Re:Why RDF Is the Natural Knowledge Layer for AI Systems
by IanCal on Friday September 05, 2025 @09:23AM
(#45138281)
I had the idea a few hours ago so I'm sure there are holes in this but my first idea is forming a graph where the relationship isn't a fixed label but a description that is then embedded as a vector.
First of all, consider that in a way each edge label is a one-hot binary vector. And we search using only binary methods. A consequence is anything outside of that very narrow path all data is missed in a search. A simple step could be to change that to anything within an X similarity to some target vector. Could you then search "(fixed term) is a love interest of b?" and have b? filled from facts like "(fixed term) is intimate with Y" and "(fixed term) has a date with Z"?
There are probably issues, I'm sure there are, but some blend of querying but with some fuzziness feels potentially useful.
Re:Why RDF Is the Natural Knowledge Layer for AI Systems
by fishmicrowaver on Friday September 05, 2025 @07:55PM
(#45145098)
Isn't this exactly what neo4j does for graphrag?
Re:Why RDF Is the Natural Knowledge Layer for AI Systems
by IanCal on Saturday September 06, 2025 @05:34AM
(#45147870)
Is that vectors for edges or for searching the nodes? I’m talking about encoding the edges as vectors for traversal.
Re:Why RDF Is the Natural Knowledge Layer for AI Systems
by fishmicrowaver on Saturday September 06, 2025 @08:17AM
(#45148619)
Yes you can do that with neo4j.
Curious: how would you imagine it working if there were such a graph db?