine-tuning β€’ Production Deployment | Advanced | 5-6 hrs | | [πŸ€– 06](./Module06/) | [AI Agents & Function Calling](./Module06/README.md) | Agent frameworks & MCP | Agent Introduction β€’ Function Calling β€’ Model Context Protocol | Advanced | 4-5 hrs | | [πŸ’» 07](./Module07/) | [Platform Implementation](./Module07/README.md) | Cross-platform samples | AI Toolkit β€’ Foundry Local β€’ Windows Development | Advanced | 3-4 hrs | | [🏭 08](./Module08/) | [Foundry Local Toolkit](./Module08/README.md) | Production-ready samples | Sample applications (see details below) | Expert | 8-10 hrs | ### 🏭 **Module 08: Sample Applications** - [01: REST Chat Quickstart](./Module08/samples/01/README.md) - [02: OpenAI SDK Integration](./Module08/samples/02/README.md) - [03: Model Discovery & Benchmarking](./Module08/samples/03/README.md) - [04: Chainlit RAG Application](./Module08/samples/04/README.md) - [05: Multi-Agent Orchestration](./Module08/samples/05/README.md) - [06: Models-as-Tools Router](./Module08/samples/06/README.md) - [07: Direct API Client](./Module08/samples/07/README.md) - [08: Windows 11 Chat App](./Module08/samples/08/README.md) - [09: Advanced Multi-Agent System](./Module08/samples/09/README.md) - [10: Foundry Tools Framework](./Module08/samples/10/README.md) ### πŸ“Š **Learning Path Summary** - **Total Duration**: 36-45 hours - **Beginner Path**: Modules 01-02 (7-9 hours) - **Intermediate Path**: Modules 03-04 (9-11 hours) - **Advanced Path**: Modules 05-07 (12-15 hours) - **Expert Path**: Module 08 (8-10 hours) ## What You'll Build ### 🎯 Core Competencies - **Edge AI Architecture**: Design local-first AI systems with cloud integration - **Model Optimization**: Quantize and compress models for edge deployment (85% speed boost, 75% size reduction) - **Multi-Platform Deployment**: Windows, mobile, embedded, and cloud-edge hybrid systems - **Production Operations**: Monitoring, scaling, and maintaining edge AI in production ### πŸ—οΈ Practical Projects - **Foundry Local Chat Apps**: Windows 11 native application with model switching - **Multi-Agent Systems**: Coordinator with specialist agents for complex workflows - **RAG Applications**: Local document processing with vector search - **Model Routers**: Intelligent selection between models based on task analysis - **API Frameworks**: Production-ready clients with streaming and health monitoring - **Cross-Platform Tools**: LangChain/Semantic Kernel integration patterns ### 🏒 Industry Applications **Manufacturing** β€’ **Healthcare** β€’ **Autonomous Vehicles** β€’ **Smart Cities** β€’ **Mobile Apps** ## Quick Start **Recommended Learning Path** (20-30 hours total): 0. **πŸ“– Introduction** ([Introduction.md](./introduction.md)): EdgeAI foundation + industry context + learning framework 1. **πŸ“š Foundation** (Modules 01-02): EdgeAI concepts + SLM model families 2. **βš™οΈ Optimization** (Modules 03-04): Deployment + quantization frameworks 3. **πŸš€ Production** (Modules 05-06): SLMOps + AI agents + function calling 4. **πŸ’» Implementation** (Modules 07-08): Platform samples + Foundry Local toolkit Each module includes theory, hands-on exercises, and production-ready code samples. ## Career Impact **Technical Roles**: EdgeAI Solutions Architect β€’ ML Engineer (Edge) β€’ IoT AI Developer β€’ Mobile AI Developer **Industry Sectors**: Manufacturing 4.0 β€’ Healthcare Tech β€’ Autonomous Systems β€’ FinTech β€’ Consumer Electronics **Portfolio Projects**: Multi-agent systems β€’ Production RAG apps β€’ Cross-platform deployment β€’ Performance optimization ## Repository Structure ``` edgeai-for-beginners/ β”œβ”€β”€ πŸ“– introduction.md # Foundation: EdgeAI Overview & Learning Framework β”œβ”€β”€ πŸ“š Module01-04/ # Fundamentals β†’ SLMs β†’ Deployment β†’ Optimization β”œβ”€β”€ πŸ”§ Module05-06/ # SLMOps β†’ AI Agents β†’ Function Calling β”œβ”€β”€ πŸ’» Module07/ # Platform Samples (VS Code, Windows, Jetson, Mobile) β”œβ”€β”€ 🏭 Module08/ # Foundry Local Toolkit + 10 Comprehensive Samples β”‚ β”œβ”€β”€ samples/01-06/ # Foundation: REST, SDK, RAG, Agents, Routing β”‚ └── samples/07-10/ # Advanced: API Client, Windows App, Enterprise Agents, Tools β”œβ”€β”€ 🌐 translations/ # Multi-language support (8+ languages) └── πŸ“‹ STUDY_GUIDE.md # Structured learning paths & time allocation ``` ## Course Highlights βœ… **Progressive Learning**: Theory β†’ Practice β†’ Production deployment βœ… **Real Case Studies**: Microsoft, Japan Airlines, enterprise implementations βœ… **Hands-on Samples**: 50+ examples, 10 comprehensive Foundry Local demos βœ… **Performance Focus**: 85% speed improvements, 75% size reductions βœ… **Multi-Platform**: Windows, mobile, embedded, cloud-edge hybrid βœ… **Production Ready**: Monitoring, scaling, security, compliance frameworks πŸ“– **[Study Guide Available](STUDY_GUIDE.md)**: Structured 20-hour learning path with time allocation guidance and self-assessment tools. --- **EdgeAI represents the future of AI deployment**: local-first, privacy-preserving, and efficient. Master these skills to build the next generation of intelligent applications. ## Other Courses Our team produces other courses! Check out: - [MCP for Beginners](https://github.com/microsoft/mcp-for-beginners) - [AI Agents For Beginners](https://github.com/microsoft/ai-agents-for-beginners?WT.mc_id=academic-105485-koreyst) - [Generative AI for Beginners using .NET](https://github.com/microsoft/Generative-AI-for-beginners-dotnet?WT.mc_id=academic-105485-koreyst) - [Generative AI for Beginners using JavaScript](https://github.com/microsoft/generative-ai-with-javascript?WT.mc_id=academic-105485-koreyst) - [Generative AI for Beginners](https://github.com/microsoft/generative-ai-for-beginners?WT.mc_id=academic-105485-koreyst) - [ML for Beginners](https://aka.ms/ml-beginners?WT.mc_id=academic-105485-koreyst) - [Data Science for Beginners](https://aka.ms/datascience-beginners?WT.mc_id=academic-105485-koreyst) - [AI for Beginners](https://aka.ms/ai-beginners?WT.mc_id=academic-105485-koreyst) - [Cybersecurity for Beginners](https://github.com/microsoft/Security-101??WT.mc_id=academic-96948-sayoung) - [Web Dev for Beginners](https://aka.ms/webdev-beginners?WT.mc_id=academic-105485-koreyst) - [IoT for Beginners](https://aka.ms/iot-beginners?WT.mc_id=academic-105485-koreyst) - [XR Development for Beginners](https://github.com/microsoft/xr-development-for-beginners?WT.mc_id=academic-105485-koreyst) - [Mastering GitHub Copilot for AI Paired Programming](https://aka.ms/GitHubCopilotAI?WT.mc_id=academic-105485-koreyst) - [Mastering GitHub Copilot for C#/.NET Developers](https://github.com/microsoft/mastering-github-copilot-for-dotnet-csharp-developers?WT.mc_id=academic-105485-koreyst) - [Choose Your Own Copilot Adventure](https://github.com/microsoft/CopilotAdventures?WT.mc_id=academic-105485-koreyst) ## Getting Help If you get stuck or have any questions about building AI apps, join: [![Azure AI Foundry Discord](https://img.shields.io/badge/Discord-Azure_AI_Foundry_Community_Discord-blue?style=for-the-badge&logo=discord&color=5865f2&logoColor=fff)](https://aka.ms/foundry/discord) If you have product feedback or errors while building visit: [![Azure AI Foundry Developer Forum](https://img.shields.io/badge/GitHub-Azure_AI_Foundry_Developer_Forum-blue?style=for-the-badge&logo=github&color=000000&logoColor=fff)](https://aka.ms/foundry/forum)