The Adobe PDF Extract API and Adobe Document Generation API are now available to developers.
PDF Extract API is able to extract all PDF elements from a document, according to Adobe.
It can be used to quickly and accurately extract data for use in machine learning models, analysis, indexing or storage, said the company.
That data can then be used in conjunction with technologies such as robotic process automation and natural language processing.
International examiner Cambridge Assessment has been using PDF Extract API to digitise more than 100 years of test material to create a content bank. PDF Extract API is said to have saved the team 2,000 days of labour for every 50,000 questions harvested, while maintaining a 90% accuracy rate.
As its name suggests, the Document Generation API helps programmatically generate documents with dynamic data.
Data can come from sources such as ERP or CRM systems can be merged with custom Microsoft Word templates, thus producing Word and PDF documents containing dynamic data.
Document Generation API is integrated with Adobe Sign, so the resulting documents can be signed electronically.
The Document Generation API is also available via the Adobe PDF Services connector in Microsoft Power Automate to automate the preparation of invoices, agreements, and other documents. 15 ready-to-use templates are provided.
"Our vision for Adobe Document Services is to give developers and IT organisations a platform of choice and flexibility across a broad selection of APIs," said Asia Pacific head of Adobe Document Cloud Chandra Sinnathamby.
"As part of that mission, we continue to make sure that our APIs are available wherever developers find and manage cloud software and services for their businesses. The new APIs we launched today will support developers by accelerating solutions and helping them create seamless PDF experiences."