KAG
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.
OpenSPG/KAG
View on GitHub ↗KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.
KAG grew +0.6% in the last 30 days, ranks 95th of 1,530 in Memory & Knowledge (RAG), last commit 267 days ago.
Star trajectory
123 days tracked+0.6% in 30d, below the Memory & Knowledge (RAG) median of +1.0%.
Last commit 267 days ago, staler than the median of 16d.
How it compares in Memory & Knowledge (RAG)
Ranked 95th of 1,530 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 25
- Forks
- 721
- Watchers
- 80
- Open issues
- 164
- Releases
- 6
- Created
- 2024-09-21
- Stars this week
- +15
You've seen where KAG stands today.
Get the moves before everyone else: the 5 Memory & Knowledge (RAG) repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.