Configure document sources for AgentFlow Unstructured

Learn how to configure document sources so AgentFlow Unstructured can access the files you want to process.

Prerequisites:

You must have access to AgentFlow Unstructured.
A published extraction template must be available. For more information, see Create and publish an extraction template.
You have the required authentication details for the source you want to configure. For AWS S3, you have the required role and bucket information and for Google Cloud Storage, you have the service account JSON credentials and bucket information.

Configure a document source so that AgentFlow Unstructured can access files from a supported storage location for document processing.

To configure a document source:

From AgentFlow, select AgentFlow Unstructured.
In AgentFlow Unstructured, select Document AI.
Go to Configure sources and select Let's get started. The Sources page is displayed.
Select + Configure Source to add a new source.
1. Select a source type: AWS S3 or Google Cloud Storage.
2. In the Source Configuration Name field, enter a unique name for the source.
3. Enter the authentication details.
  - For AWS S3, confirm the Authentication Type and enter Role ARN, Bucket Region, and Bucket Name.
    Note: The IAM role you enter in Role ARN must have access to the selected S3 bucket and must be configured with the trust relationship required for AgentFlow Unstructured.
  - For Google Cloud Storage, paste the paste the service account JSON credentials into Service Account JSON, enter Bucket Name, and Location.
4. Select Test Connection to verify that the source is accessible.
5. Select Save .

Result

The document source is configured. You can now use the source when you create or configure a document pipeline. For more information, see Set up automated pipelines.

Unify and manage your data

Configure document sources for AgentFlow Unstructured

Footer