Setup & Prerequisites
There are a few prerequisites to getting started with integrating LLMs into your C# application:
- LLM API Key - To generate messages using an LLM, you will need to have an API Key for the LLM you are using.
- NuGet Package - Install the Microsoft Teams AI library:
dotnet add package Microsoft.Teams.AI
- In your C# application, you should include your keys securely using
appsettings.json
or environment variables
myapp/
βββ myapp.sln # Solution file
βββ myapp.slnlaunch.user # Launch configuration
βββ myapp/ # Main project directory
βββ .editorconfig # Editor configuration
βββ appsettings.json # Application configuration
βββ appsettings.Development.json # Development configuration
βββ myapp.csproj # Project file
βββ MainController.cs # Main controller
βββ Program.cs # Application entry point
βββ Properties/
βββ launchSettings.json # Launch settings
Azure OpenAIβ
You will need to deploy a model in Azure OpenAI. Here is a guide on how to do this.
Once you have deployed a model, configure your application using either appsettings.json
or environment variables:
Environment Variables
AZURE_OPENAI_API_KEY=your-azure-openai-api-key
AZURE_OPENAI_MODEL_DEPLOYMENT_NAME=your-azure-openai-model
AZURE_OPENAI_ENDPOINT=your-azure-openai-endpoint
AZURE_OPENAI_API_VERSION=your-azure-openai-api-version
info
The AZURE_OPENAI_API_VERSION
is different from the model version. This is a common point of confusion. Look for the API Version here
OpenAIβ
You will need to create an OpenAI account and get an API key. Here is a guide on how to do this.
Once you have your API key, configure your application:
Environment Variables
OPENAI_API_KEY=sk-your-openai-api-key