Introducing s-1: Sievly’s new document reading model
All posts
Guides
Guide: Parse, Extract, Split or Edit?
A short guide to picking the right Sievly endpoint for the job, and when to chain them.
Theo Albrecht
·
Product Lead, Workbench
sievly
Choosing an endpoint
Sievly has four core endpoints. Each does one job well, and most production pipelines chain two or three of them.
Parse
Use Parse when you want the whole document as clean, structured content: text, tables and figures in reading order, ready for search or retrieval.
Extract
Use Extract when you know the fields you need. Give it a schema and get back values with citations.
Split
Use Split when one file holds many documents. It finds the boundaries so each part can be handled on its own.
Edit
Use Edit to fill forms or update documents with plain-language instructions, keeping the original layout.
More from the blog
sievly
Introducing s-1
Announcements
Introducing s-1, our new document reading model
s-1 reads PDFs, scans and spreadsheets the way a careful analyst does, and returns structured data with a citation for every value. It is available in preview today.
sievly
Reading order
Research
Research note: reading order in complex layouts
Multi-column pages, sidebars and callouts confuse simple reading order. We share what we learned teaching s-1 to follow the page the way a person would.
sievly
Quarryline × Sievly
Case Studies
How Quarryline turns research notes into a searchable knowledge base
Quarryline’s data team uses Parse and Extract to turn thousands of analyst notes, filings and spreadsheets into clean, cited records their AI assistant can trust.