Brains

The Brains page (route /datasets) lists all datasets in your workspace. Each dataset — labeled “brain” in the UI — is a container for documents and all subsequent operations. See Datasets for the underlying concept; the API, SDK, and route names continue to use “dataset”.

​

Dataset list

Each row shows:

• Name — The dataset identifier.
• Documents — Number of files in the dataset.
• Status — Ready (has documents) or Empty.
• Graph Model — The graph model bound to the dataset, when one is configured.
• Created — Creation timestamp.

Use the search bar to filter datasets by name. Click any column header (Name, Documents, Status, Graph Model, Created) to sort by that column; click again to toggle ascending/descending. The active sort column is highlighted with an arrow indicator.

​

Create a brain

Click New brain, enter a name, and confirm. The brain (dataset) is created immediately and appears in the list. Newly created datasets are automatically granted tenant-level read and write permissions, so every member of the current tenant can see and write to them. To restrict a dataset to specific users, revoke the tenant grant and assign per-user permissions through the permissions API.

​

Upload documents

1. Select a dataset from the list (or create one).
2. On the dataset detail page, drag files into the upload area or click to browse.
3. Supported formats: PDF, CSV, TXT, Markdown, JSON, DOCX.

After upload, the add and cognify pipeline runs in the background. The header shows Processing… while the knowledge graph is being built. When processing finishes, the header updates to show a Last synced timestamp.

​

Sync a dataset

For datasets connected to an external source, the dataset detail page includes a Sync button that re-runs the cognify pipeline against the current dataset contents. Use this to rebuild the knowledge graph after source data changes without uploading new files again. While syncing, the button shows a spinning icon and the label Syncing…. The Last synced timestamp updates when the sync completes.

​

Dataset breadcrumb

The breadcrumb at the top of the UI follows the structure Workspace / Dataset / Page. The dataset selector appears only on pages where filtering by dataset is relevant: the Dashboard, Search, Knowledge Graph, and dataset detail pages. On other pages the breadcrumb shows only the workspace and current page name. Selecting a dataset in the breadcrumb is global — it filters content across all applicable pages:

• The Search page queries only that dataset.
• The Knowledge Graph page visualizes only that dataset’s graph.
• The Dashboard scopes metrics and search to that dataset.

To search or visualize across all datasets, set the breadcrumb back to All datasets. On a dataset detail page the breadcrumb shows Workspace / [Dataset] / Documents.

​

Delete a brain

Open the context menu on a brain row and select Delete brain. This removes the dataset, all its documents, and the associated knowledge graph. This action cannot be undone.