What do you want to do?
3 use cases
-
Convert a PDF to clean markdown
Run marker_single on one PDF and get markdown with tables and equations preserved.
View prompt
Using datalab-to/marker, install it with `pip install marker-pdf`, run `marker_single /path/to/file.pdf --output_format markdown --output_dir ./out` on <my PDF>, and summarise any pages where the output looks wrong.
-
Pull just the tables out of a PDF
Use the TableConverter to extract tables only, in a page range you pick.
View prompt
With datalab-to/marker, run `marker_single /path/to/file.pdf --converter_cls marker.converters.table.TableConverter --page_range "0,5-10,20"` on <my report PDF> and turn each extracted table into a CSV.
-
Raise accuracy with hybrid LLM mode
Add the use_llm flag so an LLM merges tables across pages and fixes inline math and forms.
View prompt
Using datalab-to/marker, configure an LLM service from its README, then run `marker_single /path/to/file.pdf --use_llm --redo_inline_math` on <my PDF> and compare the result with a run without the flag.
Quick start with Marker
- Check you have what it needs: Python 3.10+ and PyTorch; pip; A GPU is best, CPU and Apple Silicon also work in fast mode.
- Open datalab-to/marker on GitHub and read the README and license.
- Install with
pip install marker-pdf - Run
marker_single /path/to/file.pdfto convert one file - Add
--output_formatand--output_dirto choose format and folder - Open the markdown and check tables and equations
These steps come from our top use case, Convert a PDF to clean markdown, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for datalab-to/marker
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forAnyone who needs clean text from PDFs for notes, search or LLM pipelines, such as researchers, analysts and developers.
- Why it is hot41k stars, talked about in 2 AI sources we track
- LanguagePython
- Sourcegithub.com/datalab-to/marker ยท Back to Hot repos
Requirements
- Python 3.10+ and PyTorch
- pip
- A GPU is best, CPU and Apple Silicon also work in fast mode
Add this badge to your README
Maintain Marker? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/datalab-to-marker/?utm_source=github&utm_medium=badge&utm_campaign=datalab-to-marker)
HTML
<a href="https://dedupedai.com/use-cases/datalab-to-marker/?utm_source=github&utm_medium=badge&utm_campaign=datalab-to-marker"><img src="https://dedupedai.com/badge/datalab-to/marker.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Marker
What is Marker?
Marker converts PDFs, images, PPTX, DOCX, XLSX, HTML and EPUB files into markdown, JSON, chunks or HTML. It formats tables, equations and code blocks, extracts images, strips headers and footers, and can optionally use an LLM to raise accuracy. It is an open-source project on GitHub: https://github.com/datalab-to/marker.
How do I use Marker?
Install with pip install marker-pdf; then run marker_single /path/to/file.pdf to convert one file; add --output_format and --output_dir to choose format and folder. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is Marker for?
Anyone who needs clean text from PDFs for notes, search or LLM pipelines, such as researchers, analysts and developers.
What can I do with Marker?
3 use cases so far, for example: Convert a PDF to clean markdown; Pull just the tables out of a PDF; Raise accuracy with hybrid LLM mode. Each has steps and a copy-paste agent prompt.
What do I need to run Marker?
Python 3.10+ and PyTorch; pip; A GPU is best, CPU and Apple Silicon also work in fast mode.
What are alternatives to Marker?
Other hot AI repos in Data and analytics: Auto Ontology, Datatrove, Chronos Forecasting, Apify MCP Server, Crawlee Python.
Is Marker safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.