Live data from Hacker News

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

memgraph.com

31–40 of 56 posts

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

#31

Earlier quoted context omitted.

If you want a production-grade graph DBMS, you don't have that many OSS options that are reliable and well-supported. In the relational space, it took OSS options like Postgres many decades (and somehow paid-for person-years) to get to a place where enterprises seriously consider migrating off Oracle to it.

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

In OSS or generally?

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

#34
post #24
post #18

I think I found a place Dodge can save some money. Memgraph pricing is ridiculous.

Even paying a college grad to babysit a server costs more than their yearly rate. I assume you're speaking as someone who loves to host everything for themselves, but the logic is surely different in enterprise/government, no?

It depends on your usage models, but if you compare it to AWS Neptune, the pricing seems quite high. I doubt NASA is running queries 24x7 for this use case so other options could be less expensive.

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

#36

Earlier quoted context omitted.

If you want a production-grade graph DBMS, you don't have that many OSS options that are reliable and well-supported. In the relational space, it took OSS options like Postgres many decades (and somehow paid-for person-years) to get to a place where enterprises seriously consider migrating off Oracle to it.

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.

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

#37

> "To make sure everyone understands that, I prefer label property graphs over RDF." I have two major issues with virtually all graph DBMSs that are not RDF/SPARQL-based: 1) They do not allow structure-preserving querying. That is, I query a graph and want the results to be a smaller graph. This is trivial in SQL, you just 'SELECT * FROM x WHERE ...' and the result set you get is tabular just like the table x. In SPA…

"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.

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

#38
post #29
post #6

As an alternative to a pure graph db (e.g. here, memgraph), has anyone here used Apache's AGE graph-database extension for Postgresql? For making a knowledge graph that can live alongside SQL?

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.

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

#39
The use case at NASA isn’t even new. We built this precise thing in 2008. All standards-based.

See https://www.w3.org/2001/sw/sweo/public/UseCases/Nasa/ for a public case study.

This work led to Stardog.

Which is used extensively in NASA today—

https://gpdisonline.com/wp-content/uploads/2019/09/StardogNA...

https://www.informationweek.com/machine-learning-ai/stardog-...

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

#40

> "To make sure everyone understands that, I prefer label property graphs over RDF." I have two major issues with virtually all graph DBMSs that are not RDF/SPARQL-based: 1) They do not allow structure-preserving querying. That is, I query a graph and want the results to be a smaller graph. This is trivial in SQL, you just 'SELECT * FROM x WHERE ...' and the result set you get is tabular just like the table x. In SPA…

"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.
Post reply on HN