←back to thread

20 points aljgz | 1 comments | | HN request time: 0.202s | source

Have you had the experience of using/developing knowledge bases? Here is my scenario:

My team is dealing with a lot of information: Wikis, Code repos, Monitoring dashboards, internal chat messages, emails, Task tickets, related systems, etc.

There are many cases when we need to do ad-hoc searches for anything related to a concept. For instance, imagine if someone makes a change to a metric, there is a need to find all dashboards that might be using this metric to make sure they are still valid after the change.

I don't want to just fix this problem, but create the ability to find related information in ad-hoc cases.

The ramp-up time is not important, as long as some positive value can be created with a small initial effort.

Any existing products (Paid/Free/Open Source, etc) and any references to existing knowledge (designs, discussions) about this would be really appreciated.

1. TomasBM ◴[] No.45610160[source]
You might want to look into knowledge graphs (KGs), graph databases, ontologies, and similar.

I personally and professionally used these to do some cool things, like run audits across different systems simultaneously. Common stack would include Protege for creating the ontologies (i.e., a schema of how the things you're interested in link to each other), Ontotext Refine or py scripts to populate the graphs, and Ontotext GraphDB or Neo4j AuraDB for storing them.

It's relatively easy to then connect this knowledge base to an LLM, and get more flexibility out of it.

That said, there aren't that many user-friendly tools that get the most out of KGs. Most people I worked with weren't interested in KGs or knowledge bases themselves, they just wanted their particular problem solved. And often, it was easier to justify purchasing a subscription to managed tools that (claim to) solve the problem.

So, unless you're OK with building some middleware to combine user apps with KGs, it won't stick with others, in my experience.