gkg

Extract entities and relationships from unstructured text into a queryable knowledge graph.

3|1|Updated Dec 5, 2025

Search Tags:#knowledge graph #semantic search #information retrieval #text analysis #AI applications

Ready to run

npx skills add https://github.com/trungdo9/ClauKit --skill gkg-trungdo9

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gkg
Source: https://github.com/trungdo9/ClauKit/tree/main/skills/software/gkg
Command: npx skills add https://github.com/trungdo9/ClauKit --skill gkg-trungdo9

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires kg-gen, KGTK, spaCy, LangChain, LlamaIndex, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Gkg helps users to construct semantic knowledge graphs from unstructured text, such as design documents, RFCs, ADRs, and transcripts, by extracting entities and relations for easy querying.

Core Features & Use Cases

Text to Knowledge Graph Conversion: Converts prose into a semantic knowledge graph, where nodes represent concepts (e.g., services, people) and edges represent relationships.
Queryable Output: The output graph is queryable, allowing users to retrieve information efficiently.
Use Case: Useful for organizations with large documentation sets, allowing users to quickly find information about services, components, or decisions without manually searching through documents.

Quick Start

To start using Gkg, you can simply run the command: "build semantic graph from design documents."

Frequently Asked Questions about gkg

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build a knowledge graph from unstructured text documents?▼

Building a knowledge graph from unstructured text involves extracting entities and relationships from documents like RFCs and transcripts to construct queryable nodes and semantic edges for efficient information retrieval.

What is the best way to extract entities and relationships for semantic search?▼

Extracting entities and relationships for semantic search is done by converting unstructured text into a structured knowledge graph, enabling efficient querying of domain-specific information without manual document searches.

How does knowledge graph extraction work with LangChain and LlamaIndex?▼

Knowledge graph extraction with LangChain and LlamaIndex processes unstructured text to identify concepts as nodes and interactions as edges, outputting a structured graph for AI-powered applications.

Can I query domain-specific information from design documents and ADRs?▼

You can query domain-specific information from design documents and ADRs by converting them into a semantic knowledge graph, enabling quick retrieval of details about services, components, or decisions.

Do I need spaCy to perform text analysis for knowledge graph generation?▼

spaCy is used as a dependency for text analysis, working alongside kg-gen and KGTK to parse unstructured text and extract the entities and relations needed for knowledge graph generation.

When should I use a semantic knowledge graph instead of standard text search?▼

Use a semantic knowledge graph instead of standard text search when managing large documentation sets, as it structures concepts and relationships to retrieve interconnected domain-specific information efficiently.