This repository contains AI examples that aim to grow the understanding of using Microsoft AI toolsets in applications by providing samples of implementation and references to support the Microsoft Build conference in 2022.
| Project | Description |
|---|---|
| Codex for Minecraft Non-Player Characters | Use Codex to generate code to power a non-player character (NPC) in Minecraft and accomplish a variety of in-game tasks. |
| Codex Command Line Interface | Use Codex to convert natural language into commands in Bash, Z shell (zsh) and PowerShell. |
| Codex Babylon | Use natural language to create and manipulate 3D objects in Babylon.js, from simple primitives to complex scenes. |
| Azure Search - Query Classification | Leveraging large language models (LLMs) to enable semantic understanding with Azure Cognitive Search that improves the search experience. |
| ML.NET on Excel | Bring your own ML.NET model to Excel. |
| Turtlebot3 Simulator with Bonsai | Train reinforcement learning policies for Turtlebot3 using Microsoft Bonsai. |
| ONNX Runtime with Unreal Engine 5 | Apply style transfer models in Unreal Engine 5 via the ONNX Neural Network Inference (NNI) plugin powered by ONNX Runtime. |
| Papiro Document Intelligence | A conference intelligence application that uses intelligence APIs to showcase what might be done to support conferences with AI. |
| locutus GPT-2 Text Generation | Demonstrate an end-to-end process within Azure Machine Learning to deploy the GPT-2 model from Hugging Face and fine-tuned it on the writings of Homer. |
This project is not intended to be the forum on discussing Microsoft products nor requesting new features.
- How to build Codex solutions (Microsoft Build 2022 on-demand session)
- How to get Codex to produce the code you want
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 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. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.
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. 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.