Welcome to ExtractForm

ExtractForm is an AI-powered document extraction platform. Define a schema describing the fields you need, upload documents, and receive structured JSON — with webhooks, batch processing, and cloud storage integrations built in.

What do you want to do?

Extract data from a document

Upload a PDF or image and get structured JSON in under 5 minutes.

Define what fields to extract

Create schemas with field types, validation, and allowed values.

Process many files at once

Run batch extractions across uploads, URLs, or connected storage.

Get notified when extraction completes

Import from Google Drive, Dropbox, or S3

Connect cloud storage and automate folder sync.

Build with the API

Full REST API reference with request and response schemas.

Use the web dashboard

Manage schemas, jobs, webhooks, and integrations in the browser.

:::tip Prefer a visual interface? Sign in to the StructaAI Dashboard to create schemas, run jobs, and configure webhooks without writing code. The docs site links back to the dashboard from every page. :::

Key capabilities

Schema-driven extraction — Define fields, types, validation rules, and allowed values with fuzzy matching
Single and batch jobs — Process one document or hundreds via JobRuns
Async processing — Jobs are queued and processed in the background; poll or use webhooks
Cloud integrations — Google Drive, Dropbox, user-owned S3, and public URLs
Outbound webhooks — Signed HTTPS notifications for job lifecycle events
API keys — Automate with long-lived ef_live_… keys

Supported file types

PDF, DOCX, DOC, TXT, HTML, CSV, XLSX, PPTX, PNG, JPEG, and other common document and image formats.

Base URL

All API endpoints are prefixed with /api. During local development:

http://localhost:4000/api

Replace with your production API URL when deploying.

What do you want to do?​