We are excited to announce the release of Hyland Knowledge Enrichment, a powerful new data management suite that transforms unstructured enterprise content into AI-ready, contextualized data for AI agents and automation workflows. It combines advanced text and structure extraction with intelligent enrichment, delivering clean, organized, and actionable insights from documents, images, and other content types.
This release represents a strategic milestone in Hyland’s AI and data innovation roadmap. Knowledge Enrichment is built as a cloud-native API, designed to integrate seamlessly into modern data pipelines, enterprise architectures, and AI systems. It plays a critical role in helping organizations prepare their content for AI agents,intelligent automation, semantic search, and decision support, without requiring manual preprocessing or restructuring of legacy systems. This is only the first step in the larger vision of being a full data management platform.
A representation of enriched metadata for this image, including a visual description.
Note: This image is conceptualized. Knowledge Enrichment does not have a UI, but is a suite of SaaS-based APIs purpose-built for AI solution builders and ML engineers to accelerate AI readiness by taking unstructured data like documents, emails and images -- curating it into structured, organized formats that systems (AI, analytics, etc.) can use immediately.
Key features
This release enables organizations to enrich their data lakes and catalogs with meaningful metadata, summaries, relationships, and embeddings, making enterprise content more discoverable, analyzable, and usable across AI workflows, governance systems, and decision intelligence pipelines.
- Support for 600+ file types – Process and analyze diverse content formats including structured documents (PDF, Word, Excel), multimedia files (images, audio, video), code repositories, email archives, and legacy formats, ensuring comprehensive coverage of your organization's data ecosystem.
- Contextual metadata – Extract and create rich, semantically-meaningful metadata including topics, themes, entities, document types, and business context, transforming unstructured content into structured, queryable information assets.
- Contextual text chunking – Intelligently segment documents into meaningful chunks while preserving structural context, section hierarchies, and positional references, enabling more accurate retrieval and maintaining document relationships for downstream AI applications.
- Image description – Automatically generate detailed, contextually-aware descriptions of images, charts, diagrams, and visual content within documents, making visual information searchable and accessible for content discovery and compliance workflows.
- Embedding generation – Create high-dimensional vector representations of content that capture semantic meaning and relationships, enabling advanced similarity search, content clustering, and AI-powered recommendation systems across your knowledge base.
For more information, please check out the Knowledge Enrichment product guide and developer blog.
Come join us as we discuss Knowledge Enrichment in its Release Webinar on July 24 and on-demand.
