Skip to main content
The API reference and the Document Processing guides cover each endpoint on its own. Cookbooks go the other way: each one starts from a problem a team has, then walks the full path from raw file to a result you can ship, often chaining several operations together. Every recipe is a complete, copy-pasteable walkthrough in Python and JavaScript, built around a real document you can download and run against.

​
Pipelines & Workflows

Recipes that chain several operations into one pipeline.

Process Documents in Batches

Coming soon: submit and track hundreds of documents concurrently without hitting rate limits.

Multilingual Extraction

Coming soon: pull the same structured fields out of documents written in over 50 languages.

​
Document Examples

Recipes that solve one real-world document task from start to finish.

Automate Invoice Processing

Coming soon: extract line items and totals from an invoice and route uncertain values to a human.

Sort and Extract a Mixed Document Pile

Split a PDF holding several document types into one file per type, then run a type-specific extraction schema over each.

Redact Sensitive Data From a Document

Find personal data with extraction, locate every occurrence with parsing, and black it out to produce a clean redacted PDF.

Verify Identity Documents

Coming soon: extract and cross-check fields from government IDs and proof-of-address documents.

Review a Redlined Contract

Coming soon: pull clauses, parties, and tracked changes out of a legal agreement.
Want a recipe for a use case that isn’t here yet? Email support@unsiloed.ai and tell us what you’re building.