Amazon Q is a brand new generative AI-powered software that helps customers get work completed. Amazon Q can grow to be your tailor-made enterprise skilled and allow you to uncover content material, brainstorm concepts, or create summaries utilizing your organization’s information safely and securely. You should use Amazon Q to have conversations, resolve issues, generate content material, acquire insights, and take motion by connecting to your organization’s data repositories, code, information, and enterprise techniques. For extra data, see Introducing Amazon Q, a brand new generative AI-powered assistant (preview).
On this publish, we present you tips on how to carry Amazon Q, your enterprise skilled, to customers in Microsoft Groups. (Should you use Slack, check with Deploy a Slack gateway for Amazon Q, your enterprise skilled.)
You’ll give you the chance converse with Amazon Q enterprise skilled utilizing Groups direct messages (DMs) to ask questions and get solutions primarily based on firm information, get assist creating new content material akin to e mail drafts, summarize connected information, and carry out duties.
You can too invite Amazon Q enterprise skilled to take part in your Groups channels. In a channel, customers can ask Amazon Q enterprise skilled questions in a brand new message, or tag it in an present thread at any level, to supply extra information factors, resolve a debate, or summarize the dialog and seize the following steps.
Resolution overview
Amazon Q enterprise skilled is amazingly highly effective. Take a look at the next demo—seeing is believing!
Within the demo, our Amazon Q enterprise skilled software is populated with some Wikipedia pages. You possibly can populate your Amazon Q enterprise skilled software with your personal firm’s paperwork and data base articles, so it is going to be capable of reply your particular questions!
Every thing you want is offered as open supply in our GitHub repo.
On this publish, we stroll you thru the method to deploy Amazon Q enterprise skilled in your AWS account and add it to Microsoft Groups. While you’re completed, you’ll marvel the way you ever managed with out it!
The next are a few of the issues it could possibly do:
Reply to messages – In DMs, it responds to all messages. In channels, it responds solely to @mentions and responds in a dialog thread.
Render solutions containing markdown – This contains headings, lists, daring, italics, tables, and extra.
Observe sentiment – It offers thumbs up and thumbs down buttons to trace person sentiment.
Present supply attribution – It offers references and hyperlinks to sources utilized by Amazon Q enterprise skilled.
Perceive dialog context – It tracks the dialog and responds primarily based on the context.
Keep conscious of a number of customers – When it’s tagged in a thread, it is aware of who stated what, and when, so it could possibly contribute in context and precisely summarize the thread when requested.
Course of connected information – It might probably course of as much as 5 connected information for doc query answering, summaries, and extra.
Begin new conversations – You possibly can reset and begin new conversations in DM chats through the use of /new_conversation.
Within the following sections, we present tips on how to deploy the challenge to your personal AWS account and Groups account, and begin experimenting!
Conditions
That you must have an AWS account and an AWS Id and Entry Administration (IAM) function and person with permissions to create and handle the required assets and parts for this software. Should you don’t have an AWS account, see How do I create and activate a brand new Amazon Net Companies account?
You additionally must have an present, working Amazon Q enterprise skilled software. Should you haven’t set one up but, see Creating an Amazon Q software.
Lastly, you want a Microsoft account and a Microsoft Groups subscription to create and publish the app utilizing the steps outlined on this publish. Should you don’t have these, see if your organization can create sandboxes so that you can experiment, or create a brand new account and trial subscription as wanted to finish the steps.
Deploy the answer assets
We’ve offered pre-built AWS CloudFormation templates that deploy every thing you want in your AWS account.
Should you’re a developer and also you need to construct, deploy, or publish the answer from code, check with the Developer README.
Full the next steps to launch the CloudFormation stack:
Log in to the AWS Administration Console.
Select one of many following Launch Stack buttons on your desired AWS Area to open the AWS CloudFormation console and create a brand new stack.
Area
Launch Stack
N. Virginia (us-east-1)
Oregon (us-west-2)
For Stack identify, enter a reputation on your app (for instance, AMAZON-Q-TEAMS-GATEWAY).
For AmazonQAppId, enter your present Amazon Q enterprise skilled software ID (for instance, 80xxxxx9-7xx3-4xx0-bxx4-5baxxxxx2af5). You possibly can copy it from the Amazon Q enterprise skilled console.
For AmazonQRegion, select the Area the place you created your Amazon Q enterprise skilled software (us-east-1 or us-west-2).
For AmazonQUserId, enter an Amazon Q enterprise skilled person ID e mail deal with (depart clean to make use of a Groups person e mail because the person ID).
For ContextDaysToLive, enter the size of time to maintain dialog metadata cached in Amazon DynamoDB (you’ll be able to depart this because the default).
When your CloudFormation stack standing is CREATE_COMPLETE, select the Outputs tab, and hold it open—you’ll want it in later steps.
Register a brand new app within the Microsoft Azure portal
Full the next steps to register a brand new app within the Microsoft Azure portal:
Go to the Azure Portal and log in along with your Microsoft account.
Select New registration.
For Title, present the identify on your app. You possibly can hold issues easy through the use of the stack identify you used for the CloudFormation stack.
For Who can use this software or entry this API?, select Accounts on this organizational listing solely (AWS solely – Single tenant).
Select Register.
Word down the Utility (shopper) ID worth and the Listing (tenant) ID from the Overview web page. You’ll want them later when requested for MicrosoftAppId and MicrosoftAppTenantId.
Select Choose API permissions within the navigation pane.
Select Add a permission.
Select Microsoft Graph.
Select Utility permissions.
Choose Person.Learn.All.
Choose ChannelMessage.Learn.All.
Choose Workforce.ReadBasic.All.
Choose Information.Learn.All.
Select Add permissions. This permission permits the app to learn information in your group’s listing in regards to the signed-in person.
Use the choices menu (three dots) on the fitting to decide on Take away permission.
Take away the unique Person.Learn – Delegated permission.
Select Grant admin consent for Default Listing.
Select Certificates & secrets and techniques within the navigation pane.
Select New shopper secret.
For Description, present a worth, akin to description of my shopper secret.
Select a worth for Expires. Word that in manufacturing, you’ll must manually rotate your secret earlier than it expires.
Select Add.
Word down the worth on your new secret. You’ll want it later when requested for MicrosoftAppPassword.
Optionally, select Homeowners so as to add any extra house owners for the applying.
Register your new app within the Microsoft Bot Framework
Full the next steps to register your app within the Microsoft Bot Framework:
Go to the Microsoft Bot Framework and log in along with your Microsoft account.
Optionally, you’ll be able to create and add a customized icon on your new Amazon Q enterprise skilled bot. For instance, we created the next utilizing Amazon Bedrock picture playground.
Enter your most well-liked show identify, bot deal with, and outline.
For Messaging endpoint, copy and paste the worth of TeamsEventHandlerApiEndpoint out of your stack Outputs tab.
Don’t choose Allow Streaming Endpoint.
For App kind, select Single Tenant.
For Paste your app ID beneath to proceed, enter the MicrosoftAppId worth you famous earlier.
For App Tenant ID, enter the MicrosoftAppTenantId worth you famous earlier.
Go away the opposite values as they’re, comply with the phrases, and select Register.
On the Channels web page, below Add a featured channel, select Microsoft Groups.
Select Microsoft Groups Industrial (commonest), then select Save.
Conform to the Phrases of Service and select Agree.
Configure your secrets and techniques in AWS
Let’s configure your Groups secrets and techniques as a way to confirm the signature of every request and publish on behalf of your Amazon Q enterprise skilled bot.
On this instance, we aren’t enabling Groups token rotation. You possibly can allow it for a manufacturing app by implementing rotation by way of AWS Secrets and techniques Supervisor. Create a difficulty (or, higher but, a pull request) within the GitHub repo if you’d like this function added to a future model.
Full the next steps to configure a secret in Secrets and techniques Supervisor:
On the AWS CloudFormation console, navigate to your stack Outputs tab and select the hyperlink for TeamsSecretConsoleUrl to be redirected to the Secrets and techniques Supervisor console.
Select Retrieve secret worth.
Select Edit.
Substitute the values of MicrosoftAppId, MicrosoftAppPassword, and MicrosoftAppTenantId with the values you famous within the earlier steps.
Deploy your app into Microsoft Groups
Full the next steps to deploy the app to Groups:
Go to the Developer Portal for Groups and log in along with your Microsoft Groups person account.
Select Apps within the navigation pane, then select New app.
For Title, enter your bot identify.
Enter a reputation for Full identify and each quick and full descriptions (you need to use the bot identify for all of them if you’d like, simply don’t depart them empty).
Enter values for Developer data and App URLs. For testing, you can also make up values, and URLs like https://www.anycompany.com/. Use actual ones for manufacturing.
For Utility (shopper) ID*, enter the worth of MicrosoftAppId from earlier.
Select Save.
Below Branding, you’ll be able to add AI-generated icons, or completely different icons, or none in any respect, it’s as much as you. The next are some examples:
Shade icon 192×192
Define icon 32×32
Below App options, select Bot.
Choose Enter a bot ID, and enter the MicrosoftAppId worth from the sooner steps.
Below What can your bot do?, choose Add and obtain information.
Below Choose the scopes through which individuals can use this command, choose Private, Workforce, and Group chat.
Select Save.
Select Publish.
Select Obtain the app package deal to obtain a .zip file to your pc.
Select Preview in Groups to launch Microsoft Groups (work or college) app.
Within the navigation pane, select Apps, then Handle your apps, then Add an app.
Select Add an app to your orgs app catalog, and choose the .zip file you downloaded. This provides the app to Groups.
Choose the cardboard on your new app, select Add, and look forward to it to finish (10–20 seconds).
Add your bot to a number of groups
Full the next step so as to add your bot to a crew:
Within the Groups app, choose your crew and select Handle crew.
On the Apps tab, select the brand new Amazon Q enterprise skilled app, and select Add.
Now you’ll be able to check your bot in Microsoft Groups!
Begin utilizing Amazon Q enterprise skilled
Full the next steps to start out utilizing Amazon Q enterprise skilled in Groups:
Open your Groups shopper.
Below Apps, add your new Amazon Q enterprise skilled app to a chat.
Optionally, add your Amazon Q enterprise skilled app to a number of Groups channels.
Within the app DM chat, enter Good day.
You’ve now deployed a robust new AI assistant into your sandbox Groups setting.
Play with it, strive all of the options mentioned on this publish, and duplicate the stuff you noticed within the demo video. Most significantly, you’ll be able to ask about subjects associated to the paperwork that you’ve got ingested into your personal Amazon Q enterprise skilled software. However don’t cease there. You could find extra methods to make it helpful, and whenever you do, tell us by posting a remark.
As soon as you’re satisfied how helpful it’s, speak to your Groups admins (present them this publish) and work with them to deploy it in your organization’s Groups organizations. Your fellow workers will thanks!
Clear up
While you’re completed experimenting with this resolution, delete your app in Microsoft Groups, Bot Framework, and Azure portal. Then clear up your AWS assets by opening the AWS CloudFormation console and deleting the AMAZON-Q-TEAMS-GATEWAY stack that you simply deployed. This deletes the assets that you simply created by deploying the answer.
Conclusions
The pattern Amazon Q enterprise skilled Groups software mentioned on this publish is offered as open supply—you need to use it as a place to begin on your personal resolution, and assist us make it higher by contributing again fixes and options by way of GitHub pull requests. Discover the code, select Watch within the GitHub repo to be notified of latest releases, and verify again for the most recent updates. We’d additionally love to listen to your solutions for enhancements and options.
For extra data on Amazon Q enterprise skilled, check with the Amazon Q (For Enterprise Use) Developer Information.
In regards to the Authors
Gary Benattar is a Senior Software program Growth Supervisor in AWS HR. Gary began at Amazon in 2012 as an intern, specializing in constructing scalable, real-time outlier detection techniques. He labored in Seattle and Luxembourg and is now primarily based in Tel Aviv, Israel, the place he dedicates his time to constructing software program to revolutionize the way forward for Human Assets. He co-founded a startup, Zengo, with a deal with making digital wallets safe by means of multi-party computation. He acquired his MSc in Software program Engineering from Sorbonne College in Paris.
Bob Strahan is a Principal Options Architect within the AWS Language AI Companies crew.