Semantic Kernel Plugin using Azure Functions

The sk-csharp-azure-functions Azure Functions application demonstrates how to execute a semantic function.

Prerequisites

• .NET 6 is required to run this starter.
• Azure Functions Core Tools is required to run this starter.
• Install the recommended extensions
  • C#
  • Semantic Kernel Tools

Configuring the starter

The starter can be configured by using either:

• Enter secrets at the command line with .NET Secret Manager
• Enter secrets in appsettings.json

For Debugging the console application alone, we suggest using .NET Secret Manager to avoid the risk of leaking secrets into the repository, branches and pull requests.

Using .NET Secret Manager

Configure an OpenAI endpoint

cd sk-csharp-azure-functions
dotnet user-secrets set "serviceType" "OpenAI"
dotnet user-secrets set "serviceId" "text-davinci-003"
dotnet user-secrets set "deploymentOrModelId" "text-davinci-003"
dotnet user-secrets set "apiKey" "... your OpenAI key ..."

Configure an Azure OpenAI endpoint

cd sk-csharp-azure-functions
dotnet user-secrets set "serviceType" "AzureOpenAI"
dotnet user-secrets set "serviceId" "text-davinci-003"
dotnet user-secrets set "deploymentOrModelId" "text-davinci-003"
dotnet user-secrets set "endpoint" "https:// ... your endpoint ... .openai.azure.com/"
dotnet user-secrets set "apiKey" "... your Azure OpenAI key ..."

Configure the Semantic Kernel logging level

dotnet user-secrets set "LogLevel" 0

Log levels:

• 0 = Trace
• 1 = Debug
• 2 = Information
• 3 = Warning
• 4 = Error
• 5 = Critical
• 6 = None

Using appsettings.json

Configure an Azure OpenAI endpoint

1. Copy settings.json.azure-example to ./config/appsettings.json
2. Edit the file to add your Azure OpenAI endpoint configuration

Running the starter

To run the Azure Functions application just hit F5.

To build and run the Azure Functions application from a terminal use the following commands:

dotnet build
func start --csharp