Flows

Flows

Flows Overview

With Flows, your instance can have multiple workflows, or flows, which are made of blocks that represent essential parts of the data-extraction process. In addition to Classification, Identification, and Transcription Blocks, you can work with various other blocks.

Flow Blocks

With the introduction of flows, we have created the following types of blocks to help you customize your flows to meet your teams’ needs. To learn more about any of these blocks or for assistance in adding them to your flows, contact your Hyperscience representative.

Document Processing Flow in V43

In v43, the Document Processing flow included in the instance is a flow group rather than a single flow. The Document Processing flow group consists of a subflow called “Document Processing Subflow V43,” which contains the latest versions of the blocks.

Document Processing Subflow Settings

This article describes the settings available in the Document Processing Subflow included in v43. The settings available in custom flows may differ from those described here, depending on which blocks are included in those flows.

Document Processing with ORCA Subflow Settings

This article describes the settings available in the Document Processing with ORCA Subflow. The settings available in custom flows may differ from those described here, depending on which blocks are included in those flows.

Editing Flows in Flow Studio

You can change the blocks in a flow and customize its blocks’ settings in the following ways: editing the flow with the Flows SDK using the Build Mode options in Flow Studio in the application.

Modifying Custom Code Blocks

Accessing this feature

Your access to the feature described in this article depends on your license package and pricing plan. To learn which features are available to your organization and how to add more, contact your Hyperscience representative.

On-Error Flows

Defining Automatic Block-Retry Policies

Flow Runs Page

When a submission is processed in Hyperscience, its flow-execution information can be viewed in the Hyperscience application. This information can be used to determine why the number of submissions ingested is greater than the number of submissions processed.

Testing and Debugging Flows

With our testing and debugging tools, you can see more information about why a particular submission failed. You can also learn more about how flows are constructed and use what you've learned to build and test your own flows with our Flows SDK.

Using the General Prompting Block

Entity Recognition Block

To extract meaningful data from documents, it is necessary to identify both context-based and structured information within text. The Entity Recognition Block is a processing block used within a flow to identify and extract this information from documents.