Connected-Data/cdkg-challenge
Let’s build a curated Knowledge Graph based on the collective wisdom of 260+ experts
**Technical Summary:** Extracts knowledge from 150+ expert conference talks via transcript processing and LLM-powered entity/relationship extraction, storing results in a property graph (Kuzu) with domain and lexical schemas. The project provides raw transcripts, curated metadata, evaluation QA datasets, and source code to enable community contributions toward production-ready knowledge graph curation. Targets downstream applications through public query APIs and plans visualization/natural language interfaces for knowledge discovery.
Stars
41
Forks
8
Language
Python
License
MIT
Category
Last pushed
Oct 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Connected-Data/cdkg-challenge"
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