Source Box Data Extract

[barduinor]

Hi folks,

As a developer advocate working for Box.com we would like to contribute with a new source connector that will enable Airbyte users to extract data from documents stored in Box.

This new connector implements several Box features:

• Extract the text representation of a document
• Get a Box AI answer to a question or questions about a document
• Extract structured data in free format from an unstructured document
• Extract structured data using a formal structure from an unstructured document

Tell us about the new connector you’d like to have

• Which source and which destination?
  • Source Box.com Files
  • Destination: Any
• Do you need a specific version of the underlying data source e.g: you specifically need support for an older version of the API or DB?
  • No

Describe the context around this new connector

Why do you need this integration? How does your team intend to use the data? This helps us understand the use case.

A significant percentage of data available to companies is lost somewhere in unstructured documents.
What if we could use AI to read those documents and return structured data that can easily be integrated into other systems of record, workflows, etc.

How often do you want to run syncs?
Depends on the use case

If this is an API source connector, which entities/endpoints do you need supported?
Folder, Files, AIAsk, AiExtract, and AIExtractStructured

If the connector is for a paid service, can we name you as a mutual user when we subscribe for an account?
Which company should we name?
Box.com is indeed a paid service, we are targeting common customers between the companies, and developers who use both products to create solutions..
The are free developer accounts available and it would be my pleasure to give Airbyte access to a development sandbox.

Are you willing to submit a PR?
Yes, in the next hour or so