Unstructured Data Ingestion

Dataworkz ingests unstructured content from files and web sources and converts it into structured datasets ready for chunking and embedding.

• Ingesting Unstructured Data — Create a custom ingestion job without an AI application

• Unstructured File Ingestion — Ingest PDFs, Excel, Word, PowerPoint, plain text, and Markdown files

• HTML / SharePoint Ingestion — Crawl web pages or ingest from SharePoint