This repository contains demos and samples for the Microsoft Build: AI Day (Austria). It contains the following labs:
- OpenAI Chat Completions Basics (C# and .NET or Python)
- Function Calling with Chat Completions (C# and .NET)
- Using Tools with the new Assistant API
- Embeddings and the RAG model (TypeScript and Node.js)
Attendees can decide the complexity level on their own:
- L200: People who are less familiar with coding can take the existing code, try to run it (description will be provided), play with prompts, and think about possible use cases in their professional or personal life.
- L300: People who are a bit familiar with coding can extend the existing code by copying and modify parts of the samples (ideas will be provided).
- L400: People who are very familiar with coding can take the samples as a starting point or inspiration and implement their own use case.
We recommend that you use Development Containers to work with this repository. Here is how you can get started:
- Make sure that you have Docker installed locally.
- Install Visual Studio Code
- Install the Remote Development extension pack
- Clone this repository
- Open the repository in Visual Studio Code
- When asked whether you want to reopen the folder using Dev Containers, say yes.
- You are all set!
If you do not want to use Dev Containers, install the following software on your machine:
- If you want to work with C# and .NET:
- .NET 8 SDK
- Visual Studio 2023 (v17.9)
- Latest version of Visual Studio Code with the extensions listed in extensions.json
- If you want to work with TypeScript and Node.js:
- Latest LTS version of Node.js
- Latest version of Visual Studio Code
Within this workshop we are working with a shared Azure OpenAI tenant and specific deployments. As part of the workshop you will receive an .env file from your instructors, so you can access the shared Azure OpenAI tenant from your project folder. After adding the .env file to the root of this repository, or copying the .env.template file and rename it, you will be able to execute the various labs in this repostiory.
The hands-on-labs in this repo use the Adventure Works LT sample database. If you participate in the official hackathon, your trainers will provide a connection string to an instance of Adventure Works LT in Azure. If you work on the samples at home, install Adventure Works LT in Azure or on a local SQL Server.
We recommend to install Azure Data Studio to interactively explore the sample database. Alternatively, you can use SQL Server Management Studio.