Onboarding Unstructured Data

Anzo processes unstructured data through configurable text analytics and natural language processing (NLP) pipelines that find and extract data and convert it to the graph data model. Anzo can process all common file types such as Office documents, PDFs, web pages, and email messages, and can analyze text within Excel, databases, and knowledgebases, or XML columns, properties, and fields. Anzo finds, analyzes, extracts, and ingests concepts, entities, sentiment, topics, classifications, events, facts, and thousands of types of relationships.

The topics in this section provide instructions for creating pipelines and onboarding unstructured data. For information about setting up the Anzo Unstructured environment, see Deploying a Static Anzo Unstructured Cluster.