Overview
This node converts any input file into markdown format using the external 'markitdown' command-line tool. It is useful for scenarios where users want to transform various file types into markdown for documentation, content management, or further processing in markdown-compatible systems. For example, converting HTML, PDF, or other supported files into markdown text automatically within an n8n workflow.
Use Case Examples
- Convert an uploaded HTML file to markdown for easier editing and integration into a CMS.
- Transform PDF reports into markdown format for automated documentation generation.
Properties
| Name | Meaning |
|---|---|
| Input Binary Field | Specifies the name of the binary property that contains the file to be processed and converted into markdown. |
Output
JSON
data- The markdown content converted from the input file, returned as a UTF-8 string.
Dependencies
- Requires the external 'markitdown' command-line tool to be installed and accessible in the system PATH.
- Requires Python 3 and the 'markitdown' package installed via pip.
Troubleshooting
- If the 'markitdown' command is not found, the node throws an error instructing to install Python 3 and the 'markitdown' package, and ensure the command is in the system PATH.
- Errors related to missing or invalid binary input data will cause the node to fail unless 'Continue On Fail' is enabled, in which case the error message is returned in the output JSON.
- Ensure the input binary field name matches the actual binary property name in the input data to avoid errors.
Links
- Python Official Site - Download and install Python 3, required for 'markitdown'.
- markitdown PyPI Package - Information and installation instructions for the 'markitdown' Python package.