Flow tools
Processing documents in flows (Public preview)
This feature is currently in public preview. Functionality and behavior may change in future updates.
Enabling document processing in watsonx Orchestrate Developer Edition
Run the following command to enable watsonx Orchestrate Developer Edition to process documents:
[BASH]
Configuring document processing in flows
In your flow, include a call to the ‘docproc()’ method to process a document. This method accepts the following input arguments:
Parameter | Type | Required | Description |
---|---|---|---|
name | string | Yes | Unique identifier for the node. |
task | string | Yes | Specifies which information is extracted from the document upon processing; supported values are:
|
display_name | string | No | Display name for the node. |
description | string | No | Description of the node. |
The input to a docproc
node is expected to be of type DocumentContent
, from the module ibm_watsonx_orchestrate.flow_builder.types
.
Example use of the docproc
node in a flow:
[Python]
You can find more examples in the flow_builder folder, such as invoice_extraction, text_extraction, and utilities_bill_extraction.