Skip to main content
The Datasets page lists all datasets in your workspace. Each dataset is a container for documents and all subsequent operations — see Datasets for the underlying concept.

​
Dataset list

Each row shows:
  • Name — The dataset identifier.
  • Documents — Number of files in the dataset.
  • Created — Creation timestamp.
  • Status — Ready (has documents) or Empty.
Use the search bar to filter datasets by name.

​
Create a dataset

Click New Dataset, enter a name, and confirm. The dataset is created immediately and appears in the list.

​
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.
Uploaded files are automatically processed through the add and cognify pipeline. Processing status is shown per document.

​
Dataset breadcrumb

The breadcrumb at the top of the UI shows the currently selected dataset. This selection is global — it filters content across all pages. When you select a dataset in the breadcrumb:
  • 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.

​
Delete a dataset

Open the context menu on a dataset row and select Delete. This removes the dataset, all its documents, and the associated knowledge graph. This action cannot be undone.
Dataset operations are also available through the REST API and the Cloud SDK.