smartextract user guide

Welcome to the smartextract user guide!

What is smartextract?

smartextract is a document understanding platform leveraging state-of-the-art AI methods, including generative models (LLMs). It allows you to combine various procedures such as OCR, document splitting and classification, information extraction and data validation in order to assemble document processing pipelines automating a wide range of back-office tasks — from simple or standard use-cases to highly customized and complex ones.

How do I get started?

The best way to start exploring the possibilities offered by smartextract is through the web-based user interface. After creating an account, you will be able to immediately process various types of document with out-of-the-box extraction models and customize those models to fit your needs.

If you have a rather special use case, you can also define an extraction model from scratch; alternatively, contact us for assistance.

For most users, the web UI covers all needs, including validating and exporting extraction data. We hope our UI is intuitive enough that no additional documentation is necessary. If you require programmatic access, there is a REST API which is documented in this guide.