The Concept of Knowledge Cores

One of the biggest challenges currently facing RAG architectures is the ability to quickly reuse and integrate knowledge sets. TrustGraph solves this problem by storing the results of the Naive Extraction process in reusable Knowledge Cores. Being able to store and reuse the Knowledge Cores means the Naive Extraction process has to be run only one time for a given text corpus. These reusable Knowledge Cores can be loaded back into TrustGraph and used for RAG.

A Knowledge Core has two components:

• Set of Graph Edges
• Set of mapped Vector Embeddings

When a Knowledge Core is loaded into TrustGraph, a loader script places the graph edges and vector embeddings in queues where they are loaded into the chosen graph store, Cassandra or Neo4j, and then Qdrant.