Skip to content

RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.

1.3 KB
Raw Blame

sidebar_position: 3 slug: /file_management/link_knowledge_base sidebar_label: Link Dataset title: Link Dataset sidebar_custom_props: { categoryIcon: LucideFolderDot }

Link Dataset {#link-knowledge-base}

The file management page allows you to add files directly to a Dataset. After the association is created, you can continue operations such as parsing, chunking, and retrieval from the Dataset side. The specific processing status is subject to the Dataset document page.

Link a Single File

  1. Find the target file in the file list.
  2. Hover over the row, then click the Add to Dataset icon in the Action column.
  3. In the pop-up window, select one or more Datasets.
  4. Click Save to save the association.

Link a single file

Batch Link

  1. Select multiple files that need to be linked.
  2. In the batch operation bar, click Add to Dataset.
  3. Select the target Dataset and save.

Batch link files

A single-file operation replaces the Dataset associations of that file with the current selection. A batch operation adds the selected files to the target Dataset. If the same file serves multiple Datasets, confirm the target Dataset name before saving.