Create and publish an extraction template

Learn how to create an extraction template to extract structured data from documents in Unstructured augmentation.

Create, validate, and publish a template to define what information Unstructured augmentation must extract from your documents and how the extracted output maps to Reltio entities and attributes. During this process, you review the extracted JSON, verify the mapped fields, and publish the template for use in document pipelines.

Use this procedure to create a reusable template for automated bulk extraction. To process a single document without configuring a source or pipeline, see One Time Upload.

Prerequisites

Before you begin, ensure you meet the following requirements:

You need an active Reltio tenant with access to Unstructured augmentation.
You must have a source document that contains data to extract in one of these formats:
- PPTX: up to 15 MB
- DOCX or PDF: up to 10 MB
- HTML or RTF: up to 5 MB
- TXT: up to 2 MB
- PNG, JPG/JPEG, or TIFF/TIF: up to 10 MB. Image files require OCR to be enabled for your environment.

To create and publish an extraction template

In Unstructured augmentation, select Unstructured extraction.
Under Automated Bulk Extraction, in the Create template section, select Create template. The Create new template page is displayed.

Note: To process a single document instead, under One Time Upload, select Proceed. For more information, see
1. In the Template name field, enter a name for the template.
2. In Upload a file section, drag and drop a sample file, or select click to upload a file.
  For supported file formats and size limits, see the Prerequisites section.
3. Select the Use OCR for scanned/handwritten documents toggle below Upload a file to enable or disable OCR for the uploaded file.
4. From the Client ID dropdown, select an existing client ID or create a new client ID, and then select Fetch tenants. The Select a tenant field is displayed below. To create a new client ID, see Client Credentials at a glance.
5. From the Select a tenant dropdown, select the tenant that should receive the extracted structured data from your documents.
Select Next to proceed to the Review Extraction step. Review the extracted JSON output to confirm that the expected data was extracted.

Review the uploaded document in the left pane and the extracted JSON output on the right pane. Confirm that the extracted output contains the expected values.
1. Enter text in the Search bar to find specific fields or values in the extracted JSON output, if needed.
2. Select Finetune extraction to open the AI Chat Extraction box.
3. Add instructions for any additional data you want to extract and select Extract information. Unstructured augmentation updates the extracted JSON.
Select Next to go to the Verify Mappings step. A Mapping Fields... message appears while Unstructured augmentation maps the extracted JSON to the data model of your target tenant.
1. Use File View or JSON View to inspect the source content and extracted structure.
2. Use Search to find specific values, if needed.
3. In the Verify entities section on the right pane, review each entity card. Confirm the entity type, mapped attribute count, and confidence value for each entity.
4. Select Verify for an entity type to review the mapping details and confirm that each extracted document field maps to the correct entity type.
5. Check the values in RELTIO ATTRIBUTES and EXTRACTED FIELD KEY to confirm that the field maps to the correct Reltio attribute.
6. Review the VALUES column to make sure the extracted content is correct and complete.
7. Review the CONFIDENCE column to understand how certain the system is about that mapped value.
8. Expand rows to review additional mapped content, if needed.
9. Update the selected Reltio attribute for a field if the mapping needs correction.
10. Select Verify attributes to indicate you've verified all attributes and their mappings.
Select Next to continue to the publishing step.
1. Review the template details and select Publish to publish the template.

Result

Unstructured augmentation publishes the template. You can select it when you create or configure a document pipeline. For more information, see Configure document sources for Unstructured augmentation and Set up automated pipelines.

Unify and manage your data

Create and publish an extraction template

Footer