Re:Memary is a cutting-edge long-term memory system based on...
by dbish on Monday April 29, 2024 @10:52AM
(#40199089)
Yes, but this doesn’t seem to be an actual knowledge graph which is part of the issue imho. If you look at the Microsoft knowledge graph paper linked in the repo it looks like they build out a real entity-relationship based knowledge graph rather then storing responses and surface form text directly.
Re:Memary is a cutting-edge long-term memory system based on...
by jjfoooo6 on Monday April 29, 2024 @03:49PM
(#40203239)
I think it's relatively unlikely that having an agent write graph queries will outperform vector search against graph information outputted into text and then transformed into vectors.
The related issue that I think is being conflated in this thread is that even if your goal was to directly support graph queries, you could accomplish this with a vanilla database much easier than running a specialized graph db
Re:Memary is a cutting-edge long-term memory system based on...
by gaogao on Monday April 29, 2024 @05:41PM
(#40204460)
Outperform in what way? There's some distinct things it already does better on like multi-hop and aggregate reasoning than a similarity context window dump. In general, tool-assisted, of which KG querying is one tool, does pretty good on the benchmarks and many of the LLM chats cutting over to it as the default.
> if your goal was to directly support graph queries, you could accomplish this with a vanilla database much easier than running a specialized graph db
Postgres and MySQL do have pretty reasonable graph query extensions/features. If by easier, you mean effort to get up a MVP, I'd agree, but I'm a bit more dubious on the scale up, as you'd probably get something like Facebook and Tao.
I need to dig into what they're doing here more with their approach, but I think using an LLM for both producing and consuming a knowledge graph is pretty nifty, which I wrote up about a year ago here, https://friend.computer/jekyll/update/2023/04/30/wikidata-ll... .
I will say figuring out how to actually add that conversation properly into a large knowledge graph is a bit tricky. ML does seem slightly better at producing an ontology than humans though (look how many times we've had to revise scientific names for creatures or book ordering)