Skip to content

Commit 6a5e8bb

Browse files
committed
add draft of teams app content
1 parent caf0de8 commit 6a5e8bb

File tree

1 file changed

+49
-3
lines changed

1 file changed

+49
-3
lines changed

articles/ai-services/openai/concepts/use-your-data.md

Lines changed: 49 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -297,19 +297,65 @@ Along with using Elasticsearch databases in Azure OpenAI Studio, you can also us
297297

298298
---
299299

300-
## Deploy to a copilot (preview) or web app
300+
## Deploy to a copilot (preview), Teams app (preview), or web app
301301

302302
After you connect Azure OpenAI to your data, you can deploy it using the **Deploy to** button in Azure OpenAI studio.
303303

304304
:::image type="content" source="../media/use-your-data/deploy-model.png" alt-text="A screenshot showing the model deployment button in Azure OpenAI Studio." lightbox="../media/use-your-data/deploy-model.png":::
305305

306-
This gives you the option of deploying a standalone web app for you and your users to interact with chat models using a graphical user interface. See [Use the Azure OpenAI web app](../how-to/use-web-app.md) for more information.
306+
This gives you multiple options for deploying your model.
307307

308-
You can also deploy to a copilot in [Copilot Studio](/microsoft-copilot-studio/fundamentals-what-is-copilot-studio) (preview) directly from Azure OpenAI studio, enabling you to bring conversational experiences to various channels such as: Microsoft Teams, websites, Dynamics 365, and other [Azure Bot Service channels](/microsoft-copilot-studio/publication-connect-bot-to-azure-bot-service-channels). The tenant used in the Azure OpenAI service and Copilot Studio (preview) should be the same. For more information, see [Use a connection to Azure OpenAI On Your Data](/microsoft-copilot-studio/nlu-generative-answers-azure-openai).
308+
#### [Copilot](#tab/copilot)
309+
310+
You can deploy to a copilot in [Copilot Studio](/microsoft-copilot-studio/fundamentals-what-is-copilot-studio) (preview) directly from Azure OpenAI studio, enabling you to bring conversational experiences to various channels such as: Microsoft Teams, websites, Dynamics 365, and other [Azure Bot Service channels](/microsoft-copilot-studio/publication-connect-bot-to-azure-bot-service-channels). The tenant used in the Azure OpenAI service and Copilot Studio (preview) should be the same. For more information, see [Use a connection to Azure OpenAI On Your Data](/microsoft-copilot-studio/nlu-generative-answers-azure-openai).
309311

310312
> [!NOTE]
311313
> Deploying to a copilot in Copilot Studio (preview) is only available in US regions.
312314
315+
#### [Teams app](#tab/teams)
316+
317+
You can deploy to a standalone Teams app (preview) directly from Azure OpenAI Studio, enabling you to bring conversational experience to your users in Teams to improve operational efficiency and democratize access of information. This Teams app is limited to users within a single tenant and personal chat (non-group chat) scenarios.
318+
319+
As a developer, follow the steps below:
320+
321+
1. Make sure you have fulfilled the prerequisite here
322+
* Tutorial - Build Custom Copilot - Teams | Microsoft Learn
323+
* Sign in to you M365 account and enable “custom app upload”
324+
* How to install the Azure CLI | Microsoft Learn
325+
* You have “Cognitive Service OpenAI user” role of the AOAI resource you are using
326+
327+
1. After you have added your data, click “deploy” and then “a Teams app(preview)”. Enter the name of your Teams app and download the zip file
328+
329+
1. Extract the zip file and open the folder in VSCode.
330+
331+
1. If you chose “API key” in data connection, manually copy and paste your Azure AI Search key in `src\prompts\chat\config.json` file. If you chose “system assigned managed identity”, you can skip this step. Learn more about different data connection options here
332+
333+
1. Click “debug in Edge” to run it locally only in your environment.
334+
335+
1. After you have tested it locally, you can provision, deploy and finally publish your Teams app.
336+
337+
1. Provision your app: https://learn.microsoft.com/en-us/microsoftteams/platform/toolkit/provision
338+
1. Go to Azure portal and select the resource group, select the newly created Azure App Service
339+
1. Go to settings > identity, enable system assigned identity
340+
1. Click “Azure role assignments” and click “add role assignments”.
341+
1. Scope: resource group
342+
1. Subscription: the subscription of your AOAI resource
343+
1. Resource group of your AOAI resource
344+
1. Role: Cognitive Service OpenAI user
345+
346+
1. Deploy to Azure: https://learn.microsoft.com/en-us/microsoftteams/platform/toolkit/deploy
347+
348+
1. Publish to Teams: https://learn.microsoft.com/en-us/microsoftteams/platform/toolkit/publish
349+
350+
351+
See also [Tutorial - Build Custom Copilot](https://learn.microsoft.com/en-us/microsoftteams/platform/teams-ai-library-tutorial).
352+
353+
#### [Web app](#tab/web-app)
354+
355+
Deploying to a standalone web app lets you and your users to interact with chat models through a graphical user interface. See [Use the Azure OpenAI web app](../how-to/use-web-app.md) for more information.
356+
357+
---
358+
313359
## Use Azure OpenAI On Your Data securely
314360

315361
You can use Azure OpenAI On Your Data securely by protecting data and resources with Microsoft Entra ID role-based access control, virtual networks, and private endpoints. You can also restrict the documents that can be used in responses for different users with Azure AI Search security filters. See [Securely use Azure OpenAI On Your Data](../how-to/use-your-data-securely.md).

0 commit comments

Comments
 (0)