Loading...

Streamline Location-Specific Policies with SharePoint and Amazon Bedrock

Streamline Location-Specific Policies with SharePoint and Amazon Bedrock

Global companies often face challenges in providing employees with location-specific policies. For instance, leave policies in the USA differ significantly from those in India. However, when documents are stored together in systems like SharePoint without proper filtering, employees may waste time searching or risk following incorrect policies. This issue also impacts knowledge bases like Amazon Bedrock, where unfiltered content leads to inaccurate answers.

The Solution: Metadata Filtering with SharePoint and Amazon Bedrock

By integrating Amazon Bedrock Knowledge Bases with SharePoint and leveraging metadata filtering, companies can create intelligent Retrieval-Augmented Generation (RAG) systems. These systems automatically retrieve relevant policy documents based on location filters, ensuring employees receive accurate, location-specific information.

How It Works (In Simple Terms)

  • Organize Documents in SharePoint: Assign metadata (e.g., country-specific tags) to each document.
  • Connect SharePoint to Amazon Bedrock: Sync SharePoint as a data source for Amazon Bedrock Knowledge Bases.
  • Apply Metadata Filters: Use filters to retrieve only location-relevant content when employees query the system.

Real-World Example: Leave Policies

Consider leave policies for the USA and India:

  • USA Policy: Based on ACME Corporation’s USA Employee Leave Policy, employees receive different types of leave: Vacation Leave (0-2 years of service: 10 days/80 hours), Sick Leave - 5 days (40 hours) per calendar year. Additionally, employees receive paid holidays (11 days), bereavement leave, and jury duty leave. Eligible employees may receive up to 12 weeks for parental leave.
  • India Policy: According to ACME Corporation India’s leave policy, you are entitled to the following types of leave: Privilege/Earned Leave: 24 days per year, Sick/Casual Leave: 12 days per calendar year. Optional Holidays: 2 days per year. The policy includes other types of leave such as Maternity Leave: 26 weeks.

Disclaimer: Please note that the leave policies uploaded to SharePoint and used in this demonstration were generated using AI. These AI-generated policies are intended for illustrative purposes only.

Using metadata filtering:

  • Employees in the USA see only the USA policy.
  • Employees in India see only the India policy.

This eliminates confusion and ensures compliance.

Implementation Steps

Add metadata to your SharePoint documents

First, ensure your documents have the right metadata in SharePoint:

  1. We will use the default Title column in your SharePoint document library
  2. Assign “Leave_Policy_USA” or “Leave_Policy_India” to the appropriate documents

aws-bedrock-sp-0

Set up a connection between SharePoint and Amazon Bedrock

Next, set up a connection between SharePoint and Amazon Bedrock:

  1. In AWS console, create a new Knowledge Base
  2. Select SharePoint as your data source
  3. Set up SharePoint App-Only authentication to connect to SharePoint
  4. Sync the data source to begin indexing content from SharePoint

aws-bedrock-sp-5

aws-bedrock-sp-10

aws-bedrock-sp-11

Note: I’m still exploring how custom metadata columns can be used for unstructured data formats. If I find a solution, I’ll create a separate blog post. For now, we’ll focus on using the out-of-the-box metadata fields generated by the OpenSearch collection.

Test metadata filtering using sample queries to ensure accuracy

Let us test a few questions both with and without filters to see how the selected model generates responses. This will help demonstrate the difference in relevance and accuracy when metadata filtering is used. For this example, I’ve used the Nova Pro 1.0 model to generate the responses.

No Filter

As you can see, the answers are a mix of both USA and India policies, with chunks being pulled from documents for both regions.

aws-bedrock-sp-6

With x-amz-bedrock-kb-title ^ Leave_Policy_USA Filter

With the filter x-amz-bedrock-kb-title ^ Leave_Policy_USA, the response is clearly specific to the USA, showing only the relevant policy for that region.

aws-bedrock-sp-7

With x-amz-bedrock-kb-title ^ Leave_Policy_India Filter

With the filter x-amz-bedrock-kb-title ^ Leave_Policy_India, the response is clearly specific to the India, showing only the relevant policy for that region.

aws-bedrock-sp-8

Benefits of Metadata Filtering

  • Accurate Information: Employees access policies specific to their region.
  • Time-Saving: Reduces time spent sifting through irrelevant documents.
  • Improved Compliance: Ensures employees follow the correct policies.
  • Centralized Management: All policies remain in one system for easy updates.

Conclusion

Combining SharePoint’s document management capabilities with Amazon Bedrock’s metadata filtering creates a powerful solution for global organizations. This approach simplifies policy management and ensures employees receive accurate, location-specific information without requiring complex coding or major system changes.

Published on:

Learn more
Home | Joseph Velliah
Home | Joseph Velliah

Fulfilling God’s purpose for my life

Share post:

Related posts

Report on partial license assignments via the Graph SDK for PowerShell

In this article, we explore a simple PowerShell script to report on "partial" license assignments in Microsoft 365, that is licenses for which...

11 hours ago

Lewis and Laura vs. Fabric Notebooks and Microsoft Graph: Part 1

This week my friend Laura GB told me about some fun she was having with Python in Fabric Notebooks, working to access Excel table data for pro...

1 day ago

Microsoft Teams Copilot without transcription becomes default for meetings – conversation history now persists

Microsoft Teams Copilot will default to running without transcription for new meetings starting mid-September 2025, with conversation history ...

1 day ago

SharePoint Pages: Sections with AI

Sections with AI in SharePoint Pages enables users to create rich page sections using natural language prompts powered by Copilot. Rolling out...

1 day ago

Viva Engage: Export event posts

Viva Engage event organizers can export posts from the past 28 days as a .csv file, including content, status, timestamps, upvotes, and reacti...

1 day ago

Microsoft Teams: New organizer controls for in-meeting management

Microsoft Teams introduces Organizer Controls in the meeting toolbar, consolidating management features into one menu for improved usability a...

1 day ago

Microsoft 365 Copilot Chat: New ways to include files and emails in prompts

Microsoft 365 Copilot Chat now lets users quickly include files and emails in prompts by typing ‘/’ to search and reference content, enhancing...

1 day ago

Microsoft 365 Copilot: New ways to include files and emails as part of prompts in chat web scope

Microsoft 365 Copilot Chat now lets users easily include files and emails in prompts by typing ‘/’ to search and reference content, enhancing ...

1 day ago

Copilot in Teams meetings: user-controlled on/off toggle

Microsoft Teams will soon let users toggle Copilot off during meetings, disabling recording, transcripts, and Facilitator while off. Rollout s...

1 day ago

Microsoft Copilot (Microsoft 365): Reference a Loop or Page when creating a presentation with Copilot

You can now reference a Loop or Page when you create a presentation with Copilot within the PowerPoint application. Product PowerPoint Release...

1 day ago
Stay up to date with latest Microsoft Dynamics 365 and Power Platform news!
* Yes, I agree to the privacy policy