Skip to main content
Ravenna transforms your existing knowledge base content into AI-powered answers delivered directly in Slack. Connect your documentation, wikis, and internal resources to help your team get instant, accurate responses.
Introduction

​
Creating a knowledge folder

Knowledge folders organize your imported content and control how it’s used by Ravenna AI, as you can scope it to certain queues only.
1

Navigate to Knowledge

Click the Knowledge tab in the left navigation.
Introduction
2

Create a folder

Click the Create button to add a new knowledge folder.
3

Configure folder settings

Set your folder name.

​
Adding documents

1

Open your folder

Navigate to within a knowledge folder. Documents can omly exisit witin a parent folder.
2

Add documents

Click Add Documents in the top right corner.
3

Select your source

Choose your knowledge source and complete the authentication flow to grant Ravenna access.
Introduction

​
Knowledge sources

Ravenna supports multiple knowledge sources to help you centralize your organization’s information:

Slack

Import messages and threads from your Slack channels.

Notion

Sync your Notion pages and databases.

Google Drive

Import documents from Google Drive.

Confluence

Sync your Confluence spaces and pages.

Coda

Import your Coda documents and pages.

Website

Import content from public websites.

​
Searching your knowledge

Ravenna uses a hybrid search approach combining semantic understanding with keyword matching to find the most relevant content.
Ravenna employs two complementary search methods:
  • Semantic search: Uses AI embeddings to understand the meaning and context of queries, finding conceptually similar content even when exact keywords don’t match
  • BM25 keyword search: Traditional text-based search that excels at finding exact matches and specific terminology
  • Hybrid ranking: Results from both methods are combined and ranked to surface the most relevant documents
This dual approach ensures Ravenna can answer both conceptual questions and specific keyword-based queries effectively.
Once your content is imported, test how Ravenna AI responds using the Chat Panel:
1

Open the chat panel

Click Chat in the top right of the KB Documents screen.
2

Ask questions

Ask Ravenna anything related to the content you’ve imported to see how it responds.
Introduction
Use the chat panel to validate that your knowledge base is working as expected. You can put your current knowledge to the test and see how Ravenna responds, and then go and make changes to your source documents as needed, until you’re happy with the results.

​
Managing documents

Reorganize your knowledge base by moving documents between folders:
  • Single document: Select a document and choose Move from the actions menu
  • Bulk move: Select multiple documents and move them all at once to a target folder
  • Preserved metadata: Document content, sync status, and metadata remain intact when moved
  • Updated references: AI responses automatically use the new folder location after moving
Moving documents doesn’t affect their availability to AI - they remain searchable and usable in responses.
Ravenna preserves the organizational structure from your source systems:
  • Preserved organization: Original folder and page structures from services like Notion or Confluence are maintained in Ravenna
  • Easy navigation: Navigate the knowledge base using the familiar structure from your source system
  • Automatic updates: When documents are moved or reorganized in the source service, the hierarchy updates during the next sync
This mirroring approach ensures your knowledge base in Ravenna feels familiar and maintains the organizational logic you’ve already established.

​
Syncing and monitoring

Ravenna defaults to automatically sync your knowledge daily to keep content up-to-date.
1

Open folder details

Navigate to your knowledge folder and view the Details panel on the right.
2

Adjust auto-sync

Toggle auto-sync on or off in the Auto-sync section.
Introduction
The sync does not run at the same time everyday, it is randomized, however it will run once in every 24 hour period
Trigger a manual sync anytime to immediately update your knowledge base with the latest content from your source. Simply click the Sync button in the top right of your knowledge folder.
Monitor the status of your knowledge folder syncs in real-time:
  • Sync state badge: View the current sync status in the folder’s Details panel
    • Done: Sync completed successfully
    • In Progress: Sync is currently running
    • Queued: Sync is scheduled to run
    • Errored: Sync encountered an error
  • Progress indicator: Track sync completion percentage for large imports
  • Last sync timestamp: See when the folder was last successfully synced
  • Documents synced count: View how many documents have been imported
Sync progress updates automatically - no need to refresh the page to see the latest status.
When a sync fails, Ravenna provides detailed error information to help you resolve issues:
  • Error messages: View specific error details in the folder’s Details panel under “Sync state”
  • Common errors:
    • Authentication expired: Reconnect your integration to restore access
    • Source unavailable: The source content or service is temporarily inaccessible
    • Permission denied: Ravenna no longer has access to the content
    • Content not found: The source document or page has been deleted or is inaccessible
  • Automatic retry: Failed syncs are automatically retried during the next scheduled sync
  • Manual retry: Click the Sync button to immediately retry a failed sync
  • Document preservation: If a document disappears from the source, Ravenna marks it with an error but doesn’t delete it from your knowledge base to protect content your bot depends on
If a sync error persists, check your integration connection and ensure Ravenna still has the necessary permissions to access your content.

​
Archiving documents

Archive documents and folders to exclude them from AI responses while keeping them in your knowledge base for reference.
  • Selective exclusion: Archive specific documents or entire folders to prevent them from being used in AI responses
  • Preserved structure: Archived content remains in your knowledge base for reference but won’t influence AI answers
  • Cascade archiving: When you archive a parent folder, all child documents and subfolders are automatically archived
  • Smart sync behavior: During auto-sync, new documents added to archived folders in your source system are automatically archived in Ravenna
  • Easy recovery: Unarchive content anytime to make it available to the AI again
Archiving is useful for:
  • Outdated documentation that’s no longer relevant
  • Deprecated processes or procedures
  • Sensitive information that should be retained but not actively used by AI
  • Historical content that needs to be preserved for compliance

​
Queue scoping

Control which Slack channels can access specific knowledge folders.
Queue scoping is useful when different teams need access to different knowledge bases, or when you want to provide specialized knowledge for specific support channels.
  • Global access (default)
  • Queue-specific access
By default, knowledge folders are accessible to answer questions from any channel where Ravenna AI is present.
⌘I