Get clean text and structure out of PDFs, HTML, tables and images before anything else.
Starting with Source types, Document parsing, Tables, Cleaning and metadata, Connectors and crawlers, Ingestion pipelines, and more
Made for you now: slide lessons from basics to production, usually with code and a quiz. See a finished one
Get clean text and structure out of PDFs, HTML, tables and images before anything else.
AI EngineeringStage 6 of 17: Data ingestion and document parsing
Start with these 6. 10 more are one tap away.
PDFs, web pages, docs, tickets and databases each need their own way in.
PDFs, tables, layout and OCR.
Keep rows and columns intact so numbers stay next to their labels.
Dedupe, clean and tag content so retrieval can filter it.
Pull from drives, wikis, websites and APIs on a schedule.
Keep sources fresh: schedules, change detection and re-indexing.