Introduction

​

Document Ingestion APIs

There are two main document processing endpoints, one parses them into chunks, markdown or JSON. And the other, extracts structured information. Both endpoints support documents, slides, spreadsheets, and images.

​

Parse

Converts a document into chunks, markdown or JSON. The primary use-case is to make it easy to post-process Documents, so that they can be indexed, summarized, etc and written into databases.

​

Extraction

Extracts structured information from a document. The primary use-case is for data entry automation, business process automation, and to write information in document databases or structured databases.

​

Document Upload

API to upload documents, so that they can be processed by the Parse and Extraction endpoints.

​

Retrieval endpoints

Returns parsed or extracted information from documents. These APIs have to be called with a Job ID, which is returned when a Parse or Extraction job is submitted.