Skip to content

Latest commit

 

History

History
48 lines (34 loc) · 2.58 KB

README.md

File metadata and controls

48 lines (34 loc) · 2.58 KB
Raw

Book Creator Sample Learning App

!IMPORTANT This learning sample is for educational purposes only and should not be used in any production use case. It is intended to highlight concepts of Semantic Kernel and not any architectural / security design practices to be used.

Watch the Book Creator Sample Quick Start Video.

Running the sample

  1. You will need an Open AI Key or Azure Open AI Service key for this sample.
  2. Ensure the KernelHttpServer sample is already running at http://localhost:7071. If not, follow the steps to start it here.
  3. Copy .env.example into a new file with name ".env".

    Note: Samples are configured to use chat completion AI models (e.g., gpt-3.5-turbo, gpt-4, etc.). See https://platform.openai.com/docs/models/model-endpoint-compatibility for chat completion model options.

  4. You will also need to Run the following command yarn install (if you have never run the sample before) and/or yarn start from the command line.
  5. A browser will automatically open, otherwise you can navigate to http://localhost:3000 to use the sample.

Working with Secrets: KernelHttpServer's Readme has a note on safely working with keys and other secrets.

About the Book Creator Sample

The Book creator sample allows you to enter in a topic then the Planner creates a plan for the functions to run based on the ask. You can see the plan along with the results.

Caution

Each function will call Open AI which will use tokens that you will be billed for.

book-sample-app

Next Steps: Try the sample showing off how authentication and API calls work

Authentication and APIs – learn how to connect to external API's with authentication while using Semantic Kernel.

Deeper Learning Tips

  • Try modifying the language that the book is translated to via editing the translateToLanguage constant in CreateBook.tsx
  • View fetchTopics in TopicSelection.tsx to see how input variables are being fed to the ask. Try changing the number.

Next we will have a version of the sample that incorporates the planner functionality.