Confluence Data Ingestion

Turn your Confluence wiki into AI knowledge. Import documentation, runbooks, and internal guides so your Guru can answer questions based on your team’s actual knowledge base.

Why Ingest Confluence Data?

Internal Documentation

Import runbooks, onboarding guides, and process docs

CQL-Powered Selection

Use Confluence Query Language to import specific spaces or pages

Attachments Included

Images and files attached to pages are indexed too

Auto-Sync

Backfill jobs automatically import updated pages on a schedule

What Gets Indexed

Content Type	What’s Included
Pages	Full page content including tables, code blocks, and formatting
Comments	Page comments with context
Attachments	Images, PDFs, and text files
Metadata	Space, labels, author, and last modified date

Self-hosted: This integration is in beta for selected users. Cloud: Available to all users.

Setup

Create Atlassian API Token

Go to Atlassian API Token settings
Click Create API token
Copy the token

Navigate to Confluence Integration

Go to Gurubase Dashboard → Select your Guru → Integrations → Ingestions → Confluence

Connect Your Confluence

Fill in the connection details:

Field	Value
Domain	Your Atlassian domain (e.g., `yourcompany.atlassian.net`)
User Email	Your Atlassian account email
API Token	The token you created in Step 1

Adding Confluence Content

After connecting, you can import pages in two ways:

Option 1: Add Individual Pages

Best for importing specific pages by URL.

Setting	Description
URLs	Enter page URLs, one per line
Date Range	Optionally filter by last modified date
CQL Filter	Additional CQL criteria to refine selection

Option 2: Create Backfill Job

Best for bulk imports and automatic ongoing sync using CQL queries.

Setting	Description
CQL Query	Query to select which pages to import
Sync Interval	How often to check for updated pages (minimum 1 hour)
Sync Now	Manually trigger an immediate sync

Example CQL Queries

-- All pages from a specific space
space = "DOCS" AND type = "page"

-- Recently updated documentation
space = "ENGINEERING" AND lastModified >= now("-30d")

-- Pages with specific labels
label = "runbook" OR label = "onboarding"

-- Search by title
title ~ "API" AND space = "DEVELOPER"

Use backfill jobs to keep your Guru automatically updated whenever your team updates Confluence documentation.

Viewing Indexed Content

Imported pages appear as individual sources in your Guru’s data sources list. You can:

View the exact content that was indexed
Remove specific pages
Check when content was last synced

Next Steps

Jira Ingestion

Import Jira issues as knowledge sources

Zendesk Ingestion

Import Zendesk tickets and articles

Slack Bot

Deploy Gurubase in Slack

Data Sources

Add more knowledge sources

Jira Data Ingestion Slack Data Ingestion

Get Started

Guides

Integrations

Advanced