Skip to main content

Box Data Extract

Availability:
Not available Airbyte CloudAvailable Airbyte OSSAvailable PyAirbyte
Support Level:
Marketplace
Connector Version:
0.1.8(Last updated a day ago)
CDK Version:
6.42.1(Latest)

The Box Data Extract Connector enables seamless data extraction from Box, allowing users to access file content from their Box cloud storage.

This connector helps automate workflows by using Box AI to extract data directly from documents stored in Box.

For example, a company managing lease contracts can automatically capture key details and populate their system of record. Likewise, a financial institution can extract critical data from loan application documents—such as bank statements and W-2s—and integrate it into approval workflows.

By prioritizing content intelligence, this connector unlocks new opportunities for automation and AI-driven insights.

This page contains the setup guide and reference information for the Box Data Extract source connector.

Prerequisites​

You will need a Box application configured to use Client Credential Grants (CCG) Follow this guide to complete authentication.

From your box app configuration take note of:

  • Client ID: You Box App client ID. Find yours in the Box App configurations.
  • Client Secret: You Box App client secret.

Decide on what account is going to login to Box:

  • Box Subject Type: Represents the type of user to login as ("user" or "enterprise"). Enterprise will login with the application service account. User will login with the user if app can impersonate users.
  • Box Subject ID: If subject type is "enterprise", use your enterprise ID If subject type is "user", use the user id to login as.

Choose the which Box folder conatins the files you want to process:

  • Folder ID: Folder to retreive data from.
  • Recursive: Read the folders recursively.

If you are using Box AI you'll need:

  • Ask AI Prompt: If using the Ask AI, what prompt to send the AI about the document
  • Extract AI Prompt: If using the Extract AI, what prompt to send the AI about the document
  • Extract Structured AI Fields: If using the Extract Structured AI, what prompt to send the AI about the document. For more information on the expected format of this prompt check our developer documentation.

Setup guide​

Set up Box Data Extract​

For Airbyte Cloud:​

  1. Log into your Airbyte Cloud account.
  2. Click Sources and then click + New source.
  3. On the Set up the source page, select Box Data Extract from the Source type dropdown.
  4. Enter a name for the Box Data Extract connector.
  5. Fill in the information:
    1. Client ID
    2. Client Secret
    3. Box Subject Type
    4. Box Subject ID
    5. Folder ID
    6. Recursive
  6. Click Setup source

For Airbyte Open Source:​

  1. Navigate to the Airbyte Open Source dashboard.
  2. Click Sources and then click + New source.
  3. On the Set up the source page, select Box Data Extract from the Source type dropdown.
  4. Enter a name for the Box Data Extract connector.
  5. Fill in the information:
    1. Client ID
    2. Client Secret
    3. Box Subject Type
    4. Box Subject ID
    5. Folder ID
    6. Recursive
  6. Click Setup source

Supported sync modes​

The Box Data Extract source connector supports the following sync modes:

FeatureSupported?
Full Refresh SyncYes
Incremental SyncNo
SSL connectionYes
NamespacesNo

Supported Streams​

Reference​

Config fields reference

Field
Type
Property name
string
client_id
string
client_secret
string
box_subject_type
string
box_subject_id
string
box_folder_id
boolean
is_recursive
string
ask_ai_prompt
string
extract_ai_prompt
string
extract_structured_ai_fields

Changelog​

Expand to review
VersionDatePull RequestSubject
0.1.82025-03-2956593Update dependencies
0.1.72025-02-13Adding Box Extract Structured AI stream
0.1.62025-02-13Adding Box Extract AI stream
0.1.52025-02-13Adding Box Ask AI stream
0.1.42025-02-12Initial release by @BoxDevRel
Was this page helpful?