Pragence

Help centres, sites and trackers

Fourteen connector types read content over each vendor's REST API. They are for content meant for everyone who uses the assistant: published help articles, public site pages, one course's pages, one repository's issues.

These sources follow each vendor's published API and are tested against a local server that returns the vendor's response shape. They have not yet been verified against live vendor accounts. Run a first sync on a small scope and check the run before relying on one.

Read this first

  • Whole workspace, no per-person sharing. A source indexes whatever its credentials can read and makes it available to everyone who can use the project. It does not mirror who can see what at the vendor. Give it credentials that can read only what everyone may see.
  • Content the vendor limits is left out. Where a vendor marks an article as limited to signed-in users, agents or a segment, the knowledge base sources leave it out and report it on the run as restricted_at_source. Zendesk and GitBook have an admin opt-in to include it.
  • Every sync lists the whole source. Unchanged documents are skipped, and a document that is no longer listed is deleted from the index.
  • A refused sign-in fails the run with source_refused; an unreachable source fails it with source_unreachable.
  • A record with an unexpected shape is reported on the run as invalid_document and left out. An empty record is left out.
  • They are created like any other connector: see Connect a source. Field names below are the keys of credentials and settings.

What each one needs and indexes

Zendesk help centre: zendesk_help_center

Credentialsemail (an agent's email), api_token
Settingssubdomain (the part before .zendesk.com), include_restricted_articles (default false)
IndexesHelp centre articles. Drafts are left out. Articles limited to agents or a user segment are left out and reported as restricted_at_source unless include_restricted_articles is on, which makes them available to everyone who can search the collection, including a public widget

Freshdesk solution articles: freshdesk_articles

Credentialsapi_key
Settingsdomain (the part before .freshdesk.com)
IndexesPublished articles (status 2) in folders visible to all users. An article in a folder, or under a parent folder, limited to signed-in users, agents, companies, bots or segments is left out and reported. Drafts are left out

Answers link to https://<domain>.freshdesk.com/support/solutions/articles/<id>.

Zoho Desk knowledge base: zoho_desk_articles

Credentialsclient_id, client_secret, refresh_token from a Self Client in the Zoho API console, with the Desk.articles.READ scope
Settingsorg_id, data_centre (com by default; also eu, in, com.au, jp, ca, sa, com.cn)
IndexesPublished articles whose permission is everyone (ALL). Articles for registered users or agents are never read

Zoho access tokens last an hour, so every sync exchanges the refresh token for a new one. Each sync lists every article (three API credits per 50) and reads only the bodies changed since the last sync (one credit each).

Help Scout Docs: helpscout_docs

Credentialsapi_key (a Docs API key)
SettingsNone
IndexesPublished articles in public collections. Private collections are never read

Document360: document360

Credentialsapi_token
Settingsproject_version_id (empty reads every public knowledge base workspace), language (default en), site_url (used for links when Document360 returns only a path), api_host (only for the US data centre, https://apihub.us.document360.io, or private hosting)
IndexesThe published version of each article. Hidden articles and articles limited to signed-in readers are left out and reported; drafts are never read

GitBook: gitbook

Credentialsaccess_token (a personal access token)
Settingsspace_id, include_non_public_space (default false)
IndexesEvery document page of one space, as Markdown. Links and generated pages are left out

A space that is not public (private, unlisted, share link, visitor authentication) is left out and reported, and pages indexed while it was public are removed, unless include_non_public_space is on. Only pages edited since the last sync are read again.

Intercom articles: intercom_articles

Credentialsaccess_token
SettingsNone
IndexesArticles whose state is published

ServiceNow knowledge: servicenow_knowledge

Credentialsusername, password
Settingsinstance_url, for example https://acme.service-now.com
IndexesKnowledge base articles that are published and active

Airtable: airtable

Credentialsaccess_token (a personal access token)
Settingsbase_id, table (name or ID), optional title_field
IndexesEach record of one table as a document, written as field: value lines. Records with no values are left out

GitHub issues: github_issues

Credentialsaccess_token
Settingsrepository (owner/name), optional state (open, closed or all; default all), optional include_pull_requests (default false)
IndexesThe issues of one repository: title, state, labels and body. Issue comments are not indexed

GitLab issues: gitlab_issues

Credentialsaccess_token
Settingsproject (path or ID), optional instance_url (default https://gitlab.com)
IndexesThe issues of one project: title, state, labels and description. Confidential issues are left out. Comments are not indexed

Canvas course pages: canvas_pages

Credentialsaccess_token
Settingsinstance_url, for example https://canvas.university.edu; course_id
IndexesThe published pages of one course. Assignments, files and discussions are not indexed

WordPress: wordpress

CredentialsNone for a public site. username and application_password only when the site's content API needs sign-in
Settingssite_url; optional content_types (default pages and posts)
IndexesPublished pages and posts, through the site's /wp-json/wp/v2/ API

Ghost: ghost

Credentialscontent_api_key
Settingssite_url
IndexesPublic posts and pages. Members-only content is left out

Example

{
  "connector_type": "zendesk_help_center",
  "name": "Help centre",
  "collection_id": "<collection-id>",
  "schedule": "0 3 * * *",
  "credentials": {"email": "agent@example.com", "api_token": "<token>"},
  "settings": {"subdomain": "acme"}
}

Use POST /api/v1/connectors/test with the same connector_type, credentials and settings to check the sign-in before creating it.

Not covered

Tickets, Slack messages, CRM records and GitHub pull requests are covered by Workplace tools. Airtable attachments and anything that needs per-person permissions are outside these sources. If you need a source that is not here, see Custom connector.

On this page