Slightly than storing information in rows and columns for conventional searches, or as embeddings for vector search, a information graph represents information factors as nodes and edges. A node shall be a definite reality or attribute, and edges will join all of the nodes which have related relationships to that reality. Within the instance of a product catalog, the nodes often is the particular person merchandise whereas the sides shall be comparable traits that every of these merchandise possess, like measurement or coloration.

Sending a question to a information graph includes on the lookout for all of the related entities to that search, after which making a information sub-graph that brings all these entities collectively. This retrieves the related info for the question, which may then be returned again to the LLM and used to construct the response. This implies which you can cope with the issue of getting a number of comparable information sources. Slightly than treating every of those sources as distinct and retrieving the identical information a number of instances, the information shall be retrieved as soon as.

To make use of a information graph along with your RAG software, you possibly can both use an present information graph with information that’s examined and recognized to be right prematurely, or create your individual. When you find yourself utilizing your individual information—corresponding to your product catalog—it would be best to curate the information and examine that it’s correct.