zilliztech/vector-graph-rag

Graph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.

47
/ 100
Emerging

Encodes entities and relations as vectors in Milvus, eliminating the need for dedicated graph databases while replacing iterative LLM agent loops with a single reranking pass. Supports automatic triplet extraction from unstructured documents via LLM, optional pre-extracted knowledge graphs, and subgraph expansion for multi-hop traversal—all backed by Milvus Lite (zero-config local storage) or Zilliz Cloud for production deployments.

Available on PyPI.

Maintenance 10 / 25
Adoption 7 / 25
Maturity 18 / 25
Community 12 / 25

How are scores calculated?

Stars

2

Forks

1

Language

Python

License

MIT

Last pushed

Mar 05, 2026

Monthly downloads

131

Commits (30d)

0

Dependencies

15

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/zilliztech/vector-graph-rag"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.