Structured Data Processing

Learn how to process documents and extract structured data using TrustGraph’s schema-based extraction capabilities.

This feature was introduced in TrustGraph 1.2 and extended to support querying in 1.3.

Overview

TrustGraph provides capabilities for working with ‘objects’. This is data which could be described in e.g. table rows.

The following capabilities are available in TrustGraph 1.3 for you to work through with this guide.

• Loading object data from documents. In this guide tablular data from an example PDF document is extracted to an object store.
• Loading object data from structured data files. Data files in XML, JSON and CSV format can be loaded into the object store. This guide will work with an example data file.
• Querying is possible in a number of forms - this guide will look at querying using GraphQL and also executing a natural language query.
• Structured data queries can also be invoke from an agent, so that tabular data is integrated with an agent flow.

See also

• Schemas
• Load from a document
• Load from a data file
• Querying structured data
• Agent integration

---

Table of contents

• Schemas
• Structured data load from a document
• Structure data load from a data file
• Querying structured data
• Agent integration