Bulk PDF to Markdown Conversion Workflow

This n8n workflow streamlines the process of converting multiple PDF files into Markdown format, ideal for content creators, archivists, or technical teams. The workflow begins by listing PDFs from a specified source, such as Google Drive, Dropbox, or local files. It filters out non-PDFs to ensure only valid documents are processed. Each PDF is then converted to Markdown format using the PDFVector API, supporting automatic language modeling for accurate parsing. Once converted, the workflow prepares the output by renaming files and attaching relevant metadata such as page count and credits used during processing. The Markdown files are subsequently uploaded back to Google Drive in a designated folder. Finally, a summary of the conversions—including the total number of files processed and credits used—is generated and sent as a Slack notification to keep users informed about the batch processing status. This automation is particularly useful for teams managing large document repositories, enabling efficient content transformation and storage without manual effort.