whereismyai
AI Knowledge Graph
AI Knowledge Graph is an AI system extracts knowledge from text documents as triplets and visualizes relationships in an interactive graph.
This system takes unstructured text documents and uses an LLM to extract knowledge as Subject-Predicate-Object triplets. It visualizes the relationships as an interactive knowledge graph in a self-contained HTML file. Users can run it via the command line or a local web interface to ingest files, browse graphs, and ask questions. It supports text inputs including txt, md, rst, pdf, and docx files, and exports data to JSON, CSV, GraphML, and Cypher scripts. The system works with any OpenAI-compatible endpoint such as Ollama, LM Studio, vLLM, and OpenAI.
AI Knowledge Graph at a glance
Key features
- Extracts Subject-Predicate-Object triplets from documents
- Standardizes entities by merging case and plural variants
- Supports PDF, DOCX, TXT, MD, and RST file inputs
- Exports data to JSON, CSV, GraphML, and Cypher formats
- Includes an interactive visual graph explorer
- Provides a local web interface for graph management
- Offers a chat command for grounded answers from the graph
Use it for
- Generate interactive knowledge graphs from text documents
- Query generated knowledge graphs with grounded answers
- Explore entity relationships and communities visually
- Export extracted data to graph databases and tools
Alternatives to AI Knowledge Graph
- Hyper-Extract — Extracts complex knowledge graphs and hypergraphs from documents with one command.
- GraphRAG — Enhances LLM reasoning over private data using knowledge graph structures.
- Graphiti — Provides incremental updates and hybrid retrieval for knowledge graphs.
- WeKnora — Combines RAG, multi-step agents, and automatic Wiki generation in one platform.
- DeepKE — It supports multi-modal, few-shot, and document-level extraction scenarios.
- Jonex — Provides traceable, agent-ready knowledge from diverse enterprise data sources.
- CodeGraph — It eliminates file crawling, reducing AI agent tool calls by 88% and cutting costs.
- yggy — Keeps knowledge graphs automatically up to date with source citations for every fact.
- LLM Wiki Research — Compiles parallel agent research into source-backed markdown knowledge bases.
- Graphlit — Continuous ingestion, entity resolution, and provenance via a single API.
- edgextract — Runs entirely in the browser with local model execution and strict data privacy.
- LightRAG — It uses a dual-layer architecture to reduce LLM calls and retrieval latency.
All AI Knowledge Graph alternatives