Skip to main content
Folio turns unstructured documents into structured data. Upload a file, Folio runs an OCR → classify → extract pipeline, and you retrieve a typed JSON result via polling or webhook.
  • What it does — reads PDFs, images, and scanned documents; identifies the document type; and pulls out named fields with per-field confidence scores.
  • Who it’s for — health-tech teams that need reliable, privacy-preserving extraction from clinical and administrative documents at scale.
  • Where it runs — Azure Canada Central, Law 25-aligned, with optional de-identification built into the pipeline.

​
How the pipeline works

Upload (POST /v1/documents)
        ↓
   OCR  →  Classify  →  Extract
        ↓
Result available (GET /v1/documents/{id}/result)
Processing is asynchronous. A POST /v1/documents call returns a 202 with a document id almost instantly. The result is ready seconds to minutes later depending on document size and pipeline configuration.

​
How these docs are organised

SectionWhat you’ll find
Get startedQuickstart walkthrough, API key authentication
GuidesAsync model, webhooks, custom extraction schemas, de-identification, confidence & HITL, language support
API referenceFull endpoint specs auto-generated from the OpenAPI schema

​
Start here

Quickstart

Submit your first document and retrieve a structured result in under five minutes.

Authentication

Learn how API keys work and how to keep them safe.

Async model

Understand the queued → processing → completed lifecycle and how to poll or subscribe to results.

Custom schemas

Define your own field list for any document type.