Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How NASA Is Using Graph Technology and LLMs to Build a People Knowledge Graph

memgraph.com

Post reply on HN
Print view View original

41–50 of 56 posts

Re: How NASA Is Using Graph Technology and LLMs to Build a People Knowledge Graph

#41

Post by kendallgclark »

smarx007 wrote: post #25
mbuda wrote: post #12

Earlier quoted context omitted.

DISCLAIMER: The co-founder and CTO of Memgraph here. To add more context, Memgraph Enterprise pricing is explained under https://memgraph.com/pricing : "Starting at $25,000 per year for 16 GB, Memgraph has an all-inclusive, simple pricing model that scales with your workload without restrictions. No charge for compute. No charge for replicas. No charge for algorithms. No Surprises.". In addition, Memgraph Community i…

I think on this site anything that's more expensive than free is considered expensive. Countless arguments have been had on Oracle vs Postgres, including lock-in. I think lock-in is more important to consider than license cost. To be fair, it is quite nice for the pricing to be transparent. And I think it's somewhat competitive w.r.t. Stardog, for example. The community version is less restricted than Ontotext, for e…

Not really competitive with Stardog given our leading LLM integration with Voicebox. 85% pass@1 to exit POV with new customer.

Re: How NASA Is Using Graph Technology and LLMs to Build a People Knowledge Graph

#42

Post by UltraSane »

smarx007 wrote: post #40
UltraSane wrote: post #37

Earlier quoted context omitted.

"They do not allow structure-preserving querying. That is, I query a graph and want the results to be a smaller graph." I'm not sure what you mean by this. The result of a query in neo4j is a set of nodes with specified relations linking them. It is much more flexible than the way SQL can only return a single table.

Query result in openCypher is a similar rectangular result set like in SQL. See openCypher spec p. 74.

"In the RETURN part of your query, you define which parts of the pattern you are interested in. It can be nodes, relationships, or properties on these"

you can return all nodes, relationships, and paths that match a query by using this syntax

MATCH p = (a {name: 'A'})-[r]->(b) RETURN *

This is the exact opposite of a rectangular result set.

Re: How NASA Is Using Graph Technology and LLMs to Build a People Knowledge Graph

#43

Post by dgllghr »

UltraSane wrote: post #38
dgllghr wrote: post #29

Earlier quoted context omitted.

I believe AGE has unfortunately been defunded: https://github.com/apache/age/discussions/2150 It’s a shame because it seemed like being able to query data across multiple paradigms would be really useful

My dream databases is Neo4j style relationships and MongoDB style documents.

Databases like that do exist. There is ArangoDB for example. I have no idea if it’s any good

Re: How NASA Is Using Graph Technology and LLMs to Build a People Knowledge Graph

#44

Post by rage4774 »

gitroom wrote: post #27

Man, love seeing pushback on automated skill matchingsometimes feels like tech folks keep inventing new tools just to dodge actual conversations. Ever wonder if all this automation just makes things colder instead of smarter?

And slower, if we‘re honest, since they never solve issues they intend to solve 100% and human attention is still needed (which is good)

Re: How NASA Is Using Graph Technology and LLMs to Build a People Knowledge Graph

#45

Post by grounder »

UltraSane wrote: post #38
dgllghr wrote: post #29

Earlier quoted context omitted.

I believe AGE has unfortunately been defunded: https://github.com/apache/age/discussions/2150 It’s a shame because it seemed like being able to query data across multiple paradigms would be really useful

My dream databases is Neo4j style relationships and MongoDB style documents.

Check out SurrealDB. It might be exactly what you're looking for. https://surrealdb.com/

Re: How NASA Is Using Graph Technology and LLMs to Build a People Knowledge Graph

#47

Post by jcgrillo »

UltraSane wrote: post #36
jcgrillo wrote: post #28

Earlier quoted context omitted.

Are there any? My experience so far with graph databases is a resounding failure.

I'm using Neo4j to build a CMDB and it is awesome.

That's good to hear, how large is the graph you're building (nodes, edges) and how do queries perform?
Post reply on HN