Getting Started

Supported File Formats

Document Understanding supports the following file types.

JPG, PNG, PDF, and TIFF files are supported.

Supported Languages

Document Understanding supports several languages depending on the model version.

  • Version 1 - English is supported.
  • Version 2 - Multilingual support (except English).
The following table lists the languages supported by each version:
Supported Languages (by language code)
Model Name Variable Version 1 Languages Version 2 Languages

Optical Character

Recognition (OCR)

NOT APPLICABLE EN

AR, ZH, FR, DE, HE, JA, PT, RU, ES, NL, UK

Document Classification

NOT APPLICABLE EN NOT APPLICABLE

Custom Document

Classification

NOT APPLICABLE EN NOT APPLICABLE

Table Extraction

NOT APPLICABLE EN NOT APPLICABLE

Key-Value Extraction

Invoice EN

AR, ZH, FR, DE, HE, JA, PT, RU, ES, NL, UK

Key-Value Extraction

Receipt EN

AR, ZH, FR, DE, HE, JA, PT, RU, ES, NL, UK

Key-Value Extraction

Driver ID EN NOT APPLICABLE

Key-Value Extraction

Passport EN NOT APPLICABLE

Key-Value Extraction

Health ID EN NOT APPLICABLE

Custom Key-Value Extraction

NOT APPLICABLE

Classic

Evaluated for:

EN, ES, PG

Supports 200+ more languages by design.

Generative

Evaluated for:

EN, ES, FR, GR, DU

Supports 200+ more languages by design.

Supported Regions

Document Understanding services are hosted in regions and availability domains. A region is a localized geographic area, and an Availability domain is one or more data centers located in that region.

For Custom Models using Generative AI

You can create and mange custom generative models v2.0 only in the following regions:
  • Brazil East (Sao Paulo)
  • Japan Central (Osaka)
  • UK South (London)
  • US Midwest (Chicago)

See Creating a Custom Generative Model V2.0 (New).

For all other Document Understanding Features

Except for the subset of regions that you can manage custom generative models in, Document Understanding is hosted in the following regions:

Accessing the Service

You access Document Understanding using the Console, REST API, SDK, or CLI.

Use the following options to access Document Understanding

Pick an option, based on your preference and its suitability, for the task you want to complete:
  • The Oracle Cloud Infrastructure Console is an easy-to-use, browser-based interface. To access the Console, you must use a supported browser.
  • The REST APIs provide the most functionality, but require programming expertise. API reference and endpoints provide endpoint details and links to the available API reference documents including the Artificial Intelligence Services REST API.
  • Oracle Cloud Infrastructure provides SDKs that interact with Language without the need to create a framework.
  • The CLI provides both quick access and full functionality without the need for programming.
Note

Document Understanding isn't supported in the Oracle Always Free Tier.