Collections allow you to organize your data into logical groups. For example, you might have separate collections for "Product Documentation," "Engineering Design Docs," or "Community Support History."
In Katara, collections act as a bridge between your organization and your content:
Organization Scope: Every collection belongs to a specific Organization.
AI Context: When you configure an agent, you can specify which collections it should use as its source of truth.
Filtering: Collections help you filter your corpus so your agent doesn't get overwhelmed by irrelevant data.
Collections are often created and populated automatically by Loader Agents. When you set up a loader, it typically creates a collection to store the documents it imports.
Owner: The user who created the collection or the loader that manages it.
Editors: Users who can update the collection settings or refresh the data.
Viewers: Users who can see the collection metadata. Access to individual documents still depends on each document's own visibility, sharing, and sensitivity classification.
By default, Organization Admins and Owners have full control over all collections within the organization.
Last updated
