External Contents

As a Dydu bot manager, you have the ability to centralize and organize your external content sources directly from an intuitive interface in the BMS, allowing you to generate instant responses based on these sources and thereby improve the quality of responses provided to end users. Through the BMS navigation menu, you can access the External Content page: Content > External Content.

You will arrive on the RAG Edition page, where you can create a new collection.

By clicking on the "Your Collections" modal, you need to choose the name of the collection you want to create, and then click on "Create."

A page for your collection is displayed as shown below:

On this page, you have the ability to:

Import files:

It is possible to import multiple documents of the following types: PDF, DOCX, PPTX, TXT.

Register Sharepoints:

• The Dydu SharePoint reader enables the indexing of pages and files.

• Please refer to this documentation.

You need to register a new application in your tenant that has read permissions. The tutorial below explains the process: https://learn.microsoft.com/en-us/azure/healthcare-apis/register-application When you reach the "API permissions" step, the two necessary permissions are:

• Microsoft Graph -> Application Permissions -> Files.ReadAll (Grant Admin Consent)

• Microsoft Graph -> Application Permissions -> BrowserSiteLists.Read.All (Grant Admin Consent)*

• Set the permissions Files.ReadAll and BrowserSiteLists.Read.All for the Dydu application.

• The required elements for the configuration are:

a. clientId

b. client Secret (the value)

c. tenant Id

d. SharePoint site ID

Details of the necessary steps on how to retrieve the required values from Azure for the Dydu LLM configuration:

Go to the Azure portal:

1. Click on App registrations

1. Click on New registration

1. Give a name and click on "Register"

1. The application ID is the client_id

1. Click on Certificates & secrets. Then, in the "Client secrets" tab, click on New client secret.

1. Click on Certificates & secrets

1. Copy the generated secret value (client_secret)

1. Click on API permissions. Then click on Add a permission.

1. Click on Microsoft Graph

1. Then click on "Application permissions". Then add the Sites.Selected and Files.Read.All permissions.

1. Click on Grant admin consent for XXXX

1. To find the tenant ID:

Go to the website: https://entra.microsoft.com/

Click on "Overview":

The client ID corresponds to the tenant ID.

1. To find the SharePoint ID:

Compose the following URL: https://<tenant>.sharepoint.com/sites/<site-url>/_api/site/id

The SharePoint ID can be found in the result

<d:Id
  xmlns:d="http://schemas.microsoft.com/ado/2007/08/dataservices"  
  xmlns:m="http://schemas.microsoft.com/ado/2007/08/dataservices/metadata"  
  xmlns:georss="http://www.georss.org/georss"
  xmlns:gml="http://www.opengis.net/gml"  
  m:type="Edm.Guid">
67a90b63-3384-495d-9456-66141cf4ac28
</d:Id>

• Features:

1. Indexing pages and/or files from an entire SharePoint site:

• Standard RAG

• Displaying the original SharePoint URL in the result provided by the RAG

1. Possible integration with SAML authentication:

• A user must be authenticated via SAML

• We retrieve their group memberships

• Document permission filtering is possible: access to a subset depending on the access rights.

Not indexed:

• "Embedded" files in pages

• Videos, and some other types (Excel, WMF, ...)

Currently, the process of retrieving documents and indexing takes time (several minutes), and the most frequent refresh is once a day.

Register Smart Tribune

To configure a Smart Tribune source, the following informations are required :

• Name: URL of the Smart Tribune API to use

• API Key

• API Secret

• Knowledge base ID list : refers to the IDs of the knowledge bases to retrieve (the same API key / API secret combination can grant access to multiple knowledge bases.)

Using these informations, all documents contained in the specified knowledge bases are retrieved, regardless of their original channel (FAQ).

Register Websites:

Type of Websites:

• Domain

• Sitemap

• Specific URLs

The informations about adding your source to your collection are displayed as follows:

• Name: the name of your source that you added

• Added by: the bot manager's identifier

• Created at: the date when you added your source

• Status: the status of your source

There are three states for the status:

1. "Waiting for action": status when no action has been taken.

2. "Completed": status when the operation (indexation or suggestion) is successful.

3. "Completed with errors": status when the operation (indexation or suggestion) was completed, but there are errors.

4. "Processing": status when the operation is ongoing.

• Action: the actions you can perform on your added source > delete, edit.

Suggestion and Indexation :

• Suggest knowledge from the collection

• Indexation: index the content of the collection