Getting Started Concepts CLI Reference Environment Variables DuckDB Configuration Validation Scripting Examples Lineage & Metadata

Blueprints Blog Contact About

Getting Started Concepts CLI Reference Environment Variables DuckDB Configuration Validation Scripting Examples Lineage & Metadata

Blueprints Blog Contact About

Getting Started

Models Directives Model Kinds Smart CDC Schema Evolution Incremental Models Dependency Graph OData Sandbox Mode Maintenance Event Collection

Environment Variables

DuckDB Configuration

settings.sql secrets.sql extensions.sql catalog.sql macros.sql variables.sql sources.sql

Constraints Audits Warnings

HTTP Module Save Module OAuth Module Runtime Modules Language Reference

Ingest from a REST API YAML Model with Shared Library Track Product Analytics Build Daily Metrics Incremental SQL Model SCD2 Dimension Validated Model

Lineage & Metadata

Home / Tags / Ocr

Ocr

Mistral OCR

Extract structured data from PDF invoices using Mistral OCR — one YAML model, one shared source function, one API call per file.

On this page

Open source data infrastructure that runs on your hardware. No cloud required.

Documentation

Getting Started DuckDB Configuration CLI Reference Concepts Validation Scripting Examples Lineage & Metadata

More

Blueprints Blog Contact About Privacy Policy Terms of Service Discord GitHub

© 2026 Marcus Hernandez