Building Blocks
Cardinal’s core API endpoints for document processing and data extraction:Split
Classify docs, break apart multi-page files, auto-detect types
Extract
Enter your schema, get a custom output
Markdown
Get clean, readable text output that preserves layout
RAG
Chunk intelligently for retrieval and embedding workflows
Accessories
Enhanced processing capabilities and specialized tools:Image Metadata
Advanced OCR for images and scanned documents with high accuracy
Barcode Detection
Extract barcode data and QR codes from documents and images
Signature Detection
Detect and extract signatures from documents with verification capabilities
Dense PDF Processing
Extract complex tables and structured data from dense PDF documents
Figure Metadata
Extract metadata from charts, tables, and embedded visual elements
Tabular Summaries
Generate intelligent summaries of tabular data and spreadsheet content
Recipes
Complete workflows for common document processing scenarios:Medical Coding
Extract structured diagnosis codes
Prior Authorization
Answer complex prior authorization questions by querying patient medical histories
RCM
Query patient billing records, insurance claims, and payment histories to answer revenue cycle questions
EHR Integration
Automatically populate structured EHR fields
Need help? Contact us at team@trycardinal.ai