Hierarchical RAG architecture scaling to 693K chunks on consumer hardware (4GB VRAM). Features 3-address routing, hybrid vector+graph fusion, and SetFit classification.
-
Updated
Feb 9, 2026 - Python
Hierarchical RAG architecture scaling to 693K chunks on consumer hardware (4GB VRAM). Features 3-address routing, hybrid vector+graph fusion, and SetFit classification.
Schema-driven long-term memory layer for LLMs and agents. Video walkthrough: https://youtu.be/Efa-n6bWVzE?si=81STTdWayP0wizk1
Add a description, image, and links to the vector-databse topic page so that developers can more easily learn about it.
To associate your repository with the vector-databse topic, visit your repo's landing page and select "manage topics."