Quite 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 would be the particular person merchandise whereas the perimeters shall be comparable traits that every of these merchandise possess, like dimension or coloration.
Sending a question to a information graph includes in search of 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 that you could take care of the issue of getting a number of comparable information sources. Quite than treating every of those sources as distinct and retrieving the identical information a number of occasions, the information shall be retrieved as soon as.
Utilizing a information graph with RAG
To make use of a information graph along with your RAG software, you’ll be able to both use an current information graph with information that’s examined and recognized to be appropriate prematurely, or create your personal. When you find yourself utilizing your personal information—resembling your product catalog—it would be best to curate the information and examine that it’s correct.
