Skip to content

Files

Latest commit

 

History

History

intelligent-data-chart-generator

README.md

page_type languages products name urlFragment description extensions
sample
typescript
office-teams
Intelligent Data Chart Generator
officedev-teamsfx-samples-intelligent-data-chart-generator
Intelligent Microsoft Teams Tab app visualizing data charts based on human-language description. Powered by Azure OpenAI and Azure SQL.
createdDate
2024-01-08

Getting Started with Intelligent Data Chart Generator

This intelligent Microsoft Teams Tab app is powered by Azure OpenAI, which helps users generating data charts based on users' description of the data chart in human language. There is an input box where users tell the Tab app what data chart they want to generate, and the app interprets user's requirements then generate visual charts. The data is from Azure SQL. This sample demonstrates how to build a seamless and intuitive experience for accessing and interpreting data.

Intelligent Chart

Note: This sample will only provision single tenant Azure Active Directory app. For multi-tenant support, please refer to this wiki.

This sample illustrates

  • How to use Azure Open AI to generate data visualization based on verbal descriptions.
  • How to display the generated data visualization in Teams tab.
  • How to query data from Azure SQL database.
  • How to use TeamsFx to build backend hosting on Azure for your tab app.

Prerequisite to use this sample

Minimal path to awesome

Here are the instructions to run the sample in Visual Studio Code. You can also try to run the app using Teams Toolkit CLI tool, refer to Try the Sample with Teams Toolkit CLI

Run the app locally

  1. Clone the repo to your local workspace or directly download the source code.

  2. Open the project in Visual Studio Code.

  3. Update the .env.local.user file to add your Azure OpenAI configuration. Your configuration should look like this:

    SECRET_OPENAI_ENDPOINT=https://<your-instance-name>.openai.azure.com/
SECRET_OPENAI_DEPLOYMENT_NAME=<your-deployment-name>
SECRET_OPENAI_API_KEY=<your-api-key>

    If you have not created an Azure OpenAI resource or deployed a model, please follow this tutorial to create one.

  4. Update the .env.local.user file to add your Azure SQL Database configuration. Your configuration should look like this:

    SQL_USER=<your-sql-user-name>
SECRET_SQL_PASSWORD=<your-sql-password>
SQL_SERVER=<your-sql-server-name>.database.windows.net
SQL_DATABASE=<your-sql-database-name>

    If you have not created an Azure SQL Database resource, please follow this tutorial to create one. Once you've set up the Azure database, you can use /data/script.sql file to create the table and insert some sample data.

  5. Press F5 to start the app locally.

Deploy the app to Azure

Deploy your project to Azure by following these steps:

  1. Open Teams Toolkit in Visual Studio Code, and sign in your Azure account by clicking the Sign in to Azure in the ACCOUNTS section from sidebar.
  2. After you signed in, select a subscription under your account. The Teams Toolkit will use this subscription to provision Azure resources to host you app.
  3. Update the .env.dev.user file to add your Azure Open AI and Azure SQL configurations.
  4. Open the Teams Toolkit and click Provision in the LIFECYCLE section. Alternatively open the command palette(Ctrl+Shift+P) and type: Teams: Provision command.
  5. Open the Teams Toolkit and click Deploy in the LIFECYCLE section. Alternatively open the command palette(Ctrl+Shift+P) and type: Teams: Deploy command.

Note: Provision Azure cloud resources and deploy to Azure may cause charges to your Azure Subscription.

Preview the app in Teams

After you have completed the provision and deploy steps in Deploy the app to Azure section, you can preview your app in Teams client by following steps below:

  1. Open the Run and Debug panel from sidebar, or use short key Ctrl+Shift+D.
  2. Select Launch Remote (Edge) or Launch Remote (Chrome) in the launch configuration (a dropdown selection in the upper-left corner).
  3. Press the Start Debugging button to launch your app, the Teams web client will be automatically opened in your browser, where you will see your app running remotely from Azure.

Version History

Date Author Comments
Jan 8, 2024 Hui Miao Onboard sample in Teams Toolkit V5.0.0
Feb 27, 2024 Hui Upgrade Azure Function V4

Feedback

We really appreciate your feedback! If you encounter any issue or error, please report issues to us following the Supporting Guide. Meanwhile you can make recording of your journey with our product, they really make the product better. Thank you!