datastax/graph-rag
Graph traversal for improved RAG
This project helps developers enhance their Retrieval Augmented Generation (RAG) applications by combining traditional vector search with the ability to traverse relationships within their existing data. It takes in an existing vector store and a definition of how data points are connected, then provides a more contextually rich set of retrieved documents. The end-user is a developer building intelligent applications that need to retrieve information.
No commits in the last 6 months.
Use this if you are a developer building RAG applications and need to retrieve information based on both semantic similarity and explicit relationships within your data.
Not ideal if you are not a developer or if your application does not require navigating structured relationships within your vector store.
Stars
81
Forks
27
Language
Python
License
Apache-2.0
Category
Last pushed
May 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/datastax/graph-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
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