DylanTartarini1996/knowledge-graphs
Create and interact with Knowledge Graphs using Generative AI
Supports GraphRAG by combining vector embeddings with Neo4j graph databases to enable inter-document reasoning through entity extraction and relationship mapping. Provides a modular pipeline that chunks documents, embeds them, and uses LLM agents to construct knowledge graphs with ontology-aware node/relationship extraction. Integrates with Ollama, OpenAI, and Groq for LLMs/embeddings, and includes a Streamlit interface with Docker setup for local deployment including containerized Neo4j with APOC support.
Stars
27
Forks
9
Language
Python
License
GPL-3.0
Category
Last pushed
Dec 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/DylanTartarini1996/knowledge-graphs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
neo4j/neo4j-graphrag-python
Neo4j GraphRAG for Python
FalkorDB/GraphRAG-SDK
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
Hawksight-AI/semantica
Semantica 🧠— A framework for building semantic layers, context graphs, and decision...
gusye1234/nano-graphrag
A simple, easy-to-hack GraphRAG implementation