Combine Amazon Bedrock Information Bases with Microsoft SharePoint as a knowledge supply

Amazon Bedrock Knowledge Bases supplies basis fashions (FMs) and brokers in Amazon Bedrock contextual data out of your firm’s non-public knowledge sources for Retrieval Augmented Technology (RAG) to ship extra related, correct, and customised responses. Amazon Bedrock Information Bases gives a completely managed RAG expertise.

The information sources that may be related to as information bases are constantly increasing. This publish showcases tips on how to use one of many knowledge supply connectors; Microsoft SharePoint, an built-in content material administration and collaboration device that many organizations use for storing, organizing, and sharing their inner knowledge. See Data source connectors for the complete checklist of supported knowledge supply connectors.

Answer overview

The next are some pertinent options of the SharePoint knowledge supply inside Amazon Bedrock Information Bases:

• It supplies entry to the knowledge saved in SharePoint. The RAG structure queries and retrieves related data from the SharePoint supply to offer contextual responses based mostly on the consumer’s enter.
• It supplies the flexibility to extract structured knowledge, metadata, and different data from paperwork ingested from SharePoint to offer related search outcomes based mostly on the consumer question.
• It supplies the flexibility to sync incremental SharePoint content material updates on an ongoing foundation.
• It supplies supply attribution to the response generated by the FM.

Within the following sections, we stroll by the steps to create a information base, configure your knowledge supply, and check the answer.

Stipulations

The next are the stipulations essential to implement Amazon Bedrock Information Bases with SharePoint as a connector:

Create a information base and hook up with the information supply

Full the next steps to arrange a information base on Amazon Bedrock and hook up with a SharePoint knowledge supply:

1. On the Amazon Bedrock console, select Information bases within the navigation pane.
2. Select Create information base.

3. Within the Information base particulars part, optionally change the default title and enter an outline in your information base.
4. Within the IAM permissions part, choose an IAM position that gives Amazon Bedrock permission to entry different AWS companies. You possibly can let Amazon Bedrock create the service position or select a custom role that you have created.
5. Within the Select knowledge supply part, choose SharePoint.
6. Optionally, add tags to your information base. For extra data, see Tag resources.
7. Select Subsequent.

8. Within the Title and Description part, optionally change the default knowledge supply title and enter an outline of the information supply.
9. Within the Supply part, present the next data:
   1. For Website URLs, enter the positioning URLs to make use of for crawling and indexing the content material for RAG.
   2. For Area, enter the area title related to the information supply. For instance, if the positioning URL is https://deloittedasits.sharepoint.com/xyz.aspx, the area worth could be deloittedasits.
   3. Below Superior settings, maintain the default choices.

Whereas changing your knowledge into embeddings, Amazon Bedrock encrypts your knowledge with a key that AWS owns and manages by default. To make use of your personal AWS Key Management Service (AWS KMS) key, select Customise encryption settings (Superior) and select a key. For extra data, see Encryption of transient data storage during data ingestion.

You may also select from the next choices for the information deletion coverage in your knowledge supply:

• Delete – Deletes all underlying knowledge belonging to the information supply from the vector retailer upon deletion of a information base or knowledge supply useful resource. Notice that the vector retailer itself just isn’t deleted, solely the underlying knowledge. This flag is ignored if an AWS account is deleted.
• Retain – Retains all underlying knowledge in your vector retailer upon deletion of a information base or knowledge supply useful resource.

For extra data on managing your information base, see Manage a data source.

10. Within the Authentication part, the supported authentication methodology is ready to OAuth 2.0.
    1. For Tenant ID, enter your tenant ID. Confer with part Register a new application in the Microsoft Azure Portal of this publish to get the Tenant ID.
    2. For AWS Secrets and techniques Supervisor secret, enter an AWS Secrets Manager Confer with the part Create a Secrets Manager secret for the SharePoint data source of this publish to get the key.

The SharePoint knowledge supply will want credentials to hook up with the SharePoint On-line website utilizing the Microsoft Graph API. To facilitate this, create a brand new Secrets and techniques Supervisor secret. These credentials is not going to be utilized in any entry logs for the SharePoint On-line Website.

11. Within the Metadata Settings part, optionally choose any content material varieties that you just wish to embrace or exclude.

12. Within the Content material chunking and parsing part, choose Default.

13. Select Subsequent.
14. Within the Embeddings mannequin part, choose Titan Embeddings G1 – Textual content or one other embeddings mannequin as applicable.
15. Within the Vector database part, choose Fast create a brand new vector retailer to create a vector retailer for the embeddings.
16. Select Subsequent.

17. On the Evaluate and create web page, confirm the choices you made and select Create.

The information base creation ought to be full.

The information base with SharePoint as the information supply is now created. Nevertheless, the information supply must be synced as a way to crawl the positioning URLs and index the related content material.

18. To provoke this course of, on the information base particulars web page, choose your knowledge supply and select Sync.

Register a brand new utility within the Microsoft Azure Portal

On this part, we register a brand new utility within the Microsoft Azure Portal. We seize the Tenant ID from this step to make use of when configuring the information supply for Information Base for Amazon Bedrock. Full the next steps:

1. Open the Azure Portal and log in together with your Microsoft account. When you don’t have an account, you possibly can create one or contact your group’s administration crew.
2. Select New registration.
3. Present the next data:
   1. For Title, present the title in your utility. Let’s seek advice from this utility as TargetApp. Amazon Bedrock Information Bases makes use of TargetApp to hook up with the SharePoint website to crawl and index the information.
   2. For Who can use this utility or entry this API, select Accounts on this organizational listing solely (<Tenant title> solely – Single tenant).
   3. Select Register.
   4. Notice down the appliance (consumer) ID and the listing (tenant) ID on the Overview You’ll want them later when requested for TargetApp-ClientId and TenantId.
4. Select API permissions within the navigation pane.
5. Configure the permissions as follows:
   1. Select Add a permission.
   2. Select Microsoft Graph.
   3. Select Delegated permissions.
   4. Select Learn.All within the Consumer part.
   5. Select Learn.All within the GroupMember part.
   6. Select FullControl.All within the Websites part.
   7. Select Add permissions. This permission permits the app to learn knowledge in your group’s listing in regards to the signed-in consumer.
   8. On the choices menu (three dots), select Take away permission.
   9. Take away the unique Learn – Delegated permission.
   10. Select Grant admin consent for the default listing.

6. Select Certificates & secrets and techniques within the navigation pane.
   1. Select New consumer secret.
   2. For Description, enter an outline, similar to description of my consumer secret.
   3. Select a worth for Expires. In manufacturing, you’ll have to manually rotate your secret earlier than it expires.
   4. Select Add.
   5. Notice down the worth in your new secret. You’ll want it later when requested in your consumer secret (TargetApp-ClientSecret).
7. Optionally, select Homeowners so as to add any extra house owners for the appliance. Homeowners will have the ability to handle permissions of the Azure AD app (TargetApp).

Create a Secrets and techniques Supervisor secret for the SharePoint knowledge supply

Full the next steps to create a Secrets and techniques Supervisor secret to hook up with the SharePoint on-line websites listed as website URLs inside the knowledge supply:

1. On the Secrets and techniques Supervisor console, select Retailer a brand new secret.
2. For Secret sort, choose Different sort of secret.
3. For Key/worth pairs, enter the next:
   1. username
   2. password
   3. clientId
   4. clientSecret
4. For Encryption key, select aws/secretsmanager.
5. Select Subsequent.
6. Within the Secret title and outline part, enter the title of the key and an optionally available description.
7. Add any related tags within the Tags
8. Depart Useful resource permissions and Replication secret as default.
9. Select Subsequent.
10. Within the Configure rotation part, go away as default or modify in accordance with your organizational insurance policies.
11. Select Subsequent.
12. Evaluate the choices you chose and select Retailer.
13. On the secrets and techniques element web page, notice your secret ARN worth for use as the key when creating the Information Base for Amazon Bedrock.

Check the answer

Full the next steps to check the information base you created:

1. On the Amazon Bedrock console, select Information bases within the navigation pane.
2. Choose the information base you created and select Check.

3. Select an applicable mannequin for testing and select Apply.

4. Enter your query for the content material housed within the SharePoint website.

Clear up

When you created a brand new information base to experiment utilizing this publish and don’t plan to make use of it additional, delete the information base in order that your AWS account doesn’t accumulate prices. For directions, see Manage a knowledge base.

Conclusion

On this publish, we confirmed you tips on how to configure Amazon Bedrock Information Bases with SharePoint On-line as a knowledge supply. By connecting SharePoint On-line as a knowledge supply, staff can work together with the group’s information and knowledge saved in SharePoint utilizing pure language, making it simple to seek out related data, extract key factors, and derive invaluable insights. This could considerably enhance productiveness, decision-making, and information sharing inside the group.

Do that function on the Amazon Bedrock console right this moment! See Amazon Bedrock Knowledge Bases to be taught extra.

In regards to the Authors

Surendar Gajavelli is a Sr. Options Architect based mostly out of Nashville, Tennessee. He’s a passionate know-how fanatic who enjoys working with prospects and serving to them construct revolutionary options.

Abhi Patlolla is a Sr. Options Architect based mostly out of the New York Metropolis area, serving to prospects of their cloud transformation, AI/ML, and knowledge initiatives. He’s a strategic and technical chief, advising executives and engineers on cloud methods to foster innovation and constructive influence.