[IanCal]

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.

[fishmicrowaver]

Isn't this exactly what neo4j does for graphrag?

[IanCal]

Is that vectors for edges or for searching the nodes? I’m talking about encoding the edges as vectors for traversal.

[fishmicrowaver]

Yes you can do that with neo4j.

[IanCal]

Interesting, thanks, I'll have to explore that.