Load parsed financial tables
Connect
SPIRITT
ArynAryn
Complex documents, fully parsed
SPIRITT uses Aryn to break dense PDFs into text, tables and images, organizes them into DocSets with your properties and builds search, analytics and apps on the parsed results.
What you can do with Aryn.
Tables come out intact
Layout-aware partitioning keeps tables, sections and images structured, with OCR when pages are scanned.
Collections built for questions
DocSets hold parsed documents with custom properties, prompts and schemas you define.
Queries planned before running
SPIRITT generates and reviews query plans so analytics over the DocSet are precise.
Works with your other apps.
Get started in three steps.
01
Open your workspace
Start a SPIRITT workspace for the document collections you need to understand.
02
Connect Aryn
Connect Aryn so SPIRITT can parse documents and manage DocSets.
03
Delegate an outcome
Share the documents and questions. SPIRITT parses, organizes and builds.
Hand over a mission.
Choose a mission. Make it yours.
Put Aryn to work.
Make dense documents usable
Questions
Aryn, with SPIRITT.
01What can SPIRITT do with Aryn?+
Partition documents into structured elements, create and manage DocSets, add documents asynchronously, retrieve parsed or original files and generate query plans.
02Does it handle tables and scans?+
Yes. Partitioning supports table extraction, image handling, OCR and chunking options.
03What is a DocSet?+
A collection of parsed documents with your own properties, prompts and schema, ready for search and analytics.
04Can I get the original file back?+
Yes. SPIRITT retrieves the original binary of any document in a DocSet.
05How are large batches handled?+
Documents are added asynchronously and SPIRITT tracks outstanding tasks until they finish.
06How do I get started with Aryn?+
Open a SPIRITT workspace, connect Aryn and share a folder of documents. SPIRITT parses them and builds what you need.