marker-convert

To convert PDF to Markdown, this tool uses the Marker CLI to extract text and images, outputting structured Markdown files. It processes single files or entire folders sequentially into a dedicated output directory.

Yes, you can batch convert a folder of PDFs to HTML or JSON using the wrapper script. The tool processes each PDF sequentially and writes the converted content with metadata into a separate output folder per document.

You need the marker_single command available on your PATH to run Marker PDF conversion. Once configured, the wrapper script handles the extraction and writes run logs under a persistent state directory.

PDF to Markdown conversion supports resuming after an interruption via a persistent state. It tracks processed, failed, and error logs, allowing the conversion to continue from where it stopped without starting over.

Yes, you can enable LLM-assisted extraction when converting PDFs to JSON or other formats. When configured, Marker leverages LLMs for advanced interpretation and extraction during the conversion process.

The best way to extract images from a PDF alongside text is using Marker for conversion. It automatically extracts embedded images and saves them with the converted Markdown, HTML, or JSON content in individual output folders.