📄️ 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.
📄️ Storing Knowledge Cores
If you plan on storing a knowledge core, the storage scripts must be started PRIOR to beginning to the Naive Extraction process.
📄️ Loading Knowledge Cores
Identify a Knowledge Core to load into TrustGraph.
📄️ Custom Knowledge Configuration
One of the most powerful aspects of using knowledge graphs is the ability to "mash" disparate knowledge sets into the same graph store. Loading Knowledge Cores into TrustGraph enables making RAG requests over that entire set of knowledge. The RAG algorithms will traverse the entire knowledge graph, likely finding semantic relationships that link seemingly disparate knowledge sets.