BaranziniLab/KG_RAG
Empower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks
Extracts minimal "prompt-aware context" from the SPOKE biomedical knowledge graph (27M nodes, 53M edges across 40+ repositories) to augment LLM responses with domain-specific facts. Supports both OpenAI/Azure GPT and local Llama inference with interactive step-by-step debugging modes, using vector databases for disease-concept retrieval and graph traversal to identify relevant entity relationships without exhaustive KG querying.
938 stars. No commits in the last 6 months.
Stars
938
Forks
111
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Nov 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/BaranziniLab/KG_RAG"
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