Reasonably than storing information in rows and columns for conventional searches, or as embeddings for vector search, a data graph represents information factors as nodes and edges. A node will likely be a definite truth or attribute, and edges will join all of the nodes which have related relationships to that truth. Within the instance of a product catalog, the nodes could be the particular person merchandise whereas the sides will likely be related traits that every of these merchandise possess, like dimension or coloration.
Sending a question to a data graph includes on the lookout for all of the related entities to that search, after which making a data sub-graph that brings all these entities collectively. This retrieves the related data for the question, which might then be returned again to the LLM and used to construct the response. This implies which you can take care of the issue of getting a number of related information sources. Reasonably than treating every of those sources as distinct and retrieving the identical information a number of occasions, the info will likely be retrieved as soon as.
Utilizing a data graph with RAG
To make use of a data graph along with your RAG software, you’ll be able to both use an current data graph with information that’s examined and recognized to be appropriate prematurely, or create your personal. If you find yourself utilizing your personal information—akin to your product catalog—it would be best to curate the info and test that it’s correct.