knowledge-reduce-core
源码High-performance Knowledge-RAG pipeline featuring self-correcting LLM critique loops, MLX fine-tuning, real-time watcher daemons, pluggable local KùzuDB/cloud Neo4j graph stores, and an interactive 3D WebGL dashboard.
High-performance Knowledge-RAG pipeline featuring self-correcting LLM critique loops, MLX fine-tuning, real-time watcher daemons, pluggable local KùzuDB/cloud Neo4j graph stores, and an interactive 3D WebGL dashboard.