Getting Started

What is DocuPipe?

DocuPipe is a document AI platform that lets you define data-extraction workflows and run them with unrivaled reliability. With DocuPipe you can:

1. Parsing millions of documents and scans, in any format.
2. Define the specific information you need to extract. We call that definition a Schema.
3. Extract information reliably by applying your schema to each document. This handles variable layouts, formats, and even 60+ languages while returning a consistent set of fields called a Standardization.
4. Build Workflows that combine Classification, split operations, and more to orchestrate complex extraction tasks.

What do you want to do?

Extract consistent structured data from documents

👉 Document Extraction Quick Start

Split a document into smaller chunks using AI based on content

👉 Splitting Documents

Classify a document or document chunk into one of predefined classes

👉 Classifying Documents

Generate a visual yellow marker that grounds every prediction on the document

👉 Generating Visual Reviews

I'm a Developer. Where Are Your API Docs?

If you want to learn how to interact with DocuPipe with code, head over to our API Docs