In addition to the @intuned/sdk utilities, we offer standalone APIs for file related operations (extract structured data, extract/convert-to markdown, extract tables). These APIs can be utilized without creating projects or writing any browser automation logic, with costs varying based on the operation used and file size.

​
Sync vs. Async APIs

Each of the operations listed above is available via a Sync API and an Async API. In Sync APIs, the result is returned in the same HTTP call that was made to invoke API. In Async APIs, the result is returned in a separate HTTP call (Async Result call), using an operationId that is returned in the first call (Async Start call).

​
Extract structured data from files

For more info, checkout the reference for the Sync API and Async APIs: Async Start and Async Result.

​
Convert files to markdown

For more info, checkout the reference for the Sync API and Async APIs: Async Start and Async Result.

​
Extract tables from files

For more info, checkout the reference for the Sync API and Async APIs: Async Start and Async Result.

​
Supported file formats

We currently support pdf files and image files. We will be working on supporting other formats soon. Contact us if you have any specific requirements.

​
How are costs calculated?

  • For Markdown conversion and Table extraction APIs, cost is based on number of pages in the files processes.
  • For Structured data extraction APIs, cost is based on number of pages in the files processes and the size of the input data and the schema used. This is because structured data extraction is a two step process: convert to markdown + run extraction.