Knwler is an enterprise document intelligence platform that extracts structured knowledge graphs from documents using Large Language Models. It identifies entities, relationships, and topics from PDFs, text files, and Markdown — producing interactive reports and exports for graph analytics platforms.

Can Knwler run fully on-premise?

Yes. Knwler supports fully air-gapped operation via Ollama with open-weight models. No data leaves your infrastructure, making it suitable for classified and regulated environments with strict data sovereignty requirements.

What languages does Knwler support?

Knwler auto-detects document language and supports English, German, French, Spanish, and Dutch out of the box. Additional languages can be added by extending a single configuration file.

What export formats are available?

Knwler exports to JSON, GML, GraphML, and interactive HTML. These can be imported directly into Neo4j, Gephi, yEd, Memgraph, SurrealDB, or used to generate vector embeddings for semantic search.

How much does it cost to process a document?

Using cloud LLMs (OpenAI GPT-4o), processing costs approximately $0.20 per 20-page document. Running on-premise with local models is completely free after initial setup. Intelligent caching means re-runs cost nothing.

Examples

Belgian Civil Law

All nine books of the Belgian Civil Law were extracted and consolidated via Knwler. The visualization was made with Linkurious Ogma.

Enterprise Graph Visualization

The Human Rights in an advance graphviz based on yFiles.

Belgian Civil Law Analytics

Every extraction can be used with some graph analytics to understand the most important paragraphs, topics, entities and relationships.

CNN

The CNN homepage fetched with a simple knwler -f https://cnn.com.

Deloitte

The Deloitte 2024 Global Impact Report highlights the firm’s commitment to driving inclusive and sustainable progress amidst global challenges like geopolitical tension and rapid technological change.

NIST Artificial Intelligence Risk Management Framework

The NIST AI Risk Management Framework (AI RMF 1.0) provides a structured approach for organizations to identify, assess, and manage risks associated with artificial intelligence systems.

EU AI Act

EU Regulation 2024/1689, the Artificial Intelligence Act, establishes a unified legal framework for the development, marketing, and use of AI systems across the European Union.

Human Rights (custom graphviz)

The Universal Declaration of Human Rights is a foundational document proclaiming that all human beings possess inherent dignity and equal, inalienable rights as the basis for freedom, justice, and peace.

Human Rights (3-columns)

The Universal Declaration highlights based on graph analytics of the extracted network.

Analysis of MBTI Personality Types in Workplace Dynamics

The document analyzes the Myers-Briggs Type Indicator (MBTI) and its application in understanding personality differences in the workplace.

Key Differences Between Happiness and Meaningfulness

The document discusses the key differences between happiness and meaningfulness, highlighting that while they overlap, they have distinct predictors and implications.

VALUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation

The paper presents a framework called VALUES for systematically validating uncertainty estimation methods in semantic segmentation.

Vanden Broele: Digitale oplossingen voor lokale besturen en overheden

Vanden Broele is een Belgische organisatie die digitale oplossingen en diensten biedt aan lokale besturen, bedrijven en verenigingen.

Meta continual learning revisited: implic- itly enhancing online hessian approximation via variance reduction

Continuous machine learning research from ArXiv.