RManLuo/gfm-rag
[NeurIPS'25, ICLR'26] Graph Foundation Model for Retrieval Augmented Generation
This project helps domain experts and researchers get more accurate answers from large language models (LLMs) by giving them relevant information from a collection of documents. It takes your documents and questions, builds a "knowledge graph" to understand relationships, and then uses that graph to find the most relevant document snippets for the LLM to use. Anyone who needs to extract precise answers from vast amounts of text will find this useful.
222 stars.
Use this if you need an LLM to answer complex questions by reasoning across multiple related pieces of information within your document collection.
Not ideal if your questions are simple lookups or your documents lack interconnected concepts that would benefit from a knowledge graph.
Stars
222
Forks
26
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/RManLuo/gfm-rag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
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