Liu-rj/PolyG
PolyG: Adaptive Graph Traversal for Diverse GraphRAG Questions
PolyG helps you get more accurate and comprehensive answers from large language models (LLMs) when querying complex knowledge graphs. It takes your natural language questions about entities, relationships, or facts within a knowledge graph and provides a detailed, relevant answer by intelligently navigating the graph. This is for researchers, analysts, or anyone who needs to extract precise information from interconnected data like academic papers, literature, or e-commerce product catalogs.
Use this if you need to reliably extract specific and diverse information from large, interconnected datasets using natural language questions.
Not ideal if your questions are simple, standalone fact queries that don't require traversing relationships within a graph.
Stars
11
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Liu-rj/PolyG"
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
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...
FalkorDB/GraphRAG-SDK
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
getzep/graphiti
Build Real-Time Knowledge Graphs for AI Agents