Skip to content

docs: Add documentation for integrated vectorization. #834

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
May 10, 2024
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,9 @@ Now that the financial advisor is more informed about Woodgrove’s Emerging Mar

Note: Some of the sample data included with this accelerator was generated using AI and is for illustrative purposes only.

### Integrated Vectorization
The Chat with your data accelerator supports Integrated Vectorization, an Azure AI Search feature that pulls, processes and indexes data directly from Azure storage. This greatly simplifies the code that needs to be maintained by developers deploying the accelerator since the chunking, vectorization and indexing of data is handled by Azure AI's built-in pull-indexers. Learn more about deploying with Integrated Vectorization [here](./docs/INTEGRATED_VECTORIZATION.md).

### Speech-to-text functionality
Many users are used to the convenience of speech-to-text functionality in their consumer products. With hybrid work increasing, speech-to-text supports a more flexible way for users to chat with their data, whether they’re at their computer or on the go with their mobile device. The speech-to-text capability is combined with NLP capabilities to extract intent and context from spoken language, allowing the chatbot to understand and respond to user requests more intelligently.

Expand Down
14 changes: 14 additions & 0 deletions docs/INTEGRATED_VECTORIZATION.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
[Back to *Chat with your data* README](../README.md)

# Integrated Vectorization
[**USER STORY**](#user-story) | [**DEPLOYMENT INSTRUCTIONS**](#local-deployment-instructions)
\
\
![User Story](/media/userStory.png)
## User Story
This feature allows chunking and vectorization of data during ingestion into Azure AI Search through built-in pull-indexers. It supports automatic processing of data directly from storage - meaning the user can just upload their data to Azure Blob Storage and the built-in pull-indexers will do the chunking, vectorization and indexing. This removes the need for Chat With Your Data to explicitly perform chunking, vectorization and pushing to the search index.

## Local Deployment Instructions
In addition to the standard local deployment instructions, do the following to enable Integrated Vectorization:

* Run `azd env set AZURE_SEARCH_USE_INTEGRATED_VECTORIZATION true` before running `azd up`.
48 changes: 24 additions & 24 deletions docs/TEAMS_EXTENSION.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
[Back to *Chat with your data* README](../README.md)

# Teams extension
[**USER STORY**](#user-story) | [**TEAMS DEPLOY**](#teams-deploy) | [**SUPPORTING DOCUMENTATION**](#supporting-documentation)
[**USER STORY**](#user-story) | [**TEAMS DEPLOY**](#deployment-to-teams) | [**SUPPORTING DOCUMENTATION**](#supporting-documentation)
\
\
![User Story](/media/userStory.png)
Expand All @@ -11,24 +11,24 @@ This extension enables users to experience Chat with your data within Teams, wit
## Deployment to Teams
**IMPORTANT**: Before you proceed, installation and configuration of the [Chat with your data with speech-to-text deployment](../README.md) is required.

### Pre-requisites
### Pre-requisites
- [Visual Studio Code](https://code.visualstudio.com/)
- Extensions
- [Teams Toolkit](https://marketplace.visualstudio.com/items?itemName=TeamsDevApp.ms-teams-vscode-extension) (optional: Teams extension only)
- Install [Node.js](https://nodejs.org/en)
- Install the LTS version (Recommended for Most Users)
- [Enable custom Teams apps and turn on custom app uploading](https://learn.microsoft.com/en-us/microsoftteams/platform/concepts/build-and-test/prepare-your-o365-tenant#enable-custom-teams-apps-and-turn-on-custom-app-uploading) (optional: Teams extension only)
- In order to publish the App to the Teams Store, the Teams Administrator role is required.
- In order to publish the App to the Teams Store, the Teams Administrator role is required.

### Deploy Teams application
1. Clone this GitHub repo.
2. Open the “extensions/teams” folder with Visual Studio Code
2. Open the “extensions/teams” folder with Visual Studio Code

![Teams](/media/teams.png)
![Teams](/media/teams.png)

3. Open the file env\\.env.test

![ENV](/media/teams-1.png)
![ENV](/media/teams-1.png)

4. Locate the environment variable _AZURE_FUNCTION_URL_.
5. Replace the `<RESOURCE_TOKEN>` and `<FUNCTION_APP_CLIENT_KEY>` with the name of your Function App resource and its clientKey (created in previous section)
Expand All @@ -38,14 +38,14 @@ This extension enables users to experience Chat with your data within Teams, wit
```
![Env](/media/teams-deploy-env.png)
6. Save the file.
7. Select Teams Toolkit from the navigation panel.
7. Select Teams Toolkit from the navigation panel.

![Teams Toolkit in VS Code](/media/teams-2.png)
![Teams Toolkit in VS Code](/media/teams-2.png)

8. Within the Teams Toolkit panel, login to the following accounts:

**Sign in to Microsoft 365**: Use your Microsoft 365 work or school account with a valid E5 subscription for building your app. If you don't have a valid account, you can join [Microsoft 365 developer program](https://developer.microsoft.com/microsoft-365/dev-program) to get a free account before you start.

**Sign in to Azure**: Use your Azure account for deploying your app on Azure. You can [create a free Azure account](https://azure.microsoft.com/free/) before you start.

![Teams Toolkit Accounts](/media/teams-3.png)
Expand All @@ -60,11 +60,11 @@ This extension enables users to experience Chat with your data within Teams, wit

11. Within the command palette, select **test** for the environment.

![Select an Environment](/media/teams-6.png)
![Select an Environment](/media/teams-6.png)

12. Select the resource group created earlier in the installation

![Select a Resource Group](/media/teams-7.png)
![Select a Resource Group](/media/teams-7.png)

13. When prompted about Azure charges, select **Provision**.

Expand All @@ -76,15 +76,15 @@ This extension enables users to experience Chat with your data within Teams, wit

15. Under **Lifecycle**, select **Deploy**.

![Teams Toolkit Lifecycle Deploy](/media/teams-10.png)
![Teams Toolkit Lifecycle Deploy](/media/teams-10.png)

16. Within the command palette, select **test** for the environment.

![Select an Environment](/media/teams-6.png)
![Select an Environment](/media/teams-6.png)

17. When prompted, select **Deploy**.

![VS Code Prompt to Deploy](/media/teams-11.png)
![VS Code Prompt to Deploy](/media/teams-11.png)

18. Verify that the Deployment was successful.

Expand All @@ -96,43 +96,43 @@ This extension enables users to experience Chat with your data within Teams, wit

20. Within the command palette, select **test** for the environment.

![Select an Environment](/media/teams-6.png)
![Select an Environment](/media/teams-6.png)

21. Verify that the Publish was successful.

![Publishing successful](/media/teams-14.png)
![Publishing successful](/media/teams-14.png)

22. Select **Go to admin portal**.

![Go to Admin Portal](/media/teams-15.png)
![Go to Admin Portal](/media/teams-15.png)

23. On the Manage apps page within the Teams Admin portal, you should see one submitted custom app pending approval.

![Pending Approval](/media/teams-16.png)
![Pending Approval](/media/teams-16.png)

24. In the search by name input box, enter: **enterprise chat**

![Filtered app](/media/teams-17.png)
![Filtered app](/media/teams-17.png)

25. Select the app and then select **Allow**.

![Selected app](/media/teams-18.png)
![Selected app](/media/teams-18.png)

26. Select the app name.

![Select app name](/media/teams-19.png)
![Select app name](/media/teams-19.png)

27. Select **Publish**.

![Publish app](/media/teams-20.png)

28. When prompted, select **Publish**.

![Prompt to publish](/media/teams-21.png)
![Prompt to publish](/media/teams-21.png)

29. Depending on your environment, it may take several hours to publish.

![Teams Publish Success](/media/teams-22.png)
![Teams Publish Success](/media/teams-22.png)


### [Local deployment instructions](./TEAMS_LOCAL_DEPLOYMENT.md)
Expand All @@ -144,4 +144,4 @@ To customize the accelerator or run it locally, first, copy the .env.sample file
## Supporting documentation
### Resource links for Teams extension
This solution accelerator deploys the following resources. It's crucial to comprehend the functionality of each. Below are the links to their respective documentation:
- [Bots in Microsoft Teams - Teams | Microsoft Learn](https://learn.microsoft.com/en-us/microsoftteams/platform/bots/what-are-bots)
- [Bots in Microsoft Teams - Teams | Microsoft Learn](https://learn.microsoft.com/en-us/microsoftteams/platform/bots/what-are-bots)