Skip to content

Latest commit

 

History

History
108 lines (74 loc) · 4.14 KB

README.md

File metadata and controls

108 lines (74 loc) · 4.14 KB
Raw

Semantic Kernel C# Hello World Starter

The sk-csharp-hello-world console application demonstrates how to execute a semantic function.

Prerequisites

Configuring the starter

The starter can be configured by using either:

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 global secrets

  • spotifyClientId: The client id of your Spotify app (required to play music)
  • spotifyDeviceId: The device id of the device you want to play music on. You can get it by running the api call here
  • darkCafyUrl: The URL of the DarkCafy server. If used with flutter, it should be your phone IP address.
dotnet user-secrets set "spotifyClientId" "..."
dotnet user-secrets set "spotifyDeviceId" "..."
dotnet user-secrets set "darkCafyUrl" "http://..."

Configure an OpenAI endpoint

cd sk-csharp-hello-world
dotnet user-secrets set "serviceType" "OpenAI"
dotnet user-secrets set "serviceId" "gpt-3.5-turbo"
dotnet user-secrets set "modelId" "gpt-3.5-turbo"
dotnet user-secrets set "apiKey" "... your OpenAI key ..."

Configure an Azure OpenAI endpoint

cd sk-csharp-hello-world
dotnet user-secrets set "serviceType" "AzureOpenAI"
dotnet user-secrets set "serviceId" "gpt-35-turbo"
dotnet user-secrets set "deploymentId" "gpt-35-turbo"
dotnet user-secrets set "modelId" "gpt-3.5-turbo"
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 OpenAI endpoint

  1. Copy settings.json.openai-example to ./Config/appsettings.json
  2. Edit the file to add your OpenAI endpoint configuration

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 console application just hit F5.

To build and run the console application from the terminal use the following commands:

dotnet build
dotnet run

Troubleshooting

Getting a 400 (BadRequest) and error "Azure.RequestFailedException: logprobs, best_of and echo parameters are not available on gpt-35-turbo model. Please remove the parameter and try again."

A chat completion model (gpt-35-turbo) was set in serviceId/deploymentOrModelId while the kernel was configured to use a text completion model. The type of model used by the kernel can be configured with the endpointType secret. To fix, you can either:

  • change endpointType to chat-completion
dotnet user-secrets set "endpointType" "chat-completion"