Document Extraction
Guides, tutorials, and real-world workflows for composable document and image processing.
Calculated Fields: Let the Parser Do the Math on Your Invoices
Define formulas that compute values from other extracted fields. Subtotal + tax = total, calculated automatically.
Extract IBANs, Currencies, and Addresses from Financial Documents — Validated, Not Just Strings
Purpose-built field types for financial documents. IBAN validation, structured addresses, currency amounts with codes.
Parse Property Appraisals into Structured Data for Your Real Estate Platform
Extract property details, valuations, comparable sales, and conditions from appraisal documents automatically.
Turn Messy Supplier Catalogs into Clean Product Data — Automatically
Parse supplier PDFs and spreadsheets into structured product records. SKU, price, dimensions, descriptions.
Extract Parties, Dates, and Clauses from Legal Contracts — Automatically
Parse legal contracts into structured data. Extract parties, effective dates, termination clauses, and obligations.
From Paper Receipt to Structured JSON — Build a Receipt Scanner with One API
Scan receipts and extract merchant, items, totals, and tax as structured data. Built-in OCR, no preprocessing.
Build a Resume Parser That Actually Works — From PDF to Structured Profile
Extract name, contact info, experience, skills, and education from any resume format. One API call.
Stop Copying Invoice Data by Hand — Automate It with One API Call
Extract invoice numbers, line items, totals, and tax from any invoice format. One API call, structured JSON output.
Extract Clean Article Text from Any Document — No Boilerplate, No Noise
Pull the actual article content from PDFs, Word docs, and web pages. No headers, no footers, no navigation.
Extract Structured Data from Any PDF in 3 Lines of Code
Define a schema, send a PDF, get structured JSON with confidence scores. No regex, no templates, no training.
The Complete Guide to Document Parsing in 2026
From regex to AI extraction — the complete guide to parsing documents programmatically. Methods, tools, and code examples.