Vibe Coding DiscoverHyper-Extract
View on GitHubHypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
Hyper-Extract is a Python CLI and library that turns unstructured documents into structured knowledge — graphs, hypergraphs, temporal and spatial graphs — using LLM extraction engines like GraphRAG, LightRAG and Hyper-RAG, with FAISS-backed semantic search, incremental provenance tracking and an optional MCP server.
Use Cases
Turn papers and PDFs into interactive knowledge graphsExtract entities and relations from financial earnings reportsOn-premise document extraction with local vLLM modelsSemantic search over extracted knowledge basesIncrementally update/roll back a knowledge base as sources changeAudit which document contributed which factExport extracted graphs into an Obsidian vault with wikilinksBuild hypergraph and spatio-temporal extractions from textZero-code domain extraction via 80+ YAML templatesUse as an MCP server for agent-driven extractionIngest Word/PowerPoint/Excel/EPUB documentsCompare GraphRAG, LightRAG and Hyper-RAG extraction engines
Built With
- Language
- Python
- Frameworks
- LangChain · FAISS · Pydantic · Typer · Rich · MCP SDK · vLLM · mkdocs · pytest
Tags
knowledge-graph · hypergraph · information-extraction · rag · graphrag · lightrag · semantic-search · embeddings · llm · cli · langchain · faiss · incremental-update · provenance · obsidian-export · mcp