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.

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.

knwler

Quick Start

Simple Setup

You can install knwler in minutes using pipx. It creates an isolated environment and makes the knwler command available globally without affecting your system Python or other projects.

> pipx install knwler

After installation, run the pipeline on your documents with a single command. To process a PDF and export everything to a specific folder:

> knwler -file path/to/document.pdf --output ~/reports

This uses Ollama with the Qwen 2.5 3B model by default. To use OpenAI, set your API key and add the --openai flag:

> export OPENAI_API_KEY="your_api_key_here"
> knwler -file path/to/document.pdf --backend openai --output ~/reports

To see all available commands and options:

> knwler --help

You can also install via UV or directly from GitHub for the latest features:

> uv add knwler

Features

Capabilities

Enterprise-grade document intelligence

Purpose-built for organizations that need to extract structured insight from regulatory, legal, and compliance documents at scale.

✦

Automatic Schema Discovery

The pipeline analyzes document samples and infers optimal entity and relation types. No manual ontology engineering required.

🌐

Multilingual by Design

Auto-detects language and adapts all prompts. Supports English, German, French, Spanish, and Dutch out of the box.

🔒

Air-Gapped Operation

Run fully on-premise with local LLMs. Zero data leaves your infrastructure. Meets the strictest data sovereignty requirements.

〰

Community Detection

Automatically discovers clusters of related entities and assigns human-readable topic labels for instant thematic insight.

📄

Rich Export Ecosystem

Export to JSON, GML, GraphML, and interactive HTML. Import directly into Neo4j, Gephi, yEd, Memgraph, or SurrealDB.

⬆

Incremental Augmentation

Process new documents and the existing graph is augmented, not rebuilt. Entity descriptions are consolidated intelligently.

How It Works

Process

From document to knowledge in three steps

A streamlined pipeline that turns unstructured text into structured, queryable knowledge.

Ingest

Upload PDF, text, or Markdown documents. The system extracts and segments content into optimally sized chunks for analysis.

Extract

LLM-powered extraction identifies entities, relationships, and topics. Schema is discovered automatically or supplied by your team.

Deliver

Receive an interactive knowledge graph with community detection, topic labels, and exports ready for your graph analytics platform.

Use Cases

Applications

Built for high-stakes document workflows

Trusted by teams where accuracy, traceability, and data privacy are non-negotiable.

📋

Regulatory Compliance

Map entities and obligations across 100+ page regulatory documents. Understand cross-references and dependencies at a glance.

🖥

Legal Analysis

Extract parties, clauses, and contractual relationships from legal documents. Surface hidden connections across document sets.

📚

Research Intelligence

Build knowledge graphs from academic papers and reports. Identify key concepts, authors, and methodological connections.

👤

Due Diligence

Accelerate M&A and audit processes by automatically structuring findings from financial disclosures and corporate filings.

Examples

Real documents, real results

Each example was processed in minutes with full knowledge graph output. Explore the interactive reports yourself.

Dutch

Belgian Civil Law (Enterprise Data Viz)

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

English

Human Rights (Enterprise Graph Viz)

The Human Rights in an advance graphviz based on yFiles.

Deutsch

Deloitte Nachhaltigkeitsbericht 2024

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.