DataArcTech/ToG-3
Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval
This project helps AI engineers and researchers build sophisticated RAG (Retrieval-Augmented Generation) systems that can pull information from various sources to provide more accurate and context-aware responses. It takes in structured knowledge graphs, unstructured text, and even images, then outputs enhanced LLM capabilities for tasks like intelligent querying and content generation. The primary users are AI/ML practitioners developing advanced LLM applications.
Use this if you are an AI developer or researcher who needs a modular framework to build and experiment with advanced RAG pipelines, especially those involving knowledge graphs or multi-modal data.
Not ideal if you are looking for an out-of-the-box, end-user application or if your needs are limited to simple, vector-database-only RAG without complex graph structures or multi-modal inputs.
Stars
76
Forks
11
Language
Python
License
MIT
Category
Last pushed
Dec 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/DataArcTech/ToG-3"
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