Convert formatted markdown to PDFs without additional libraries or paid services

Built with n8n
,
1

I’ve just published a new workflow template that helps you automatically generate professional PDFs and share them with your team in Slack.

It use custom HTTP request node to create document on Google Drive (with markdown support), it is different from what other solutions shared before.

:backhand_index_pointing_right: Workflow link: Generate and Share Professional PDFs with OpenAI, Google Docs, and Slack

:backhand_index_pointing_right: Video walkthrough:

Watch the video

:sparkles: What it does

  • Uses OpenAI to generate structured content.

  • Saves and formats it nicely in Google Docs.

  • Exports the doc into a polished PDF.

  • Sends the file to your chosen Slack channel for instant sharing.

:wrench: Use Cases

  • Automating client reports.

  • Weekly project summaries.

  • HR/TA candidate reports.

  • Any process where you need a consistent, professional PDF output.

Would love to hear your thoughts, feedback, or ideas for improving this workflow! :light_bulb:

1 Like
2

Sample output formatted PDF from markdown:

Alt text
Optional title text1230×1586 79.1 KB

Alt text
Optional title text1240×1596 84.5 KB

Alt text
Optional title text1234×1592 72.5 KB

Alt text
Optional title text1262×1588 212 KB

3

Extremely useful functionality, and it worked immediately - thanks!

1 Like
4

@Justin_Simpson, awesome, I’m glad you find this helpful!

Happy coding,

Trung Tran.

5

Thank you @trungtlt . The Create Document File node is very helpful to get the md recognized as such by Google Drive!

6

See repo: PDF to Markdown Wrapper (pdftomd.sh) is a RAG workflow-friendly enhancement of Marker that converts a PDF into a single markdown file. It handles GPU and PyTorch configuration, document splitting and chunking, image BASE64 embedding, LLM post-processing and cleanup, and consolidation of output

  • Splits large PDFs into chunks (100 pages by default, 10 pages when -l/–llm is enabled) and runs Marker once on the chunk folder (avoids repeated model loads).
  • Consolidates all chunk markdown into a single .md file.
  • Optionally embeds images as Base64 (no external asset folders needed).
  • Optional text-only output that strips image links from the final markdown.
  • Optional OCR pass via bundled ocr-pdf/ocr-pdf.sh before conversion.
  • Optional LLM helper via a built-in Marker --use_llm.
  • Automatically uses GPU when available and installs CUDA-enabled torch when needed.
  • Cleans up intermediate files and attempts to stop spawned processes on exit.
  • Optional supplemental LLM post-processing step with --clean.
  • The overall result can be a much cleaner more streamlined end product more suited to RAG pipeline ingestion.