RAGFlowInstall

Summary

Uploads each input item’s binary file to the selected RAGFlow dataset, then attempts to start parsing the uploaded document for indexing.

Inputs

• Dataset ID (required) — Dataset to receive the file; selected from the available datasets.
• Binary Property (required) — Name of the incoming item’s binary property containing the file. Defaults to data. The file’s name and MIME type are taken from its binary metadata, with fallbacks of document.pdf and application/pdf.

Output shape

One output item per input item, each containing a JSON object.

On success, the object includes status: "success", an action describing whether upload and parsing started or parsing failed, the RAGFlow upload response in data, and fileName. The node posts the file to the dataset’s documents endpoint and, when it can extract document IDs from the response, posts those IDs to the chunks endpoint to start parsing. Errors stop execution unless Continue On Fail is enabled, in which case an item with an error field is returned.

Links

• n8n community nodes installation guide