- Extract: Schema-driven structured data extraction to pull out specific fields from documents.
- Parse: Convert documents to markdown to build RAG/Knowledge Graph systems.
- Orchestrate: Build programmable workflows for large-scale ingestion and enrichment of Documents, Text, Audio, Video and more.
Document Ingestion Quickstart
Get started with Document Ingestion
Common Document Ingestion Use Cases
Insurance
Extract liability and coverage details from ACORD forms
Retrieval Augmented Generation
Get high-quality layout-aware chunks from Documents for RAG and Knowledge Graphs
Legal
Analyze contracts, detect footnotes, detect presence and coordinates of signatures
Text Ingestion
Extract structured data from emails, CSVs, and HTML files