# ignite25-LAB585-supercharge-your-apps-with-local-ai

**Repository Path**: mirrors_microsoft/ignite25-LAB585-supercharge-your-apps-with-local-ai

## Basic Information

- **Project Name**: ignite25-LAB585-supercharge-your-apps-with-local-ai
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-11-20
- **Last Updated**: 2025-11-22

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

<p align="center">
<img src="img/Banner-ignite-25.png" alt="decorative banner" width="1200"/>
</p>

# [Microsoft Ignite 2025](https://ignite.microsoft.com)

## 🔥LAB585: Supercharge your apps with local AI

![License](https://img.shields.io/badge/license-MIT-blue.svg)
![.NET](https://img.shields.io/badge/.NET-9.0-purple.svg)
![Platform](https://img.shields.io/badge/platform-Windows%2011-blue.svg)
![AI](https://img.shields.io/badge/AI-Microsoft%20Experimental-orange.svg)

### Session Description

In this lab, you will learn how to add the new AI features into a WPF app and create an app that uses Semantic Search, OCR and Phi-Silica to query a PDF file and obtain answers based on it

### 🧠 Learning Outcomes

By the end of this lab, you'll have created a sophisticated application featuring:

- 🖥️ **AI-Enhanced Windows Application** - Turbocharge a Windows application with AI features and modern UI
- 🔍 **AI-Powered Search** - Semantic search using Microsoft's experimental AI indexing
- 🤖 **RAG-Powered Queries** - Local Retrieval Augmented Generation queries using Semantic Search and Phi-Silica
- 💬 **Natural Language Queries** - Ask questions about documents in plain English
- 📄 **Advanced PDF Processing** - Text extraction with the OCR API and page rendering
- 🖼️ **Visual Results** - Preview relevant document pages alongside query results
- ⚡ **Real-time Responses** - Streaming AI responses with cancellation support

### 💻 Technologies Used

1. [WinAppSDK](https://github.com/microsoft/WindowsAppSDK)
2. [Fluent UI - WinUI3](https://github.com/microsoft/WindowsAppSDK)
3. [Semantic Search](https://learn.microsoft.com/en-us/windows/ai/apis/app-content-search)
4. [OCR AI API](https://learn.microsoft.com/en-us/windows/ai/apis/text-recognition)
5. [Phi-Silica language  model](https://learn.microsoft.com/en-us/windows/ai/apis/phi-silica)

### 🌟 Semantic Search

The Semantic Search and Knowledge Retrieval API empowers developers to integrate intelligent search capabilities into their apps. By indexing in-app content and making it searchable through semantic queries, users can retrieve results based not only on exact keywords but also on semantic meaning. You can use this semantic index to enhance your own AI assistants with domain-specific knowledge, creating more personalized, context-specific experiences.

### 🌟 OCR

Text recognition, also known as optical character recognition (OCR), is supported in Windows AI Foundry through a set of artificial intelligence (AI)-backed APIs that can detect and extract text within images and convert it into machine readable character streams.

### 🌟 Phi-Silica

Phi Silica is a local language model that you can integrate into your Windows apps using Windows AI Foundry. Phi Silica is optimized for efficiency and performance on Windows Copilot+ PCs devices while still offering many of the capabilities found in Large Language Models (LLMs).

### 📚 Resources and Next Steps

| Resources          | Links                             | Description        |
|:-------------------|:----------------------------------|:-------------------|
| **Microsoft AI Documentation** | [https://docs.microsoft.com/en-us/windows/ai/](https://docs.microsoft.com/en-us/windows/ai/) | Learn more on Windows AI |
| **WinUI3 Tutorials** | [https://docs.microsoft.com/en-us/dotnet/desktop/wpf/](https://docs.microsoft.com/en-us/dotnet/desktop/wpf/) | WinUI3 Documentation |
| **Windows AI APIs** | [https://docs.microsoft.com/en-us/windows/ai/apis/](https://docs.microsoft.com/en-us/windows/ai/apis/) | Learn more on Windows AI APIs |
| Ignite 2025 Next Steps | [https://aka.ms/Ignite25-Next-Steps](https://aka.ms/Ignite25-Next-Steps?ocid=ignite25_nextsteps_cnl) | Links to all repos for Ignite 2025 Sessions |
| Learn at Ignite | [https://aka.ms/LearnAtIgnite](https://aka.ms/LearnAtIgnite?ocid=ignite25_nextsteps_github_cnl) | Continue learning on Microsoft Learn |

## Content Owners

<table>
<tr>
    <td align="center"><a href="http://github.com/brunosonnino">
        <img src="https://avatars.githubusercontent.com/u/110240926?s=400&u=5d4d76024214733423c5a6ecabb1cadc1228dc1a&v=4" width="100px;" alt="Bruno Sonnino" "/><br />
        <sub><b>Bruno Sonnino </b></sub></a><br />
            <a href="https://github.com/brunosonnino" title="talk">📢</a> 
    </td>
    <td align="center"><a href="http://github.com/gregwoo_microsoft">
        <img src="https://avatars.githubusercontent.com/u/120929158?s=400&u=dceb49466f897c4e454fb9bbdc68f84774d83283&v=4" width="100px;" alt="Greg Woo"/><br />
        <sub><b>Greg Woo</b></sub></a><br />
            <a href="https://github.com/gregwoo_microsoft" title="talk">📢</a> 
    </td>
</tr></table>


## Contributing

This project welcomes contributions and suggestions.  Most contributions require you to agree to a
Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us
the rights to use your contribution. For details, visit [Contributor License Agreements](https://cla.opensource.microsoft.com).

When you submit a pull request, a CLA bot will automatically determine whether you need to provide
a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions
provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.

## Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft
trademarks or logos is subject to and must follow
[Microsoft's Trademark & Brand Guidelines](https://www.microsoft.com/legal/intellectualproperty/trademarks/usage/general).
Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.
Any use of third-party trademarks or logos are subject to those third-party's policies.