Knowledge Management: Connecting to an External Knowledge Source

Talkdesk Knowledge Management™ allows users to create and organize content, and also to connect with external knowledge sources that may already be in use in the contact center.

All content connected to Talkdesk via Knowledge Management is searchable and will be automatically available for other apps such as Copilot (to learn more about Copilot, please check this article).

Once Knowledge Management has been installed, you can connect knowledge bases from the following sources:

 

Creating a Knowledge Base

To create a new Knowledge Base, please follow these steps:

image14.png

1. Click on My Apps and select Knowledge Management [1].

 

KM_new_1.png

2. Click on External sources [2].

3. Select Connect new source [3].

 

KM_new_4.png

4. Select the Knowledge Source type you want to connect with Talkdesk [4].

5. Fill out the form according to the instructions provided for each type, and press Continue when you’re done [5].

 

Status and Knowledge Base Details

The “Status” and “Knowledge Base Details” settings are available for configuration in all knowledge base types.

image10.png

  1. In "Status” [1], use the toggle to activate/deactivate the knowledge base. If it is set to "Active" (green), the knowledge base will be indexed at the specified time intervals,+. Otherwise, the knowledge base will not be indexed or searchable.
  2. The “Knowledge Base Details” section is composed of the “Name” and “Description” fields. These provide an easy way to identify each created knowledge base and understand its purpose:
    • Name [2]: Enter a unique name to identify the knowledge base (1-64 characters, non-blank).
    • Description [3]: Add a description detailing the purpose of the knowledge base (1-160 characters, non-blank).
    • “Ring Group(s) [4]: To restrict the content in your knowledge base to agents in one or more ring groups, please type them below by clicking on the Add Ring Group link. Note: In case you do not add a Ring Group, the content will be accessible to all agents.
    • “Language” [5]: Here you can choose the language of the knowledge base content.

 

Connection Settings

The “Connection Settings” section provides the required data to connect (and authenticate, if needed) to a knowledge base. This section’s fields vary according to the type of knowledge base being created. The following subsections contain information on the “Connection Settings” of each knowledge base type.

 

Confluence

The “Connection Settings” for Confluence consist of four mandatory fields:

image3.png

  1. “Confluence base URL” [1]: Add the Atlassian domain that your company is using (e.g., https://mycompanyinc.atlassian.net/).
  2. “Confluence space(s)” [2]: Add a list of Confluence spaces with knowledge base articles to be extracted:
  • The space names must only consist of alphanumeric characters (1–255 characters).
  • Minimum of 1 space and maximum of 10 spaces.
  1. “Username” [3]: Add the email address of the Confluence user account that will be used to extract the knowledge base articles (1–255 characters).
  2. “API token” [4]: Add the API token of the Confluence account. It must include only alphanumeric characters (1–255 characters).

 

Remote File

The Remote File option allows you to connect to a web-based ZIP file:

image12.png

 

  1. “URL” [1]: Add the URL where a zip file with the articles is stored (e.g., https://mycompanyinc.drive.com).

Please visit the Remote File Configuration article for detailed information on how to configure this setting.

 

Salesforce

Salesforce’s “Connection Settings” consist of seven mandatory fields. For more information on how to get the required data in Salesforce, please read the article Knowledge Management: Salesforce Connection Settings.

image8.png

  1. “URL” [1]: Add the URL of the Salesforce account where the knowledge base articles are located (e.g., https://mycompanyinc.my.salesforce.com).
  2. “Username” [2]: Enter the email address of the user associated with the account added in the previous field (1–255 characters).
  3. “Security token” [3]: Enter the user password from Salesforce, with the Salesforce security token appended at the end:
  • Characters may be alphanumeric, blank spaces, or one of these special characters: ! " # $ % & ' ( ) * + , - . / : ; < = > ? @ [ \ ] ^ _ ` { | } ~
  • 24 to 255 characters allowed.
  1. “Login URL” [4]: Enter the login URL for the type of Salesforce instance (e.g., test.salesforce.com or login.salesforce.com).
  2. “Grant Type” [5]: Add the grant type that is used as the authentication method (e.g., password).
  • Use only alphanumeric characters, “-“, “:“, or “_“.
  • 8 to 44 characters allowed.
  1. “Client ID” [6]: Enter the ID of the Copilot Connected App:
  • Use only alphanumeric characters, “.” or “_”
  • 8 to 256 characters allowed.
  1. “Client secret” [7]: Enter the secret of the Copilot Connected App.
  • Use only alphanumeric characters.
  • 8 to 256 characters allowed.

 

Zendesk Guide

The Zendesk Guide’s “Connection Settings” will extract articles from Zendesk Guide. The Connection Settings contain three mandatory fields.

new_1.png

  1. “URL” [1]: Add the URL of the Zendesk account where the knowledge base articles or tickets are located (e.g., https://mycompanyinc.zendesk.com).
  2. “Username” [2]: Enter the email address of a user authorized to access the articles/tickets in the Zendesk account previously indicated (1-255 characters).
  3. “API token” [3]: Enter the API token or user password of the Zendesk account that has been previously indicated (6-255 characters).

 

C2Perform

The C2Perform “Connection Settings” is composed of two mandatory fields:

image4.png

  1. “URL” [1]: Enter the URL of the current version of C2Perform API (e.g., https://app.c2perform.com/api/mykb_pages_all_v1.php).
  2. “Account authorization key” [2]: Enter the authorization key from C2Perform.

 

Oracle Service Cloud

The Oracle Service Cloud “Connection Settings” is composed of three mandatory fields and one optional field:

image11.png

  1. “URL” [1]: Enter your REST Server URL (e.g., https://help.<company>.com).
  2. “Username” [2]: Add the username of the account used to access the Oracle SvC Answers API (1-255 characters).
  3. “Password” [3]: Enter the password of the account used to access the Oracle SvC Answers API (1-20 characters).
  4. “SQL Query” (optional field) [4]: If you wish, you can enter a SQL query to filter Answers and exclude them from indexation by Copilot (1-255 characters):
  • e.g., to filter out answers that are not in a “Public” state: statusWithType.statusType.lookupName = 'Public'.

 

Intercom

The “Connection Settings” for Intercom consists of two mandatory fields:

image4.png

  1. “URL” [1]: Enter the API endpoint (e.g., https://api.intercom.io). 
  2. “Account authorization key” [2]: Enter the authorization key from an Intercom account.

 

ServiceNow

The ServiceNow connector only supports integration with the ServiceNow KB Standard object. As a pre-requisite for this connector to work, a ServiceNow engineer or Admin needs to install in the ServiceNow account the Knowledge API Plug-in. This plug-in is not installed by default in an out-of-the-box ServiceNow account. Please refer to the vendor article on "Knowledge Article Templates" for more details.

The ServiceNow “Connection Settings” is composed of three mandatory fields:

image13.png

  1. “ServiceNow base URL” [1]: Enter your company account domain (e.g., <company-name>.service-now.com).
  2. “Username” [2]: Add a ServiceNow user account (1-255 characters).
  3. “Password” [3]: Enter the password of the ServiceNow account (1-20 characters).

 

Google Drive

Before connecting Knowledge Management to your documents (Google Slides, Google docs, among others) in Google Drive, you must first use a Google admin to get the setup right.

Please reach out to your IT Admin responsible for the Google Drive/Workspace setup and request a service account creation. This service account must have read-only permission for the user and shared drives where your content is stored. 

The account needs the following permissions:

  • https://www.googleapis.com/auth/drive.readonly.
  • https://www.googleapis.com/auth/drive.metadata.readonly.
  • https://www.googleapis.com/auth/admin.directory.user.readonly.
  • https://www.googleapis.com/auth/admin.directory.group.readonly.

The Google Drive “Connection Settings” is composed of three mandatory fields:

image_googledrive.png

  1. “Admin account” [1]: Insert your admin e-mail address.
  2. “Client account” [2]: Enter your client’s e-mail account.
  3. “Private key” [3]: Refers to your Google Drive password

Note: This connector is only available in the U.S. region.

 

MS Sharepoint

Microsoft (MS) Sharepoint can be used as a data source for Talkdesk Knowledge Management. 

To begin using do so, you must first reach out to your IT Admin responsible for the MS Sharepoint/Azure, and check the following:

  • Basic authentication credentials containing the user name and password with site admin permissions to connect to SharePoint Online.
  • Deactivated Security Defaults in your Azure portal using an administrative user. Note: For more information on managing security default settings in the Azure portal, see Microsoft documentation on how to enable/disable security defaults.
  • Deactivated multi-factor authentication (MFA) in your SharePoint account, so that Talkdesk is not blocked from crawling your SharePoint content.

To complete the process, use an admin’s username and password.

 

MS Sharepoint Connection Settings

The MS Sharepoint “Connection Settings” is composed of three mandatory fields:

image_mssharepoint.png

  • “URL” [1]: The format for the host URL you enter is https://yourdomain.sharepoint.com/sites/mysite. Your URL must start with https and contain sharepoint.com.
  • “Username” [2]: Enter a Sharepoint that belongs to a user account. Please use a Sharepoint access scope logic to narrow down to specific folders, directories, or other sensitive content that is present in the main Sharepoint location.
  • “Password” [3]: Insert your password.

 

MS Sharepoint Supported File Types

These are the supported file types for the MS Sharepoint connector.

Document format Treated as How document is treated Original structure
Portable Document Format (PDF) HTML Converted to HTML, then content is extracted. Unstructured
HyperText Markup Language (HTML) HTML HTML tags are filtered out to extract content. Content must between the main HTML start and closing tags (<HTML>content</HTML>). Semi-structured
Extensible Markup Language (XML) XML XML tags are filtered out to extract content. Semi-structured
Extensible Stylesheet Language Transformation (XSLT) XSLT Tags are filtered out to extract content. Semi-structured
MarkDown (MD) Plain text Content is extracted with MarkDown syntax included. Semi-structured
Comma Separated Values (CSV) CSV Content extracted from each cell, with a single file treated as a single document result. Structured for FAQ files, otherwise semi-structured
Microsoft Excel (XLS and XLSX) XLS and XLSX Content extracted from each cell, with a single file treated as a single document result. Semi-structured
JavaScript Object Notation (JSON) Plain text Content is extracted with JSON syntax included. Semi-structured
Rich Text Format (RTF) RTF RTF syntax is filtered out to extract content. Semi-structured
Microsoft PowerPoint (PPT) PPT Only text content is extracted from PowerPoint slides for search. Images and other content are not extracted. Unstructured
Microsoft Word (DOCX) DOCX Only text content is extracted from Word pages for search. Images and other content are not extracted. Unstructured
Plain text (TXT) TXT All text in the text document is extracted. Unstructured

 

Additional MS Sharepoint Information

  • Within Talkdesk, you can create repeated connectors to MS Sharepoint (e.g. map different portions of your Sharepoint with different permission level for access to different users)
  • The connector supports custom field mappings only for the “Files” entity.
  • The connector does not support change log mode, as well as new or modified content sync for SharePoint 2013.
  • If an entity name has the % character in its name, the connector will skip these files due to API limitations.
  • OneNote can only be crawled by the connector using a Tenant ID. As well as with OAuth 2.0, OAuth 2.0 refresh token, or SharePoint App Only authentication activated for SharePoint Online.
  • The connector crawls the first section of a OneNote document using its default name only, even if the document is renamed.
  • The connector crawls links in SharePoint 2019, SharePoint Online, and Subscription Edition, only if “Pages” and “Files” are selected as entities to be crawled in addition to Links.
  • The connector crawls links in SharePoint 2013 and SharePoint 2016 if “Links” is selected as an entity to be crawled.
  • The connector crawls list attachments and comments only when “List Data” is also selected as an entity to be crawled.
  • The connector crawls event attachments only when “Events” is also selected as an entity to be crawled.
  • For SharePoint Online version, the ACL token will be in lower case. For example, if the user’s principal name in the Azure portal is MaryMajor@domain.com, the ACL token in the SharePoint Connector will be marymajor@domain.com.
  • In Identity Crawler for SharePoint Online and Server, if you want to crawl nested groups, you have to activate Local as well as AD Group Crawling.
  • If you're using SharePoint Online, and the User Principal Name in your Azure Portal is a combination of uppercase and lowercase, the SharePoint API internally converts it to lowercase. Because of this, the Talkdesk SharePoint connector sets ACL in lowercase.

 

Web Crawler

Web Crawler allows websites or other pages to be crawled, and their content indexed to be used as Knowledge across the Talkdesk platform. 

When you use the web crawler to retrieve webpages and index them as your documents, you specify the websites you want. For that, provide the respective URLs. You can only crawl websites that use the secure communication protocol: Hypertext Transfer Protocol Secure (HTTPS). If you receive an error when crawling a website, it could be that the website is blocked from that action.

If a website requires basic authentication, please provide the username and password.

The Web Crawler “Connection Settings” is composed of two options and one mandatory field:

image_webcrawler.png

  1. “Username” [1]: Your user’s account.
  2. “Password” [2]: Refers to your password.
  3. “URL(s)” [3]: Provide the seed or sitemap URLs of the website or websites you want to index.

Note: This connector is only available in the U.S. region.

 

Refresh Settings

For all sources, the “Refresh Settings” define when and how frequently the knowledge base should be re-indexed so that the information is up-to-date.

image15.png

  1. “Initial time” [1]: Select the date (including hours and minutes) of the first time the knowledge base should be re-indexed.
  2. “Period” [2]: Select how frequently the data should be re-indexed.

 

Updating a Knowledge Base

To update an existing Knowledge Base, please follow these steps:

KM_new_2.png

  1. Go to the External Sources page, locate the knowledge base you wish to edit, and click on the settings icon [1].
  2. Change the data as you see fit. The fields need to be filled according to the instructions above for each source.
  3. When you’re done, hit the Save button.

 

Deleting a Knowledge source

To delete an existing Knowledge source, please follow these instructions:

KM_new_3.png

  1. Go to the External sources page, locate the knowledge source you wish to delete, click on the settings icon [1] and choose Delete.
  2. To confirm the deletion, simply select Delete Knowledge source [2] in the pop-up window.
All Articles ""
Please sign in to submit a request.