PDF ingestion is the ability of knowledge connectors to extract and sync PDF content from supported knowledge sources (Sharepoint, and when released, Google Drive). Content extracted from PDF files is synced with Knowledge and made availablewherever external content is used.

What's my plan?
All Suites Team, Growth, Professional, Enterprise, or Enterprise Plus
Support with Knowledge Professional or Enterprise

Summary: ◀▼

PDF ingestion lets you automatically extract and sync text from PDFs in supported knowledge sources like SharePoint, making content available for AI agents and generative search. It updates during regular syncs, supports up to 100 PDFs per account, and excludes encrypted files and images. To use it, connect a supported knowledge source and enable external content access for AI and search features.

Important: PDF Ingestion is currently in an early access program (EAP). To participate, see Enrolling in the EAP.

PDF ingestion is the ability of knowledge connectors to extract and sync PDF content from supported knowledge sources (Sharepoint, and when released, Google Drive). Content extracted from PDF files is synced with Knowledge and made available wherever external content is used.

You must be a Knowledge admin to create and manage knowledge connections.

This article contains the following topics:
  • About PDF Ingestion
  • Requirements and limitations
  • Enrolling in the EAP
  • Setting up PDF ingestion

About PDF Ingestion

When you register for this EAP, you can unlock the information in your PDF documents hosted on supported knowledge connector platforms. Content that lives in PDF files no longer needs to be manually converted or migrated. Instead, it's automatically extracted, synced, and made available for AI agents and generative search.

PDF extraction offers the following capabilities:
  • PDF ingestion from supported knowledge connectors: You can connect your existing knowledge sources to automatically ingest PDF content into your Zendesk account.
  • Automatic knowledge syncing: PDF content is updated during connector syncs, which typically runs every 24 hours.
  • PDF extraction: Text is extracted from connected PDFs, then made available for AI Agents and generative search. Equipping AI agents and generative search with PDF content helps them to provide better answers for users seeking information.

Requirements and limitations

Supported platforms include SharePoint and the upcoming Google Drive connectors. Additional platforms will be added as they become available.

To participate in this EAP, you must be a Knowledge admin and have the following:

  • Access to the PDF Ingestion EAP
  • Connected knowledge source (currently a SharePoint knowledge connector)
  • AI agents or generative search configured to access ingested content.
The following limitations apply to the PDF ingestion EAP. PDFs that don't meet this criteria are automatically and silently (no UI indication) skipped during ingestion.
  • Maximum PDF file size of 10 MB
  • Maximum of 100 PDFs per account
  • Encrypted PDFs are not supported
  • Images within PDFs are not extracted; only text extraction is supported.

Enrolling in the EAP

You can enroll in the PDF Ingestion EAP from within Knowledge admin. After you submit the EAP agreement and update your settings, you'll have automatic access to the PDF ingestion functionality.

If you have feedback about this feature during the course of the EAP, visit the dedicated community forum for PDF ingestion where we collect and manage customer product feedback.

To enroll in the PDF Ingestion EAP
  1. In Knowledge admin, click Settings () in the sidebar.
  2. Under the External content (Early Access Program) section, select Allow PDF content.

  3. Review the EAP terms and conditions, then select I agree and click Submit.
  4. On the Settings page, click Update.

Setting up PDF ingestion

Once you've signed up for the PDF ingestion EAP, the feature is automatically available to you. However, you must connect a supported external knowledge source and configure your account to allow the use of external content.

To set up PDF ingestion for use with knowledge connectors
  1. Set up one of the supported knowledge connectors:
    • SharePoint knowledge connector

    After you connect your source, PDFs synced from that source are automatically ingested into Zendesk Knowledge.

  2. Configure your AI agents or generative search to use the connected external content. See About connecting external content to Zendesk for use across knowledge experiences.
Powered by Zendesk