Skip to main content
Welcome to Datalab Recipes! This is our collection of detailed, end to end guides to help you become dangerously skilled with our API. We’ll go through edge cases you might run into, fully baked code samples, and more. Many of these examples are based on our managed API, but if you have sensitive documents, our self-hosted on prem solution might be of interest - you can do the exact same thing.

​
What do you want to do?

Parse PDFs into layout-aware HTML, Markdown, or JSON for RAG / ETL → Parse with Marker Pull tables out of PDFs, documents, or websites → Try our Table Recognition API Extract key information out of documents → Run Structured Extraction Automagically segment digitally stapled PDFs → Try Auto-Segmentation Compose multiple steps into reusable pipelines → Try Workflows