PeterGriffinJin/Graph-CoT
Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs (ACL 2024)
This project helps developers augment Large Language Models (LLMs) by enabling them to reason over structured graph data. It takes questions and a text-attributed graph as input, and outputs more accurate answers by guiding the LLM to traverse the graph step-by-step to find relevant information. This is useful for AI/ML researchers and data scientists working on improving LLM reliability and reducing 'hallucinations'.
300 stars. No commits in the last 6 months.
Use this if you are a researcher or developer looking to improve the factual accuracy and reasoning capabilities of LLMs by incorporating external knowledge presented as interconnected graphs.
Not ideal if you need a plug-and-play solution for end-users, or if your external knowledge sources are solely unstructured text documents without explicit connections.
Stars
300
Forks
31
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Dec 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/PeterGriffinJin/Graph-CoT"
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