Skip to content

ai-collab

Directory actions

More options

Directory actions

More options

Latest commit

 

History

History

ai-collab

README.md

@fluid-example/ai-collab

This is an example app that showcases the @fluidframework/ai-collab package to interact with an LLM (Large Language Model).

By default it uses Tinylicious as the server, but you can also use SharePoint embedded. Steps to do that are detailed below.

Pre-requisites

In order for the app to showcase the LLM interaction, you need to provide an OpenAI API key. Copy the .env.example file, rename the copy to .env, and replace the value of the OPEN_AI_KEY variable with your API key. Note that the app leverages the gpt-o4 model and thus an API key for a paid account is required. If you provide an API key for a free account, the app will still render, but requesting AI assistance will fail.

Getting Started

You can run this example using the following steps:

  1. Enable corepack by running corepack enable.
  2. Run pnpm install and pnpm run build:fast --nolint from the FluidFramework root directory.
    • For an even faster build, you can add the package name to the build command, like this: pnpm run build:fast --nolint @fluid-example/ai-collab
  3. Start a Tinylicious server by running pnpm start:server from this directory.
  4. In a separate terminal also from this directory, run pnpm start and open http://localhost:3000/ in a web browser to see the app running.

Using SharePoint embedded instead of tinylicious

  1. Go to page.tsx, look for comment // Uncomment the import line that corresponds to the server you want to use, comment the line for tinylicious and uncomment the line for SharePoint Embedded.
  2. In the same .env file you created in the pre-requisites section, set the correct values for the following variables:
  • NEXT_PUBLIC_SPE_CLIENT_ID
  • NEXT_PUBLIC_SPE_CONTAINER_TYPE_ID
  • NEXT_PUBLIC_SPE_ENTRA_TENANT_ID

You can get all of them through the SharePoint Embedded for Visual Studio Code extension.

Contribution Guidelines

There are many ways to contribute to Fluid.

Detailed instructions for working in the repo can be found in the Wiki.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

This project may contain Microsoft trademarks or logos for Microsoft projects, products, or services. Use of these trademarks or logos must follow Microsoft’s Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.

Help

Not finding what you're looking for in this README? Check out fluidframework.com.

Still not finding what you're looking for? Please file an issue.

Thank you!

Trademark

This project may contain Microsoft trademarks or logos for Microsoft projects, products, or services.

Use of these trademarks or logos must follow Microsoft's Trademark & Brand Guidelines.

Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.